Codex compatibility note:
- Invoke repository skills with
$skill-name in Codex; this mirrored copy rewrites legacy Claude /skill-name references.
- Task tracker mandate: BEFORE executing any workflow or skill step, create/update task tracking for all steps and keep it synchronized as progress changes.
- User-question prompts mean to ask the user directly in Codex.
- Ignore Claude-specific mode-switch instructions when they appear.
- Strict execution contract: when a user explicitly invokes a skill, execute that skill protocol as written.
- Subagent authorization: when a skill is user-invoked or AI-detected and its protocol requires subagents, that skill activation authorizes use of the required
spawn_agent subagent(s) for that task.
- Do not skip, reorder, or merge protocol steps unless the user explicitly approves the deviation first.
- For workflow skills, execute each listed child-skill step explicitly and report step-by-step evidence.
- If a required step/tool cannot run in this environment, stop and ask the user before adapting.
Codex Project-Reference Loading (No Hooks)
Codex uses static project-reference loading instead of runtime-injected project docs.
When coding, planning, debugging, testing, or reviewing, open project docs explicitly using this routing.
Always read:
docs/project-config.json (project-specific paths, commands, modules, and workflow/test settings)
docs/project-reference/docs-index-reference.md (routes to the full docs/project-reference/* catalog)
docs/project-reference/lessons.md (always-on guardrails and anti-patterns)
Missing/stale context route: If docs/project-config.json, the docs index, lessons.md, CLAUDE.md, AGENTS.md, or any task-required reference doc is missing or stale, auto-run $project-init or the narrow setup route ($project-config, $docs-init, $scan-all, $scan --target=<key>, $claude-md-init) before ordinary project-specific work. If Codex mirrors or AGENTS.md are missing/stale, ask the user to run $sync-codex; do not auto-run it.
Situation-based docs:
- Project structure/architecture/tech-stack/deployment/setup (any layer — backend, frontend, or infra):
project-structure-reference.md
- Backend/CQRS/API/domain/entity changes:
backend-patterns-reference.md, domain-entities-reference.md
- Frontend/UI/styling/design-system:
frontend-patterns-reference.md, scss-styling-guide.md, design-system/README.md
- Spec authoring,
docs/specs/ pathing, or TC format: feature-spec-reference.md, spec-system-reference.md, spec-principles.md
- Behavior/public-contract changes or spec-test-code sync:
workflow-spec-test-code-cycle-reference.md plus the spec docs above
- Derived spec indexes/ERDs/reimplementation guides:
spec-system-reference.md and source Feature Specs under docs/specs/
- Integration test implementation/review:
integration-test-reference.md
- E2E test implementation/review:
e2e-test-reference.md
- Code review/audit work:
code-review-rules.md plus domain docs above based on changed files
Do not read all docs blindly. Start from docs-index-reference.md, then open only relevant files for the task.
[BLOCKING] Execute skill steps in declared order. NEVER skip, reorder, or merge steps without explicit user approval.
[BLOCKING] Before each step or sub-skill call, update task tracking: set in_progress when step starts, set completed when step ends.
[BLOCKING] Every completed/skipped step MUST include brief evidence or explicit skip reason.
[BLOCKING] If Task tools are unavailable, create and maintain an equivalent step-by-step plan tracker with the same status transitions.
Quick Summary
Goal: Close the gap between a spec artifact that is internally well-formed and one that is COMPLETE-AND-CONFIRMED against the broader discovered system — so the artifact (a freshly-authored Feature Spec, an existing canonical spec headed for decomposition, or a refined idea + §8 test-specs) is finalized only after every related/affected behavior is reflected, every needed and pre-existing invariant is captured, every encoded assumption is classified, and every NON-OBVIOUS or CONFLICTING decision has been confirmed by the user through an exhaustive-but-budget-bounded blocking clarification gate.
Summary:
- Context-aware (Phase 0): detects which artifact it is validating —
AUTHORED-SPEC (idea-to-spec: a freshly-authored, provisional: true §1-8), EXISTING-SPEC (spec-to-pbi: a non-provisional canonical §1-8 headed for decomposition), or TEST-SPEC (idea-to-pbi deep mode: a refined idea + §8 TCs, no §1-7 draft) — and tunes which sections/categories it audits. The detection precedence + ambiguous→ask the user directly fallback are in Phase 0; the category catalog + per-context audit matrix live in references/clarify-interview.md.
- Main steps (read-this-if-nothing-else — run in order, never skip/merge): Phase 0 detect context + resolve budget → Step 0 resolve the 4 inputs (artifact,
spec-discovery landscape, originating idea, domain-analysis), flag any missing as a finding → Step 1 completeness pass vs the discovered SYSTEM (cross-ref, implied coverage, §8 TCs, invariants, UI interaction surface) → Step 2 category-driven hypothesis/decision audit — walk EVERY applicable category, classify each item OBVIOUS / NON-OBVIOUS / CONFLICTS → Step 3 brainstorm materially-changing open questions + adversarial pre-mortem → Step 4 BLOCKING ask the user directly gate on NON-OBVIOUS + CONFLICTS + high-impact within the MIN-MAX budget → Step 5 apply confirmed decisions to the artifact + Decisions Log → Step 6 validate own findings via $why-review --validate-findings, emit CLARIFIED / NEEDS-AUTHORING-FIX.
- Runs in the validation slot of its flow — AFTER the artifact exists (and, for AUTHORED, after
$artifact-review checks the spec in isolation against the artifact-facing mandates (M1-M5 + M7) and $why-review checks rationale). This skill adds the two things neither does: completeness-vs-the-discovered-system, and a BLOCKING user-confirmation loop on every non-obvious decision.
- It is NOT a duplicate of
artifact-review: that one judges the artifact against itself (sections present, ACs testable, M1-M5 + M7 clean). spec-clarify judges it against the SYSTEM (does it reflect every related spec, every existing invariant, every operation the idea implies) and against the USER (are the encoded assumptions actually what the user wants).
- Exhaustive within a budget: walk EVERY applicable validation category (per the matrix), classify every assumption/default/scope-boundary/ambiguity the artifact encodes as OBVIOUS (document and proceed), NON-OBVIOUS (must confirm with the user), or CONFLICTS (disagrees with a discovered spec or invariant → must reconcile), then route NON-OBVIOUS + CONFLICTS + high-impact items to the gate up to a configured
Spec Validation: questions=MIN-MAX budget (per-context defaults when absent). NEVER silently pick a NON-OBVIOUS decision — the whole value is the active question; the budget (not "ask only a few") is the fatigue control.
- Runs INLINE on the main agent (NOT a sub-agent): the Step 4 clarification gate is a BLOCKING ask the user directly loop, and ask the user directly only works on the main interactive agent — a sub-agent cannot ask the user. Before applying confirmed decisions, validate this skill's OWN findings through the terminal
$why-review --validate-findings gate, at parity with the other review-family skills.
Workflow:
- Phase 0 — Spec-Context Detection — detect
AUTHORED-SPEC / EXISTING-SPEC / TEST-SPEC and resolve the question budget; ambiguous context → 1 ask the user directly to confirm
- Completeness pass — cross-reference the artifact against the discovered system landscape (per-context emphasis); find missing stories/AC/rules/TCs and uncovered invariants
- Hypothesis & decision audit (category-driven) — walk every applicable category in
references/clarify-interview.md; enumerate and classify every encoded assumption as OBVIOUS / NON-OBVIOUS / CONFLICTS
- Brainstorm open questions — questions whose answers would change the artifact + a pre-mortem
- Clarification gate — BLOCKING ask the user directly on NON-OBVIOUS + CONFLICTS + high-impact items, exhaustive within the MIN-MAX budget (≤4/call, recommended-first)
- Apply — write confirmed decisions back into the artifact + a Decisions Log
- Report + verdict — CLARIFIED or NEEDS-AUTHORING-FIX, after validating own findings
Key Rules:
- Detect the validation context FIRST (Phase 0); it tunes which sections/categories are audited and the question budget. Ambiguous → confirm with one ask the user directly.
- Completeness is judged against the SYSTEM, not the artifact alone — every related/affected behavior must be reflected.
