Workflow Greenfield Init

[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: [Workflow] Trigger Greenfield Project Init workflow — full waterfall project inception from idea through implementation with a test architecture contract, integration verification, conditional E2E evaluation, and final full/focused verification.

Summary:

• Begin with the shared large-idea classification and embedded decomposition contract; run /scenario before the first plan when the outcome slices require adversarial risk analysis. A roadmap artifact is not a default greenfield prerequisite.

• Research the product, domain, technology, architecture, and foundation in order; scaffold and review the foundation before feature work.

• Every generated PBI MUST pass the Releasable Outcome Gate: one independently releasable actor-facing outcome with a complete entry-to-result journey; foundation/scaffold/setup work is enabling work attached to that outcome, never a standalone technical PBI. UI PBIs require the full page/view, navigation, component, state, and mock-app flow surface.

• Preserve the full spec/PBI/story/test chain, emit the test architecture contract before implementation planning completes, and finish with implementation, integration verification, conditional E2E evaluation, conditional experience exercise/inspection, synchronized evidence, and final full/focused verification.

• Main steps: classify/decompose → research → domain/tech/architecture + test contract → scenario/plan/review → PBI/story/mock-up/spec gates → scaffold/lint/harness/architecture review → implementation/integration verification → conditional E2E → final full/focused verification → final review/security/test/docs/handoff.

Workflow:

1. Detect — classify request scope and target artifacts.
2. Execute — apply required steps with evidence-backed actions.
3. Verify — confirm constraints, output quality, and completion evidence.

Key Rules:

• MUST ATTENTION keep claims evidence-based (file:line) with confidence >80% to act.
• MUST ATTENTION keep task tracking updated as each step starts/completes.
• MUST ATTENTION define success criteria before execution and loop until observable verification passes.
• MUST ATTENTION when creating/reviewing specs or tests, name Business Intent / Invariant Guarded or the protected business intent/invariant and ensure the test would fail if that intent breaks.
• MUST ATTENTION classify the greenfield idea with isLargeIdea = multipleIndependentOutcomes || ambiguousOrResearchHeavy || releaseScopeDecomposition || oversizedPbiThatMustSplit before market research, architecture, specs, PBIs, or plans. When true, require the complete embedded large_idea_decomposition block in the owning PBI/spec with outcome_slices, dependencies_order, non_goals, risks_evidence, and deferred_work_owner, then carry stable slice IDs into stories, mock-ups, and the all-PBI presentation; run /scenario only when the selected scope needs adversarial risk analysis, otherwise record the conditional skip with evidence. An explicit roadmap request may use the standalone writer separately.
• MUST ATTENTION emit and validate the Test Architecture & Execution Contract matrix before the first implementation plan completes; block handoff when any applicable tier lacks a copy-ready full command, focused command, zero-match behavior, or unique run/data identity, and record evidence-backed N/A for non-applicable tiers.
• MUST ATTENTION after /integration-test-verify, inspect configured E2E evidence and invoke /e2e-test only when a runnable E2E framework/command is configured; otherwise record explicit evidence-backed N/A. The final /test must report full/focused verification and exact results.
• NEVER skip mandatory workflow or skill gates.

Repeated Steps Disambiguation (CRITICAL for task creation)

This workflow has steps that appear multiple times. When creating tasks, use these descriptions to distinguish them:

NEVER deduplicate — each occurrence is a distinct task with a different purpose.

IMPORTANT MANDATORY Steps: /idea -> /web-research -> /deep-research -> /market-analysis -> /business-evaluation -> /spec-discovery -> /domain-analysis -> /why-review -> /tech-stack-research -> /architecture-design -> /architecture-scalability-review -> /why-review -> /scenario -> /plan -> /plan-review -> /security-review -> /performance-review -> /plan-review -> /refine -> /why-review -> /artifact-review --type=pbi -> /story -> /why-review -> /artifact-review --type=story -> /pbi-challenge -> /dor-gate -> /pbi-mockup -> /plan-validate -> /why-review -> /spec [mode=tests] -> /why-review -> /artifact-review --type=spec-tests -> /spec-clarify -> /plan -> /plan-review -> /scaffold -> /linter-setup -> /harness-setup -> /architecture-review-full -> /scan --target=ui-system -> /scan --target=backend-patterns -> /scan --target=integration-tests -> /scan --target=project-structure -> /why-review -> /plan-execute -> /seed-test-data -> /domain-entities-review -> /spec [mode=tests] -> /why-review -> /artifact-review --type=spec-tests -> /plan -> /plan-review -> /integration-test -> /integration-test-review -> /integration-test-verify -> /e2e-test -> /test -> /workflow-review-changes -> /security-review -> /changelog -> /test -> /scan --target=domain-entities -> /docs-update -> /workflow-end -> /watzup