- Walk EVERY applicable category (breadth is mandatory); route NON-OBVIOUS + CONFLICTS + high-impact items to the gate up to the configured/default budget. The budget — not "surface only a few" — is the fatigue control.
- NON-OBVIOUS and CONFLICTS decisions MUST go to the user; only OBVIOUS decisions are documented-and-proceeded.
- Runs INLINE (no
execution-mode: subagent) because the clarification gate needs ask the user directly, which requires the main interactive agent.
- This complements — never duplicates —
artifact-review (isolation / M1-M5 + M7) and why-review (rationale).
Be skeptical. Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence percentages (Idea should be more than 80%).
Why This Skill Exists
A Feature Spec can be internally perfect — all 8 sections present, every AC testable, every prose line tech-agnostic — and still be WRONG, because:
- It silently omits a related behavior the discovered system already owns (a spec that doesn't reflect an adjacent capability's invariant ships a contradiction).
- It encodes a default, scope boundary, or ambiguous behavior that the AUTHOR picked but the USER never confirmed (the most expensive specs fail not on what they said, but on what they assumed without asking).
- It leaves open questions whose answers would materially change §1-8 — and nobody surfaced them before code started.
artifact-review --type=spec-tests and --type=design check the spec in isolation against the artifact-facing mandates (M1-M5 + M7 — M6 binds the reviewer, not the artifact) and an adversarial section-quality checklist. why-review checks the rationale of decisions already made. Neither one (a) cross-references the spec against the broader discovered system, nor (b) actively ASKS THE USER to confirm the non-obvious choices. spec-clarify is the gate that does both — completeness-vs-system plus a blocking human-confirmation loop — so the spec is finalized confirmed, not merely well-formed.
Delineation from sibling skills (so reviewers see NO duplication):
| Skill |
Judges the spec against… |
Output |
Asks the user? |
artifact-review --type=spec-tests / --type=design |
ITSELF — artifact-facing mandates (M1-M5 + M7), AC testability, adversarial section quality |
PASS / WARN / FAIL |
No (AI self-review) |
why-review |
the RATIONALE of its decisions |
PASS / NEEDS-WORK + validated findings |
Only to escalate (ask the user directly) |
spec-clarify (this skill) |
the SYSTEM + the USER — completeness vs discovered landscape, confirmed decisions |
CLARIFIED / NEEDS-AUTHORING-FIX |
YES — blocking gate on every non-obvious decision |
Why not just extend artifact-review? Self-review cannot ask the user, and adding a blocking interactive gate to a skill designed to run as a fresh sub-agent breaks the sub-agent contract (a sub-agent cannot run ask the user directly). The completeness-vs-system pass and the human-confirmation loop need a distinct, inline invocation point.
Alternatives Considered
| Approach |
Pros |
Cons |
Decision |
Add a "completeness + confirm" phase to artifact-review --type=spec-tests |
No new skill; one place to maintain |
artifact-review runs fresh sub-agents for re-review; a sub-agent cannot run ask the user directly, so the confirm loop is impossible there |
Rejected — the blocking user gate is structurally incompatible with the sub-agent re-review model |
Fold the open-questions brainstorm into why-review |
why-review already does adversarial rationale work |
why-review validates decisions already MADE; it does not surface decisions the author never realized they made, nor confirm them with the user |
Rejected — different purpose (rationale of made decisions vs surfacing+confirming unmade ones) |
| Fully autonomous — AI resolves every ambiguity by best-guess, no user gate |
Fastest; no human round-trip |
Automation bias: a silently-picked NON-OBVIOUS default ships a spec the user never agreed to; the failure surfaces only in code |
Rejected — the cost of a wrong silent default exceeds one confirmation round |
| Run BEFORE authoring instead of after |
Catches gaps earlier |
Before authoring there is no concrete artifact to audit for hypotheses/conflicts; the assumptions are not yet encoded |
Rejected — this gate operates on a CONCRETE artifact; earlier discovery is scout/spec-discovery's job |
A separate spec-validate skill (mirroring plan-validate) per flow |
Clean single-purpose per context |
+1 skill per context = SYNC-carrier + mirror + catalog drift; duplicates this skill's completeness-vs-system engine three times |
Rejected — the three contexts share ONE core (audit a concrete artifact vs system + user); a Phase-0 branch over one skill is the lower future-change-cost choice |
| Keep the single AUTHORED context + minimal gate |
Smallest skill |
Fails the two PBI flows (spec-to-pbi has NO spec-decision gate; idea-to-pbi has only plan/PBI gates) and the "ask a lot of questions / all important aspects" intent |
Rejected — leaves the exact gaps this upgrade exists to close |
Risk Assessment
| Risk |
Likelihood |
Impact |
Mitigation |
| Silent decision — AI classifies a NON-OBVIOUS choice as OBVIOUS to avoid asking |
High |
High |
Step 2 forces an explicit OBVIOUS/NON-OBVIOUS/CONFLICTS label per item; the Anti-Rationalization table rebuts "it's obvious"; ambiguity defaults to NON-OBVIOUS |
Overlap creep — drifts into re-checking M1-M5 + M7 / AC testability and duplicates artifact-review |
Medium |
Medium |
Scope is fixed to completeness-vs-system + confirmation; [HARD]→§8 coverage is a CROSS-CHECK only — the detailed TC quality audit is deferred to artifact-review --type=spec-tests |
| Question fatigue — the widened, category-driven audit asks too many questions |
Medium |
Medium |
The configured Spec Validation: questions=MIN-MAX budget (per-context default when absent) is the hard cap; ask ≥MIN only when ≥MIN genuine decisions exist, never invent filler; ≤4 options per ask the user directly call; recommended option first. Only NON-OBVIOUS + CONFLICTS + high-impact items become questions — breadth of probing is exhaustive, breadth of asking is budget-bounded |
| Context mis-detection — Phase 0 picks the wrong context and audits the wrong sections |
Medium |
High |
Explicit detection-precedence table (provisional flag + §-presence + active workflow); ambiguous → 1 ask the user directly to confirm before auditing |
| Unvalidated findings applied — AI rewrites §1-8 from a phantom completeness gap |
Medium |
High |
Step 6 runs $why-review --validate-findings on this skill's own findings BEFORE applying any decision |
| Stale landscape — the discovered-system report is outdated, so completeness is judged against a wrong baseline |
Low |
Medium |
Step 0 verifies the discovery inputs exist and are current; a missing/stale landscape is itself a NEEDS-AUTHORING-FIX finding |
Phase 0: Spec-Context Detection (run FIRST)
Before resolving inputs, detect WHICH artifact is being validated — the context tunes which sections/categories are audited and the question budget. The full per-context audit matrix + category catalog live in references/clarify-interview.md.
| Context |
Signals |
Artifact under validation |
Audit emphasis |
AUTHORED-SPEC |
active idea-to-spec; full §1-8 present; provisional: true frontmatter |
the freshly-authored §1-8 |
full §1-8 |
EXISTING-SPEC |
active spec-to-pbi; full §1-8 present; NOT provisional |
the existing canonical §1-8 |
full §1-8, weighted to decomposition-driving decisions (§3 US/AC, §4 BR, §5 ERD, §6 flows & interaction surface, §7 perms, §8 TCs) |
TEST-SPEC |
active idea-to-pbi deep mode; refined idea + §8 TCs, no §1-7 draft |
refined idea + §8 TCs |
refined-idea coverage + §8 TC decisions + implied rules |
Detection precedence: full §1-8 + provisional: true → AUTHORED-SPEC; full §1-8 + NOT provisional → EXISTING-SPEC; only §8 / refined-idea (no §1-7 draft) → TEST-SPEC. Ambiguous → 1 ask the user directly to confirm the context before auditing.
Question budget: read the injected Spec Validation: questions=MIN-MAX line (workflow injectContext supplies it per flow). When absent (standalone run), fall back to the per-context defaults in references/clarify-interview.md — AUTHORED-SPEC 5-10, EXISTING-SPEC 4-8, TEST-SPEC 3-6. The budget bounds the Step 4 gate: ask ≥MIN when ≥MIN genuine decisions exist, never exceed MAX.
State Context: {AUTHORED-SPEC | EXISTING-SPEC | TEST-SPEC} | Budget: {MIN-MAX} (injected | default) before Step 0.
Inputs (Step 0)
Resolve and confirm these inputs exist BEFORE the completeness pass. A missing input is a finding, not a reason to guess.
- The artifact under validation — resolved per the detected context:
AUTHORED-SPEC / EXISTING-SPEC → the full §1-8 Feature Spec (§1 Overview, §2 Glossary, §3 User Stories & Acceptance Criteria, §4 Business Rules with [HARD]/[SOFT] markers, §5 Domain Model, §6 Process Flows & Interaction Surface, §7 Permissions & Roles, §8 Test Specifications TC-{FEATURE}-{NNN}); TEST-SPEC → the refined idea + the §8 TC set (no §1-7 draft yet). Read docs/project-reference/feature-spec-reference.md + spec-system-reference.md + spec-principles.md first.
- The
spec-discovery landscape report — plans/{plan-dir}/research/spec-discovery-{slug}.md (Related Specs, Related Code, Affected Specs, Gaps, Invariant Landscape, Open Questions), the investigation of related/overlapping/affected specs + code. This is the baseline against which completeness is judged. For TEST-SPEC the landscape also comes from spec-discovery (present in the idea-to-pbi deep-mode sequence). If it is absent (skill run standalone), fall back to scout + investigate plus the derived $spec-index artifacts (index / ERD / reimplementation guide) under docs/specs/, and flag the absence as a finding.
- The originating idea / brainstorm — the requirement that the artifact is meant to satisfy; its implied operations and edge cases drive the missing-coverage check.
- The domain-analysis output — bounded contexts, aggregates, entities, domain events, and the invariants the artifact must respect.
State Inputs resolved: ... | Missing (flag as finding): ... before Step 1.
Workflow
Run Phase 0 (Spec-Context Detection) above first — it sets the context + budget that the steps below consume.
Inputs — resolve the four inputs above (artifact resolved per the detected context); flag any missing one as a finding.
Completeness pass (vs system) — judge the artifact against the discovered landscape, NOT against itself, weighting the sections the context emphasizes (see the per-context matrix in references/clarify-interview.md):
- Cross-reference completeness — every related/affected spec from the landscape is reflected (a behavior the system already owns and this feature touches must appear, or its absence must be deliberate and noted). For
TEST-SPEC, judge the refined idea + §8 set against the landscape.
- Implied coverage — missing user stories / acceptance criteria / business rules the originating idea implies but the artifact omits.
- Test-coverage completeness — missing §8 TCs versus the implied operations + their edge cases (presence/scope only).
- Invariant coverage — every NEEDED invariant (this feature must establish) AND every EXISTING invariant the artifact must respect (from domain-analysis / adjacent specs) is captured; each
[HARD] §4 rule has at least one §8 property/invariant TC. This is a CROSS-CHECK that the property TC exists — defer the detailed TC-quality audit (universally-quantified property, boundary counter-case, etc.) to artifact-review --type=spec-tests.
- Interaction surface completeness (UI-bearing specs) — judge §6's interaction surface against the implied UI: every view a user story needs is in the §6.2 view inventory by UX role; navigation between views (§6.3) has no dangling entry/exit; each view's observable states (§6.4 — empty/loading/populated/error/success/permission-denied) are present or deliberately absent; every UI-bearing user story has a §6.5 click-path. Backend-only specs must state the §6 skip reason. Presence/scope only — visual fidelity stays in the companion design artifact.
Hypothesis & decision audit (category-driven) — walk EVERY applicable category for the detected context (the 9-category catalog + per-context matrix in references/clarify-interview.md); for each, run its audit prompts to surface every assumption, default value, scope boundary, and ambiguous behavior the artifact encodes. Classify each:
- OBVIOUS — a single reasonable reading any competent reader shares → document it in the Decisions Log and proceed.
- NON-OBVIOUS — more than one defensible reading, or a default the user has not confirmed → candidate for the Step 4 gate.
- CONFLICTS — disagrees with a discovered landscape spec or an existing invariant → MUST be reconciled (and surfaced to the user). Default to NON-OBVIOUS when the classification itself is unclear.
Probing breadth is exhaustive (every applicable category); asking breadth is the budget.
Brainstorm open questions — questions whose answers would MATERIALLY change the artifact (scope, a default, an invariant boundary, an actor/permission). Run an adversarial pre-mortem: "this artifact ships and the feature fails in production within 3 months — what spec gap caused it?" Each pre-mortem failure that maps to a real gap becomes either a NON-OBVIOUS question or a completeness finding.
Interaction Surface category (UI-bearing specs): treat each of these as a gate candidate — an ambiguous view (its UX role or purpose has more than one defensible reading), a missing observable state (a view whose error/empty/permission-denied behavior the spec leaves unstated), and an unmapped click-path (a UI-bearing user story with no §6.5 step path, or a navigation transition with no business trigger). Classify each OBVIOUS / NON-OBVIOUS / CONFLICTS like any other; route NON-OBVIOUS + CONFLICTS to the gate within the budget. Ask about UX intent only — never about framework/route/CSS/component-class detail (that belongs to the companion design artifact).
Clarification gate (BLOCKING ask the user directly) — present the NON-OBVIOUS + CONFLICTS + high-impact items to the user as structured options, exhaustive within the MIN-MAX budget from Phase 0: ask ≥MIN questions when ≥MIN genuine decisions exist, never exceed MAX, ≤4 options per call, the recommended option FIRST, issue multiple ask the user directly calls when there are more than 4 decisions. When fewer than MIN genuine decisions exist, ask only the genuine ones and record "below-MIN: only N real decisions" — NEVER invent filler. Capture each answer. NEVER silently pick a NON-OBVIOUS decision — the active question is the entire point of this gate.
Apply — write the confirmed decisions back into the relevant artifact sections AND record them in an "Open Questions / Decisions Log" (resolved decisions with the user's choice + rationale, plus residual items still below 80% confidence). For AUTHORED-SPEC/EXISTING-SPEC, when the confirmed answers reveal material gaps, loop the spec author via $spec [mode=update] to re-author the affected sections, then re-run Step 1 against the updated spec. For EXISTING-SPEC this skill does NOT itself re-author — confirmed changes route through $spec [mode=update]; for TEST-SPEC the decisions feed PBI decomposition + any $spec [mode=tests] refinement.
Report + verdict — before applying decisions, run $why-review --validate-findings <report-path> on THIS skill's own findings (validate-before-fix discipline, at parity with artifact-review / plan-review); fix/drop any finding the gate flags, then apply only validated decisions. Write the report to plans/reports/spec-clarify-{date}.md and emit a verdict:
- CLARIFIED — every NON-OBVIOUS/CONFLICTS decision confirmed by the user, completeness gaps resolved or accepted, no residual blocking question.
- NEEDS-AUTHORING-FIX — material completeness gap or unreconciled conflict requires re-authoring via
$spec [mode=update] before the spec can be finalized.
Output
## Spec Clarification Report
**Spec:** {spec path}
**Date:** {date}
**Verdict:** CLARIFIED | NEEDS-AUTHORING-FIX
**Confidence:** {X%} — {what was verified vs. what remains residual}
### Completeness (vs discovered system)
| Area | Status | Gap / Evidence (`file:line` or spec/section ref) |
| -------------------------------------- | ------ | ----------------------------------------------------------------------------- |
| Related/affected specs reflected | ✅/❌ | {which related behavior is/ isn't reflected} |
| Implied stories / AC / rules | ✅/❌ | {missing item the idea implies} |
| §8 TC coverage vs operations | ✅/❌ | {operation/edge case with no TC} |
| Invariant coverage (needed + existing) | ✅/❌ | {`[HARD]` rule without a §8 property TC, or existing invariant not respected} |
### Hypothesis & Decision Audit
| # | Encoded assumption / default / boundary | Class (OBVIOUS / NON-OBVIOUS / CONFLICTS) | Evidence |
| --- | --------------------------------------- | ----------------------------------------- | -------- |
| 1 | {assumption} | {class} | {ref} |
### Open Questions (pre-mortem + materially-changing)
1. {question — what changes in §1-8 depending on the answer}
### Decisions Log
| Decision | User's confirmed choice | Applied to | Residual confidence |
| ---------------------- | ------------------------------------ | ---------- | ----------------------- |
| {non-obvious decision} | {answer by asking the user directly} | §{n} | {>=80% / <80% residual} |
### Verdict
{CLARIFIED | NEEDS-AUTHORING-FIX} — {evidence-based justification; if NEEDS-AUTHORING-FIX, the exact `$spec [mode=update]` scope}
Key Rules
- Detect the context FIRST (Phase 0) —
AUTHORED-SPEC / EXISTING-SPEC / TEST-SPEC tunes which sections/categories are audited and the question budget; ambiguous → 1 ask the user directly to confirm before auditing.