IMPORTANT MANDATORY Steps: /idea -> /web-research -> /deep-research -> /market-analysis -> /business-evaluation -> /spec-discovery -> /domain-analysis -> /why-review -> /tech-stack-research -> /architecture-design -> /architecture-scalability-review -> /why-review -> /scenario -> /plan -> /plan-review -> /security-review -> /performance-review -> /plan-review -> /refine -> /why-review -> /artifact-review --type=pbi -> /story -> /why-review -> /artifact-review --type=story -> /pbi-challenge -> /dor-gate -> /pbi-mockup -> /plan-validate -> /why-review -> /spec [mode=tests] -> /why-review -> /artifact-review --type=spec-tests -> /spec-clarify -> /plan -> /plan-review -> /scaffold -> /linter-setup -> /harness-setup -> /architecture-review-full -> /scan --target=ui-system -> /scan --target=backend-patterns -> /scan --target=integration-tests -> /scan --target=project-structure -> /why-review -> /plan-execute -> /seed-test-data -> /domain-entities-review -> /spec [mode=tests] -> /why-review -> /artifact-review --type=spec-tests -> /plan -> /plan-review -> /integration-test -> /integration-test-review -> /integration-test-verify -> /e2e-test -> /test -> /workflow-review-changes -> /security-review -> /changelog -> /test -> /scan --target=domain-entities -> /docs-update -> /workflow-end -> /watzup

[BLOCKING] Each selected step MUST ATTENTION invoke its Skill tool — marking a selected task completed without skill invocation is a workflow violation. A declared conditional step such as /scenario may be marked skipped only with evidence and an explicit reason; NEVER batch-complete validation gates.

Activate the workflow-greenfield-init workflow. Run /start-workflow workflow-greenfield-init with the user's prompt as context.

Steps: /idea → /web-research → /deep-research → /market-analysis → /business-evaluation → /spec-discovery → /domain-analysis → /why-review → /tech-stack-research → /architecture-design → /architecture-scalability-review → /why-review → /scenario → /plan → /plan-review → /security-review → /performance-review → /plan-review → /refine → /why-review → /artifact-review --type=pbi → /story → /why-review → /artifact-review --type=story → /pbi-challenge → /dor-gate → /pbi-mockup → /plan-validate → /why-review → /spec [mode=tests] → /why-review → /artifact-review --type=spec-tests → /spec-clarify → /plan → /plan-review → /scaffold → /linter-setup → /harness-setup → /architecture-review-full → /scan --target=ui-system → /scan --target=backend-patterns → /scan --target=integration-tests → /scan --target=project-structure → /why-review → /plan-execute → /seed-test-data → /domain-entities-review → /spec [mode=tests] → /why-review → /artifact-review --type=spec-tests → /plan → /plan-review → /integration-test → /integration-test-review → /integration-test-verify → /e2e-test → /test → /workflow-review-changes → /security-review → /changelog → /test → /scan --target=domain-entities → /docs-update → /workflow-end → /watzup

[CONDITIONAL TERMINAL DOMAIN-ENTITY REFERENCE REFRESH] After /test and before /docs-update, run /scan --target=domain-entities to refresh the project-reference entity catalog only when the final diff changes an entity/model, DTO/data contract, persistence schema/migration, or entity-sync evidence represented in docs/project-reference/domain-entities-reference.md. Otherwise mark the scan step completed with a cited skip reason naming the changed files and why they are outside this scope; this is the explicitly authorized exception to the per-step skill-invocation rule.

[BLOCKING TEST ARCHITECTURE HANDOFF GATE] During /architecture-design, emit the Test Architecture & Execution Contract matrix before the first /plan completes. Before /plan-execute or any feature-implementation handoff, validate every potentially applicable Unit, Integration/System, and E2E row: APPLICABLE requires evidence-backed runner/framework/configuration, copy-ready full and focused commands, zero-match behavior, and unique run/data identity; missing any of these blocks handoff. Record N/A — <evidence> for every non-applicable tier; never substitute an assumption for missing evidence.