- Walk every applicable category, ask within the budget — probing breadth is exhaustive (the 9-category catalog × the per-context matrix in
references/clarify-interview.md); the Spec Validation: questions=MIN-MAX budget (per-context default when absent) caps how many reach the gate. Never invent filler to hit MIN; never exceed MAX.
- Completeness is judged against the SYSTEM — every related/affected behavior from the discovered landscape must be reflected, or its absence deliberately noted. The artifact passing in isolation is NOT enough.
- NON-OBVIOUS and CONFLICTS go to the user — only OBVIOUS decisions are documented-and-proceeded; ambiguity in the classification itself defaults to NON-OBVIOUS.
- NEVER silently pick a non-obvious decision — the blocking ask the user directly gate is the entire value of this skill.
- Runs INLINE, not as a sub-agent — the clarification gate needs ask the user directly, which only the main interactive agent can run; do NOT add
execution-mode: subagent.
- Complements, never duplicates —
artifact-review owns isolation/M1-M5 + M7, why-review owns rationale; cross-check the [HARD]→§8 mapping only and defer the detailed TC-quality audit to artifact-review --type=spec-tests.
- Validate before applying — run
$why-review --validate-findings on this skill's own findings before rewriting any §1-8 section.
- Evidence-based — every completeness gap, classification, and conflict cites
file:line / a spec section / an invariant ref with a confidence percentage.
[IMPORTANT] Use task tracking to break ALL work into small tasks BEFORE starting — including a final review task to verify completeness and that every non-obvious decision was confirmed.
Evidence Gate: MANDATORY IMPORTANT MUST ATTENTION — every claim requires file:line proof or traced evidence with confidence percentage (>80% to act).
Nested Task Expansion Contract — For workflow-step invocation, the [Workflow] ... row is only a parent container; the child skill still creates visible phase tasks.
- Call the current task list first. If a matching active parent workflow row exists, set
nested=true and record parentTaskId; otherwise run standalone.
- Create one task per declared phase before phase work. When nested, prefix subjects
[N.M] $skill-name — phase.
- When nested, link the parent with
TaskUpdate(parentTaskId, addBlockedBy: [childIds]).
- Orchestrators must pre-expand a child skill's phase list and link the workflow row before invoking that child skill or sub-agent.
- Mark exactly one child
in_progress before work and completed immediately after evidence is written.
- Complete the parent only after all child tasks are completed or explicitly cancelled with reason.
Blocked until: the current task list done, child phases created, parent linked when nested, first child marked in_progress.
Project Reference Docs Gate — Run after task-tracking bootstrap and before target/source file reads, grep, edits, or analysis. Project docs override generic framework assumptions.
- Identify scope: file types, domain area, and operation.
- Read
docs/project-config.json first — the project's machine-readable map. It is the single source of truth for THIS repo (modules/paths, framework + search keywords, test/E2E/integration run-commands, design system, architecture rules, workflow patterns); ground exact paths, run-commands, and conventions on it before investigating, planning, or coding — never assume framework defaults (CLAUDE.md + reference docs are derived from it). If it — or the docs index, lessons.md, CLAUDE.md, AGENTS.md, or any required reference doc — is missing or stale, auto-run $project-init or the narrow route ($project-config, $docs-init, $scan-all, $scan --target=<key>, $claude-md-init) first; if Codex mirrors or AGENTS.md are stale, ask the user to run $sync-codex (never auto-run it).
- Required docs by trigger: always
docs/project-reference/lessons.md; doc lookup docs-index-reference.md; review code-review-rules.md; backend/CQRS/API backend-patterns-reference.md; domain/entity domain-entities-reference.md; frontend/UI frontend-patterns-reference.md; styles/design scss-styling-guide.md + design-system/design-system-canonical.md; integration tests integration-test-reference.md; E2E e2e-test-reference.md; feature docs/specs feature-spec-reference.md + spec-system-reference.md + spec-principles.md; behavior/public-contract/spec-test-code sync workflow-spec-test-code-cycle-reference.md; derived spec index/ERD/reimplementation guides spec-system-reference.md + source Feature Specs under docs/specs/; architecture/new area project-structure-reference.md.
- Read every required doc, then before target work state:
Reference docs read: ... | Not applicable: ....
Ready when: scope evaluated, docs/project-config.json consulted, required docs checked/read or setup route completed, lessons.md confirmed, citation emitted.
Task Tracking & External Report Persistence — Bootstrap this before execution; then run project-reference doc prefetch before target/source work.
- Create a small task breakdown before target file reads, grep, edits, or analysis. On context loss, inspect the current task list first.
- Mark one task
in_progress before work and completed immediately after evidence; never batch transitions.
- For plan/review work, create
plans/reports/{skill}-{YYMMDD}-{HHmm}-{slug}.md before first finding.
- Append findings after each file/section/decision and synthesize from the report file at the end.
- Final output cites
Full report: plans/reports/{filename}.
Blocked until: task breakdown exists, report path declared for plan/review work, first finding persisted before the next finding.
Critical Thinking Mindset — Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence >80% to act.
Anti-hallucination: Never present guess as fact — cite sources for every claim, admit uncertainty freely, self-check output for errors, cross-reference independently, stay skeptical of own confidence — certainty without evidence root of all hallucination.
1---2name: spec-clarify3version: 2.0.04description: '[Code Quality] Use when validating a spec artifact''s decisions with the user — a fresh Feature Spec, a canonical spec before PBI decomposition, or a refined idea plus §8 test specs. Blocking clarification gate.'5context-budget: medium6metadata:7 source: https://skillmd.com/skills/duc01226/spec-clarify8---9
10> Codex compatibility note:
11>
12> - Invoke repository skills with `$skill-name` in Codex; this mirrored copy rewrites legacy Claude `/skill-name` references.
13> - Task tracker mandate: BEFORE executing any workflow or skill step, create/update task tracking for all steps and keep it synchronized as progress changes.
14> - User-question prompts mean to ask the user directly in Codex.
15> - Ignore Claude-specific mode-switch instructions when they appear.
16> - Strict execution contract: when a user explicitly invokes a skill, execute that skill protocol as written.
17> - Subagent authorization: when a skill is user-invoked or AI-detected and its protocol requires subagents, that skill activation authorizes use of the required `spawn_agent` subagent(s) for that task.
18> - Do not skip, reorder, or merge protocol steps unless the user explicitly approves the deviation first.
19> - For workflow skills, execute each listed child-skill step explicitly and report step-by-step evidence.
20> - If a required step/tool cannot run in this environment, stop and ask the user before adapting.
21
22<!-- CODEX:PROJECT-REFERENCE-LOADING:START -->
23
24## Codex Project-Reference Loading (No Hooks)
25
26Codex uses static project-reference loading instead of runtime-injected project docs.
27When coding, planning, debugging, testing, or reviewing, open project docs explicitly using this routing.
28
29**Always read:**
30
31- `docs/project-config.json` (project-specific paths, commands, modules, and workflow/test settings)
32- `docs/project-reference/docs-index-reference.md` (routes to the full `docs/project-reference/*` catalog)
33- `docs/project-reference/lessons.md` (always-on guardrails and anti-patterns)
34
35**Missing/stale context route:** If `docs/project-config.json`, the docs index, `lessons.md`, `CLAUDE.md`, `AGENTS.md`, or any task-required reference doc is missing or stale, auto-run `$project-init` or the narrow setup route (`$project-config`, `$docs-init`, `$scan-all`, `$scan --target=<key>`, `$claude-md-init`) before ordinary project-specific work. If Codex mirrors or `AGENTS.md` are missing/stale, ask the user to run `$sync-codex`; do not auto-run it.
36
37**Situation-based docs:**
38
39- Project structure/architecture/tech-stack/deployment/setup (any layer — backend, frontend, or infra): `project-structure-reference.md`
40- Backend/CQRS/API/domain/entity changes: `backend-patterns-reference.md`, `domain-entities-reference.md`
41- Frontend/UI/styling/design-system: `frontend-patterns-reference.md`, `scss-styling-guide.md`, `design-system/README.md`
42- Spec authoring, `docs/specs/` pathing, or TC format: `feature-spec-reference.md`, `spec-system-reference.md`, `spec-principles.md`
43- Behavior/public-contract changes or spec-test-code sync: `workflow-spec-test-code-cycle-reference.md` plus the spec docs above
44- Derived spec indexes/ERDs/reimplementation guides: `spec-system-reference.md` and source Feature Specs under `docs/specs/`
45- Integration test implementation/review: `integration-test-reference.md`
46- E2E test implementation/review: `e2e-test-reference.md`
47- Code review/audit work: `code-review-rules.md` plus domain docs above based on changed files
48
49Do not read all docs blindly. Start from `docs-index-reference.md`, then open only relevant files for the task.
50
51<!-- CODEX:PROJECT-REFERENCE-LOADING:END -->
52
53<!-- PROMPT-ENHANCE:STEP-TASK-ANCHOR:START -->
54
55> **[BLOCKING]** Execute skill steps in declared order. NEVER skip, reorder, or merge steps without explicit user approval.
56> **[BLOCKING]** Before each step or sub-skill call, update task tracking: set `in_progress` when step starts, set `completed` when step ends.
57> **[BLOCKING]** Every completed/skipped step MUST include brief evidence or explicit skip reason.
58> **[BLOCKING]** If Task tools are unavailable, create and maintain an equivalent step-by-step plan tracker with the same status transitions.
59
60<!-- PROMPT-ENHANCE:STEP-TASK-ANCHOR:END -->
61
62## Quick Summary
63
64**Goal:** Close the gap between a spec artifact that is internally well-formed and one that is COMPLETE-AND-CONFIRMED against the broader discovered system — so the artifact (a freshly-authored Feature Spec, an existing canonical spec headed for decomposition, or a refined idea + §8 test-specs) is finalized only after every related/affected behavior is reflected, every needed and pre-existing invariant is captured, every encoded assumption is classified, and every NON-OBVIOUS or CONFLICTING decision has been confirmed by the user through an exhaustive-but-budget-bounded blocking clarification gate.
65
66**Summary:**
67
68- **Context-aware (Phase 0):** detects which artifact it is validating — `AUTHORED-SPEC` (idea-to-spec: a freshly-authored, `provisional: true` §1-8), `EXISTING-SPEC` (spec-to-pbi: a non-provisional canonical §1-8 headed for decomposition), or `TEST-SPEC` (idea-to-pbi deep mode: a refined idea + §8 TCs, no §1-7 draft) — and tunes which sections/categories it audits. The detection precedence + ambiguous→ask the user directly fallback are in Phase 0; the category catalog + per-context audit matrix live in `references/clarify-interview.md`.
69- **Main steps (read-this-if-nothing-else — run in order, never skip/merge):** Phase 0 detect context + resolve budget → Step 0 resolve the 4 inputs (artifact, `spec-discovery` landscape, originating idea, domain-analysis), flag any missing as a finding → Step 1 completeness pass vs the discovered SYSTEM (cross-ref, implied coverage, §8 TCs, invariants, UI interaction surface) → Step 2 category-driven hypothesis/decision audit — walk EVERY applicable category, classify each item OBVIOUS / NON-OBVIOUS / CONFLICTS → Step 3 brainstorm materially-changing open questions + adversarial pre-mortem → Step 4 BLOCKING ask the user directly gate on NON-OBVIOUS + CONFLICTS + high-impact within the MIN-MAX budget → Step 5 apply confirmed decisions to the artifact + Decisions Log → Step 6 validate own findings via `$why-review --validate-findings`, emit CLARIFIED / NEEDS-AUTHORING-FIX.
70- Runs in the validation slot of its flow — AFTER the artifact exists (and, for AUTHORED, after `$artifact-review` checks the spec in isolation against the artifact-facing mandates (M1-M5 + M7) and `$why-review` checks rationale). This skill adds the two things neither does: completeness-vs-the-discovered-system, and a BLOCKING user-confirmation loop on every non-obvious decision.
71- It is NOT a duplicate of `artifact-review`: that one judges the artifact against itself (sections present, ACs testable, M1-M5 + M7 clean). `spec-clarify` judges it against the SYSTEM (does it reflect every related spec, every existing invariant, every operation the idea implies) and against the USER (are the encoded assumptions actually what the user wants).
72- **Exhaustive within a budget:** walk EVERY applicable validation category (per the matrix), classify every assumption/default/scope-boundary/ambiguity the artifact encodes as **OBVIOUS** (document and proceed), **NON-OBVIOUS** (must confirm with the user), or **CONFLICTS** (disagrees with a discovered spec or invariant → must reconcile), then route NON-OBVIOUS + CONFLICTS + high-impact items to the gate up to a configured `Spec Validation: questions=MIN-MAX` budget (per-context defaults when absent). NEVER silently pick a NON-OBVIOUS decision — the whole value is the active question; the budget (not "ask only a few") is the fatigue control.
73- Runs INLINE on the main agent (NOT a sub-agent): the Step 4 clarification gate is a BLOCKING ask the user directly loop, and ask the user directly only works on the main interactive agent — a sub-agent cannot ask the user. Before applying confirmed decisions, validate this skill's OWN findings through the terminal `$why-review --validate-findings` gate, at parity with the other review-family skills.
74
75**Workflow:**
76
770. **Phase 0 — Spec-Context Detection** — detect `AUTHORED-SPEC` / `EXISTING-SPEC` / `TEST-SPEC` and resolve the question budget; ambiguous context → 1 ask the user directly to confirm
781. **Completeness pass** — cross-reference the artifact against the discovered system landscape (per-context emphasis); find missing stories/AC/rules/TCs and uncovered invariants
792. **Hypothesis & decision audit (category-driven)** — walk every applicable category in `references/clarify-interview.md`; enumerate and classify every encoded assumption as OBVIOUS / NON-OBVIOUS / CONFLICTS
803. **Brainstorm open questions** — questions whose answers would change the artifact + a pre-mortem
814. **Clarification gate** — BLOCKING ask the user directly on NON-OBVIOUS + CONFLICTS + high-impact items, exhaustive within the MIN-MAX budget (≤4/call, recommended-first)
825. **Apply** — write confirmed decisions back into the artifact + a Decisions Log
836. **Report + verdict** — CLARIFIED or NEEDS-AUTHORING-FIX, after validating own findings
84
85**Key Rules:**
86
87- Detect the validation context FIRST (Phase 0); it tunes which sections/categories are audited and the question budget. Ambiguous → confirm with one ask the user directly.
88- Completeness is judged against the SYSTEM, not the artifact alone — every related/affected behavior must be reflected.
89- Walk EVERY applicable category (breadth is mandatory); route NON-OBVIOUS + CONFLICTS + high-impact items to the gate up to the configured/default budget. The budget — not "surface only a few" — is the fatigue control.
90- NON-OBVIOUS and CONFLICTS decisions MUST go to the user; only OBVIOUS decisions are documented-and-proceeded.
91- Runs INLINE (no `execution-mode: subagent`) because the clarification gate needs ask the user directly, which requires the main interactive agent.
92- This complements — never duplicates — `artifact-review` (isolation / M1-M5 + M7) and `why-review` (rationale).