[CONDITIONAL E2E GATE] Immediately after /integration-test-verify, inspect docs/project-config.json → e2eTesting and the matching runnable framework, entry points, and commands. When configured, invoke /e2e-test; otherwise complete that conditional step as N/A — <evidence> citing the configuration and repository scan, without fabricating browser setup. When the implementation exposes a configured or likely observable surface, run the conditional /experience-review after final review convergence; a relevant surface without a runnable/inspectable capability is ENVIRONMENT-BLOCKED, not N/A or PASS. The following /test step performs final full/focused verification and reports exact results and exit status for each applicable tier.

Architecture quality gate (/architecture-scalability-review, pos 11). Immediately after /architecture-design and before the first /plan, greenfield runs the architecture & scalability scorecard (init mode) so its findings and gate items feed the implementation plan. This is the comprehensive project-quality evaluation for greenfield/init — Build & CI scalability, architecture pattern (modular monolith vs. microservices / distributed-monolith avoidance), module isolation, dependency discipline, loose coupling, horizontal scaling, DRY, abstraction/easy-to-change, clean architecture, and observability/DevOps. Brownfield or day-to-day audits invoke the same skill on demand via /architecture-scalability-review mode=audit; it is intentionally NOT a member of the every-change workflow-review-changes batch — that batch's architecture-review step carries the lightweight per-change scalability & coupling regression check instead.

Supported mode: use the default workflow-greenfield-init sequence resolved from workflows.json. Do not infer a trimmed variant or skip gates that the selected manifest does not authorize.

AI Mistake Prevention — Failure modes to avoid on every task:

Re-read files after context changes. Context compaction, resume, or long-running work can make memory stale; verify current files before acting. Verify generated content against source evidence. AI hallucinates APIs, names, claims, and document facts. Check the relevant source before documenting or referencing. Check downstream references before deleting or renaming. Removing an artifact can stale docs, generated mirrors, configs, and callers; map references first. Trace the full impact chain after edits. Changing a definition can miss derived outputs and consumers. Follow the affected chain before declaring done. Verify ALL affected outputs, not just the first. One green check is not all green checks; validate every output surface the change can affect. Assume existing values are intentional — ask WHY before changing OR flagging one as a defect. Before changing or reporting a constant, limit, flag, cutoff, wording, or pattern, read nearby context and history, the CALLER's ordering, and 2+ sibling call sites of the same convention. A doc stating WHAT without WHY is missing rationale, not proof of a missing guard. Surface ambiguity before acting — don't pick silently. Multiple valid interpretations require an explicit question or stated assumption with risk. Assert the outcome your system owns, not the intermediate state your infrastructure owns. When verifying async work, assert the final business state — never the delivery/retry bookkeeping held in shared infrastructure that any co-running process can write. Such a check passes when run alone and flakes the moment anything else shares that infrastructure. Keep shared guidance role-relevant. Universal guidance must help every receiving skill or agent; code-specific obligations belong only in code-specific protocols.

Nested Task Expansion Contract — For workflow-step invocation, the [Workflow] ... row is only a parent container; the child skill still creates visible phase tasks.

1. Call TaskList first. If a matching active parent workflow row exists, set nested=true and record parentTaskId; otherwise run standalone.
2. Create one task per declared phase before phase work. When nested, prefix subjects [N.M] /skill-name — phase.
3. When nested, link the parent with TaskUpdate(parentTaskId, addBlockedBy: [childIds]).
4. Orchestrators must pre-expand a child skill's phase list and link the workflow row before invoking that child skill or sub-agent.
5. Mark exactly one child in_progress before work and completed immediately after evidence is written.
6. Complete the parent only after all child tasks are completed or explicitly cancelled with reason.

Blocked until: TaskList done, child phases created, parent linked when nested, first child marked in_progress.

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.

Incremental Result Persistence — MANDATORY for all sub-agents or heavy inline steps processing >3 files.