93
94**Be skeptical. Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence percentages (Idea should be more than 80%).**
95
96## Why This Skill Exists
97
98A Feature Spec can be internally perfect — all 8 sections present, every AC testable, every prose line tech-agnostic — and still be WRONG, because:
99
1001. It silently omits a related behavior the discovered system already owns (a spec that doesn't reflect an adjacent capability's invariant ships a contradiction).
1012. It encodes a default, scope boundary, or ambiguous behavior that the AUTHOR picked but the USER never confirmed (the most expensive specs fail not on what they said, but on what they assumed without asking).
1023. It leaves open questions whose answers would materially change §1-8 — and nobody surfaced them before code started.
103
104`artifact-review --type=spec-tests` and `--type=design` check the spec **in isolation** against the artifact-facing mandates (M1-M5 + M7 — M6 binds the reviewer, not the artifact) and an adversarial section-quality checklist. `why-review` checks the **rationale** of decisions already made. Neither one (a) cross-references the spec against the broader discovered system, nor (b) actively ASKS THE USER to confirm the non-obvious choices. `spec-clarify` is the gate that does both — completeness-vs-system plus a blocking human-confirmation loop — so the spec is finalized confirmed, not merely well-formed.
105
106**Delineation from sibling skills (so reviewers see NO duplication):**
107
108| Skill | Judges the spec against… | Output | Asks the user? |
109| ----------------------------------------------------- | ------------------------------------------------------------------------------------------- | -------------------------------------- | ----------------------------------------------------- |
110| `artifact-review --type=spec-tests` / `--type=design` | ITSELF — artifact-facing mandates (M1-M5 + M7), AC testability, adversarial section quality | PASS / WARN / FAIL | No (AI self-review) |
111| `why-review` | the RATIONALE of its decisions | PASS / NEEDS-WORK + validated findings | Only to escalate (ask the user directly) |
112| `spec-clarify` (this skill) | the SYSTEM + the USER — completeness vs discovered landscape, confirmed decisions | CLARIFIED / NEEDS-AUTHORING-FIX | **YES — blocking gate on every non-obvious decision** |
113
114**Why not just extend `artifact-review`?** Self-review cannot ask the user, and adding a blocking interactive gate to a skill designed to run as a fresh sub-agent breaks the sub-agent contract (a sub-agent cannot run ask the user directly). The completeness-vs-system pass and the human-confirmation loop need a distinct, inline invocation point.
115
116## Alternatives Considered
117
118| Approach | Pros | Cons | Decision |
119| --------------------------------------------------------------------------- | ---------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------- |
120| Add a "completeness + confirm" phase to `artifact-review --type=spec-tests` | No new skill; one place to maintain | `artifact-review` runs fresh sub-agents for re-review; a sub-agent cannot run ask the user directly, so the confirm loop is impossible there | Rejected — the blocking user gate is structurally incompatible with the sub-agent re-review model |
121| Fold the open-questions brainstorm into `why-review` | `why-review` already does adversarial rationale work | `why-review` validates decisions already MADE; it does not surface decisions the author never realized they made, nor confirm them with the user | Rejected — different purpose (rationale of made decisions vs surfacing+confirming unmade ones) |
122| Fully autonomous — AI resolves every ambiguity by best-guess, no user gate | Fastest; no human round-trip | Automation bias: a silently-picked NON-OBVIOUS default ships a spec the user never agreed to; the failure surfaces only in code | Rejected — the cost of a wrong silent default exceeds one confirmation round |
123| Run BEFORE authoring instead of after | Catches gaps earlier | Before authoring there is no concrete artifact to audit for hypotheses/conflicts; the assumptions are not yet encoded | Rejected — this gate operates on a CONCRETE artifact; earlier discovery is `scout`/`spec-discovery`'s job |
124| A separate `spec-validate` skill (mirroring `plan-validate`) per flow | Clean single-purpose per context | +1 skill per context = SYNC-carrier + mirror + catalog drift; duplicates this skill's completeness-vs-system engine three times | Rejected — the three contexts share ONE core (audit a concrete artifact vs system + user); a Phase-0 branch over one skill is the lower future-change-cost choice |
125| Keep the single AUTHORED context + minimal gate | Smallest skill | Fails the two PBI flows (spec-to-pbi has NO spec-decision gate; idea-to-pbi has only plan/PBI gates) and the "ask a lot of questions / all important aspects" intent | Rejected — leaves the exact gaps this upgrade exists to close |
126
127## Risk Assessment
128
129| Risk | Likelihood | Impact | Mitigation |
130| ------------------------------------------------------------------------------------------------------------------ | ---------- | ------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
131| **Silent decision** — AI classifies a NON-OBVIOUS choice as OBVIOUS to avoid asking | High | High | Step 2 forces an explicit OBVIOUS/NON-OBVIOUS/CONFLICTS label per item; the Anti-Rationalization table rebuts "it's obvious"; ambiguity defaults to NON-OBVIOUS |
132| **Overlap creep** — drifts into re-checking M1-M5 + M7 / AC testability and duplicates `artifact-review` | Medium | Medium | Scope is fixed to completeness-vs-system + confirmation; `[HARD]`→§8 coverage is a CROSS-CHECK only — the detailed TC quality audit is deferred to `artifact-review --type=spec-tests` |
133| **Question fatigue** — the widened, category-driven audit asks too many questions | Medium | Medium | The configured `Spec Validation: questions=MIN-MAX` budget (per-context default when absent) is the hard cap; ask ≥MIN only when ≥MIN genuine decisions exist, never invent filler; ≤4 options per ask the user directly call; recommended option first. Only NON-OBVIOUS + CONFLICTS + high-impact items become questions — breadth of _probing_ is exhaustive, breadth of _asking_ is budget-bounded |
134| **Context mis-detection** — Phase 0 picks the wrong context and audits the wrong sections | Medium | High | Explicit detection-precedence table (provisional flag + §-presence + active workflow); ambiguous → 1 ask the user directly to confirm before auditing |
135| **Unvalidated findings applied** — AI rewrites §1-8 from a phantom completeness gap | Medium | High | Step 6 runs `$why-review --validate-findings` on this skill's own findings BEFORE applying any decision |
136| **Stale landscape** — the discovered-system report is outdated, so completeness is judged against a wrong baseline | Low | Medium | Step 0 verifies the discovery inputs exist and are current; a missing/stale landscape is itself a NEEDS-AUTHORING-FIX finding |
137
138## Phase 0: Spec-Context Detection (run FIRST)
139
140Before resolving inputs, detect WHICH artifact is being validated — the context tunes which sections/categories are audited and the question budget. The full per-context audit matrix + category catalog live in [`references/clarify-interview.md`](./references/clarify-interview.md).
141
142| Context | Signals | Artifact under validation | Audit emphasis |
143| --------------- | ------------------------------------------------------------------------- | --------------------------- | ---------------------------------------------------------------------------------------------------------------------------------- |
144| `AUTHORED-SPEC` | active `idea-to-spec`; full §1-8 present; `provisional: true` frontmatter | the freshly-authored §1-8 | full §1-8 |
145| `EXISTING-SPEC` | active `spec-to-pbi`; full §1-8 present; NOT provisional | the existing canonical §1-8 | full §1-8, weighted to decomposition-driving decisions (§3 US/AC, §4 BR, §5 ERD, §6 flows & interaction surface, §7 perms, §8 TCs) |
146| `TEST-SPEC` | active `idea-to-pbi` deep mode; refined idea + §8 TCs, no §1-7 draft | refined idea + §8 TCs | refined-idea coverage + §8 TC decisions + implied rules |
147
148**Detection precedence:** full §1-8 + `provisional: true` → `AUTHORED-SPEC`; full §1-8 + NOT provisional → `EXISTING-SPEC`; only §8 / refined-idea (no §1-7 draft) → `TEST-SPEC`. **Ambiguous → 1 ask the user directly** to confirm the context before auditing.
149
150**Question budget:** read the injected `Spec Validation: questions=MIN-MAX` line (workflow `injectContext` supplies it per flow). When absent (standalone run), fall back to the per-context defaults in `references/clarify-interview.md` — `AUTHORED-SPEC` 5-10, `EXISTING-SPEC` 4-8, `TEST-SPEC` 3-6. The budget bounds the Step 4 gate: ask ≥MIN when ≥MIN genuine decisions exist, never exceed MAX.
151
152State `Context: {AUTHORED-SPEC | EXISTING-SPEC | TEST-SPEC} | Budget: {MIN-MAX} (injected | default)` before Step 0.
153
154## Inputs (Step 0)
155
156Resolve and confirm these inputs exist BEFORE the completeness pass. A missing input is a finding, not a reason to guess.
157
1581. **The artifact under validation** — resolved per the detected context: `AUTHORED-SPEC` / `EXISTING-SPEC` → the full §1-8 Feature Spec (§1 Overview, §2 Glossary, §3 User Stories & Acceptance Criteria, §4 Business Rules with `[HARD]`/`[SOFT]` markers, §5 Domain Model, §6 Process Flows & Interaction Surface, §7 Permissions & Roles, §8 Test Specifications `TC-{FEATURE}-{NNN}`); `TEST-SPEC` → the refined idea + the §8 TC set (no §1-7 draft yet). Read `docs/project-reference/feature-spec-reference.md` + `spec-system-reference.md` + `spec-principles.md` first.
1592. **The `spec-discovery` landscape report** — `plans/{plan-dir}/research/spec-discovery-{slug}.md` (Related Specs, Related Code, Affected Specs, Gaps, Invariant Landscape, Open Questions), the investigation of related/overlapping/affected specs + code. This is the baseline against which completeness is judged. For `TEST-SPEC` the landscape also comes from `spec-discovery` (present in the `idea-to-pbi` deep-mode sequence). If it is absent (skill run standalone), fall back to `scout` + `investigate` plus the derived `$spec-index` artifacts (index / ERD / reimplementation guide) under `docs/specs/`, and flag the absence as a finding.
1603. **The originating idea / brainstorm** — the requirement that the artifact is meant to satisfy; its implied operations and edge cases drive the missing-coverage check.
1614. **The domain-analysis output** — bounded contexts, aggregates, entities, domain events, and the invariants the artifact must respect.
162
163State `Inputs resolved: ... | Missing (flag as finding): ...` before Step 1.
164
165## Workflow
166
167Run **Phase 0 (Spec-Context Detection)** above first — it sets the context + budget that the steps below consume.
168
1690. **Inputs** — resolve the four inputs above (artifact resolved per the detected context); flag any missing one as a finding.
1701. **Completeness pass (vs system)** — judge the artifact against the discovered landscape, NOT against itself, weighting the sections the context emphasizes (see the per-context matrix in `references/clarify-interview.md`):
171 - **Cross-reference completeness** — every related/affected spec from the landscape is reflected (a behavior the system already owns and this feature touches must appear, or its absence must be deliberate and noted). For `TEST-SPEC`, judge the refined idea + §8 set against the landscape.
172 - **Implied coverage** — missing user stories / acceptance criteria / business rules the originating idea implies but the artifact omits.
173 - **Test-coverage completeness** — missing §8 TCs versus the implied operations + their edge cases (presence/scope only).
174 - **Invariant coverage** — every NEEDED invariant (this feature must establish) AND every EXISTING invariant the artifact must respect (from domain-analysis / adjacent specs) is captured; each `[HARD]` §4 rule has at least one §8 property/invariant TC. This is a CROSS-CHECK that the property TC exists — defer the detailed TC-quality audit (universally-quantified property, boundary counter-case, etc.) to `artifact-review --type=spec-tests`.
175 - **Interaction surface completeness (UI-bearing specs)** — judge §6's interaction surface against the implied UI: every view a user story needs is in the §6.2 view inventory by UX role; navigation between views (§6.3) has no dangling entry/exit; each view's observable states (§6.4 — empty/loading/populated/error/success/permission-denied) are present or deliberately absent; every UI-bearing user story has a §6.5 click-path. Backend-only specs must state the §6 skip reason. Presence/scope only — visual fidelity stays in the companion design artifact.
1762. **Hypothesis & decision audit (category-driven)** — walk EVERY applicable category for the detected context (the 9-category catalog + per-context matrix in [`references/clarify-interview.md`](./references/clarify-interview.md)); for each, run its audit prompts to surface every assumption, default value, scope boundary, and ambiguous behavior the artifact encodes. Classify each:
177 - **OBVIOUS** — a single reasonable reading any competent reader shares → document it in the Decisions Log and proceed.
178 - **NON-OBVIOUS** — more than one defensible reading, or a default the user has not confirmed → candidate for the Step 4 gate.
179 - **CONFLICTS** — disagrees with a discovered landscape spec or an existing invariant → MUST be reconciled (and surfaced to the user). Default to NON-OBVIOUS when the classification itself is unclear.
180 Probing breadth is exhaustive (every applicable category); asking breadth is the budget.
1813. **Brainstorm open questions** — questions whose answers would MATERIALLY change the artifact (scope, a default, an invariant boundary, an actor/permission). Run an adversarial **pre-mortem**: "this artifact ships and the feature fails in production within 3 months — what spec gap caused it?" Each pre-mortem failure that maps to a real gap becomes either a NON-OBVIOUS question or a completeness finding.
182
183 > **Interaction Surface category (UI-bearing specs):** treat each of these as a gate candidate — an ambiguous view (its UX role or purpose has more than one defensible reading), a missing observable state (a view whose error/empty/permission-denied behavior the spec leaves unstated), and an unmapped click-path (a UI-bearing user story with no §6.5 step path, or a navigation transition with no business trigger). Classify each OBVIOUS / NON-OBVIOUS / CONFLICTS like any other; route NON-OBVIOUS + CONFLICTS to the gate within the budget. Ask about UX intent only — never about framework/route/CSS/component-class detail (that belongs to the companion design artifact).
184
1854. **Clarification gate (BLOCKING ask the user directly)** — present the NON-OBVIOUS + CONFLICTS + high-impact items to the user as structured options, **exhaustive within the MIN-MAX budget** from Phase 0: ask ≥MIN questions when ≥MIN genuine decisions exist, never exceed MAX, ≤4 options per call, the recommended option FIRST, issue multiple ask the user directly calls when there are more than 4 decisions. When fewer than MIN genuine decisions exist, ask only the genuine ones and record "below-MIN: only N real decisions" — NEVER invent filler. Capture each answer. **NEVER silently pick a NON-OBVIOUS decision** — the active question is the entire point of this gate.
1865. **Apply** — write the confirmed decisions back into the relevant artifact sections AND record them in an **"Open Questions / Decisions Log"** (resolved decisions with the user's choice + rationale, plus residual items still below 80% confidence). For `AUTHORED-SPEC`/`EXISTING-SPEC`, when the confirmed answers reveal material gaps, loop the spec author via `$spec [mode=update]` to re-author the affected sections, then re-run Step 1 against the updated spec. For `EXISTING-SPEC` this skill does NOT itself re-author — confirmed changes route through `$spec [mode=update]`; for `TEST-SPEC` the decisions feed PBI decomposition + any `$spec [mode=tests]` refinement.
1876. **Report + verdict** — before applying decisions, run `$why-review --validate-findings <report-path>` on THIS skill's own findings (validate-before-fix discipline, at parity with `artifact-review` / `plan-review`); fix/drop any finding the gate flags, then apply only validated decisions. Write the report to `plans/reports/spec-clarify-{date}.md` and emit a verdict:
188 - **CLARIFIED** — every NON-OBVIOUS/CONFLICTS decision confirmed by the user, completeness gaps resolved or accepted, no residual blocking question.
189 - **NEEDS-AUTHORING-FIX** — material completeness gap or unreconciled conflict requires re-authoring via `$spec [mode=update]` before the spec can be finalized.
190
191## Output
192
193```markdown
194## Spec Clarification Report
195
196**Spec:** {spec path}
197**Date:** {date}
198**Verdict:** CLARIFIED | NEEDS-AUTHORING-FIX
199**Confidence:** {X%} — {what was verified vs. what remains residual}
200
201### Completeness (vs discovered system)
202
203| Area | Status | Gap / Evidence (`file:line` or spec/section ref) |
204| -------------------------------------- | ------ | ----------------------------------------------------------------------------- |
205| Related/affected specs reflected | ✅/❌ | {which related behavior is/ isn't reflected} |
206| Implied stories / AC / rules | ✅/❌ | {missing item the idea implies} |
207| §8 TC coverage vs operations | ✅/❌ | {operation/edge case with no TC} |
208| Invariant coverage (needed + existing) | ✅/❌ | {`[HARD]` rule without a §8 property TC, or existing invariant not respected} |
209
210### Hypothesis & Decision Audit
211
212| # | Encoded assumption / default / boundary | Class (OBVIOUS / NON-OBVIOUS / CONFLICTS) | Evidence |
213| --- | --------------------------------------- | ----------------------------------------- | -------- |
214| 1 | {assumption} | {class} | {ref} |
215
216### Open Questions (pre-mortem + materially-changing)
217
2181. {question — what changes in §1-8 depending on the answer}
219
220### Decisions Log
221
222| Decision | User's confirmed choice | Applied to | Residual confidence |
223| ---------------------- | ------------------------------------ | ---------- | ----------------------- |
224| {non-obvious decision} | {answer by asking the user directly} | §{n} | {>=80% / <80% residual} |
225
226### Verdict
227
228{CLARIFIED | NEEDS-AUTHORING-FIX} — {evidence-based justification; if NEEDS-AUTHORING-FIX, the exact `$spec [mode=update]` scope}
229```
230
231## Key Rules
232
233- **Detect the context FIRST (Phase 0)** — `AUTHORED-SPEC` / `EXISTING-SPEC` / `TEST-SPEC` tunes which sections/categories are audited and the question budget; ambiguous → 1 ask the user directly to confirm before auditing.
234- **Walk every applicable category, ask within the budget** — probing breadth is exhaustive (the 9-category catalog × the per-context matrix in `references/clarify-interview.md`); the `Spec Validation: questions=MIN-MAX` budget (per-context default when absent) caps how many reach the gate. Never invent filler to hit MIN; never exceed MAX.
235- **Completeness is judged against the SYSTEM** — every related/affected behavior from the discovered landscape must be reflected, or its absence deliberately noted. The artifact passing in isolation is NOT enough.
236- **NON-OBVIOUS and CONFLICTS go to the user** — only OBVIOUS decisions are documented-and-proceeded; ambiguity in the classification itself defaults to NON-OBVIOUS.
237- **NEVER silently pick a non-obvious decision** — the blocking ask the user directly gate is the entire value of this skill.
238- **Runs INLINE, not as a sub-agent** — the clarification gate needs ask the user directly, which only the main interactive agent can run; do NOT add `execution-mode: subagent`.
239- **Complements, never duplicates** — `artifact-review` owns isolation/M1-M5 + M7, `why-review` owns rationale; cross-check the `[HARD]`→§8 mapping only and defer the detailed TC-quality audit to `artifact-review --type=spec-tests`.
240- **Validate before applying** — run `$why-review --validate-findings` on this skill's own findings before rewriting any §1-8 section.
241- **Evidence-based** — every completeness gap, classification, and conflict cites `file:line` / a spec section / an invariant ref with a confidence percentage.
242
243---
244
245> **[IMPORTANT]** Use task tracking to break ALL work into small tasks BEFORE starting — including a final review task to verify completeness and that every non-obvious decision was confirmed.
246
247> **Evidence Gate:** MANDATORY IMPORTANT MUST ATTENTION — every claim requires `file:line` proof or traced evidence with confidence percentage (>80% to act).
248
249<!-- SYNC:nested-task-creation -->
250
251> **Nested Task Expansion Contract** — For workflow-step invocation, the `[Workflow] ...` row is only a parent container; the child skill still creates visible phase tasks.
252>
253> 1. Call the current task list first. If a matching active parent workflow row exists, set `nested=true` and record `parentTaskId`; otherwise run standalone.
254> 2. Create one task per declared phase before phase work. When nested, prefix subjects `[N.M] $skill-name — phase`.
255> 3. When nested, link the parent with `TaskUpdate(parentTaskId, addBlockedBy: [childIds])`.
256> 4. Orchestrators must pre-expand a child skill's phase list and link the workflow row before invoking that child skill or sub-agent.
257> 5. Mark exactly one child `in_progress` before work and `completed` immediately after evidence is written.
258> 6. Complete the parent only after all child tasks are completed or explicitly cancelled with reason.
259>
260> **Blocked until:** the current task list done, child phases created, parent linked when nested, first child marked `in_progress`.
261
262<!-- /SYNC:nested-task-creation -->
263
264<!-- SYNC:project-reference-docs-guide -->
265
266> **Project Reference Docs Gate** — Run after task-tracking bootstrap and before target/source file reads, grep, edits, or analysis. Project docs override generic framework assumptions.
267>
268> 1. Identify scope: file types, domain area, and operation.
269> 2. **Read `docs/project-config.json` first — the project's machine-readable map.** It is the single source of truth for THIS repo (modules/paths, framework + search keywords, test/E2E/integration run-commands, design system, architecture rules, workflow patterns); ground exact paths, run-commands, and conventions on it **before investigating, planning, or coding** — never assume framework defaults (`CLAUDE.md` + reference docs are derived from it). If it — or the docs index, `lessons.md`, `CLAUDE.md`, `AGENTS.md`, or any required reference doc — is missing or stale, auto-run `$project-init` or the narrow route (`$project-config`, `$docs-init`, `$scan-all`, `$scan --target=<key>`, `$claude-md-init`) first; if Codex mirrors or `AGENTS.md` are stale, ask the user to run `$sync-codex` (never auto-run it).
270> 3. Required docs by trigger: always `docs/project-reference/lessons.md`; doc lookup `docs-index-reference.md`; review `code-review-rules.md`; backend/CQRS/API `backend-patterns-reference.md`; domain/entity `domain-entities-reference.md`; frontend/UI `frontend-patterns-reference.md`; styles/design `scss-styling-guide.md` + `design-system/design-system-canonical.md`; integration tests `integration-test-reference.md`; E2E `e2e-test-reference.md`; feature docs/specs `feature-spec-reference.md` + `spec-system-reference.md` + `spec-principles.md`; behavior/public-contract/spec-test-code sync `workflow-spec-test-code-cycle-reference.md`; derived spec index/ERD/reimplementation guides `spec-system-reference.md` + source Feature Specs under `docs/specs/`; architecture/new area `project-structure-reference.md`.
271> 4. Read every required doc, then before target work state: `Reference docs read: ... | Not applicable: ...`.
272>
273> **Ready when:** scope evaluated, `docs/project-config.json` consulted, required docs checked/read or setup route completed, `lessons.md` confirmed, citation emitted.
274
275<!-- /SYNC:project-reference-docs-guide -->
276
277<!-- SYNC:task-tracking-external-report -->
278
279> **Task Tracking & External Report Persistence** — Bootstrap this before execution; then run project-reference doc prefetch before target/source work.
280>
281> 1. Create a small task breakdown before target file reads, grep, edits, or analysis. On context loss, inspect the current task list first.
282> 2. Mark one task `in_progress` before work and `completed` immediately after evidence; never batch transitions.
283> 3. For plan/review work, create `plans/reports/{skill}-{YYMMDD}-{HHmm}-{slug}.md` before first finding.
284> 4. Append findings after each file/section/decision and synthesize from the report file at the end.
285> 5. Final output cites `Full report: plans/reports/{filename}`.
286>
287> **Blocked until:** task breakdown exists, report path declared for plan/review work, first finding persisted before the next finding.
288
289<!-- /SYNC:task-tracking-external-report -->
290
291<!-- SYNC:critical-thinking-mindset -->
292
293> **Critical Thinking Mindset** — Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence >80% to act.
294> **Anti-hallucination:** Never present guess as fact — cite sources for every claim, admit uncertainty freely, self-check output for errors, cross-reference independently, stay skeptical of own confidence — certainty without evidence root of all hallucination.
295
296<!-- /SYNC:critical-thinking-mindset -->
297
298<!-- SYNC:evidence
299
300…(truncated)