1. Before starting: Create report file plans/reports/{skill}-{date}-{slug}.md and record Run ID, Task ID, Attempt ID, target scope, and target fingerprint.
2. After each file/section reviewed: Append findings, evidence, changed paths, and gaps immediately — never hold them in memory.
3. Delegated return: A sub-agent emits only the structured SYNC:subagent-return-contract envelope with exact totals, salient Critical/High findings (maximum ten), current attempt, and Full report: path. Inline user-facing output: Preserve the skill's requested explanation or teaching, with links to the persisted evidence; the delegated transport limit does not replace that deliverable. Do not paste a full review report into an envelope.
4. Parent synthesis: The main agent reads the full report for synthesis, acceptance, deduplication, and repair planning — not only when a named blocker exists. It preserves all severities beyond the transport cap.
5. Read-only boundary: A read-only leaf may write its report/repair proposal but MUST NOT edit source, generated output, or user data; the parent/owner performs repairs after acceptance.
6. Advancement gate: The parent records ACCEPTED for the current Attempt ID only after reconciling target, totals, gaps, and changed paths; stale or late attempts cannot advance dependent work.

Why: Context cutoff mid-execution loses ALL in-memory findings. Each disk write survives compaction. Partial results are better than no results, while explicit identity prevents a late result from being mistaken for the current run.

Report naming: plans/reports/{skill-name}-{YYMMDD}-{HHmm}-{slug}.md

Sub-Agent Return Contract — When this skill spawns a sub-agent, the sub-agent MUST return ONLY the structured envelope below. Main agent reads the envelope first, then opens the referenced report for synthesis, acceptance, deduplication, or repair planning; a full report is never pasted inline.

## Sub-Agent Result: [skill-name]

Status: ✅ PASS | ⚠️ PARTIAL | ❌ FAIL
Confidence: [0-100]%
Run ID: [stable run identifier]
Task ID: [parent task or phase identifier]
Attempt ID: [monotonic attempt/revision identifier]
Target: [exact files/paths or scope] @ [target fingerprint/commit]
Changed paths: [none | exact paths]
Finding totals: Critical=[n] | High=[n] | Medium=[n] | Low=[n]
Acceptance: PENDING | ACCEPTED | REJECTED — parent records the decision

### Findings (Critical/High surfaced — max 10 bullets)

- [severity] [file:line] [finding]

### Gaps / Unverified

- [missing host, runtime, coverage, or evidence limitation]

### Actions Taken

- [file changed] [what changed]

### Blockers (if any)

- [blocker description, or `none`]

Full report: plans/reports/[skill-name]-[date]-[slug].md

The ten-bullet limit is a transport limit, not a visibility limit: the full report may contain more than ten Medium/Low findings when no named blocker exists, and the parent MUST read it when synthesizing or deduplicating. The parent MUST reject a stale, duplicate, or superseded Attempt ID and MUST accept the current attempt before advancing a dependent step. Read-only leaves write repair proposals/reports only; they do not edit source, generated carriers, or user files.

Context budget — the return payload is a SUMMARY, not a transcript: no raw file contents / full diffs / verbatim logs inline, no re-pasted source. Everything beyond the envelope lives in the incrementally-written report. A sub-agent that would exceed the summary shape MUST persist the detail and return only the pointer; bounded transport must never become bounded visibility.

Test Architecture & Execution Contract — Treat testability as a setup/architecture acceptance condition. For every potentially applicable tier — Unit, Integration/System, E2E, and Performance/Scale (warranted at T1+/B2+) — record APPLICABLE only with evidence of its runner/framework/configuration; otherwise record N/A — <evidence> and never fabricate coverage.

1. Matrix before implementation: Record applicability, owner, runner/framework, test root, fixture/data strategy, full command, focused/partial command, zero-match behavior, CI gate, a simple/Windows entry point (a .cmd when the project needs one), the host-mode AND container-mode commands where the project supports both, and the environment reach (which of local / CI / production-shaped this tier can target).
2. Runnable scopes: Full and focused commands must be copy-ready, fail on invalid or zero-match selections, report exact counts and exit status, and be safe to repeat. E2E uses only configured browser/service commands.
3. Fresh valid state: Each run/test owns a unique run identity and business-data suffix, arranges through supported public paths, and uses realistic valid data. Reference setup is count-before-create, idempotent, and restart-safe. Intentional accumulation is additive, keyed, and integrity-checked; never hide contamination with destructive reset. Run-scoped cleanup, when supported, is opt-in and idempotent: after evidence capture it may remove only ephemeral resources owned by the current run; it must never delete persistent/additive data or another run's data, reset shared state, or replace no-reset proof.
4. Isolation and fidelity: Isolate mutable roots and parallel workers; share only immutable/reference data. Preserve real actor pacing and observable arrange barriers. Do not widen retries or weaken assertions to make a scenario pass.
5. Evidence gate: Report command, scope, identity, seed/accumulation mode, exact result, and repeat proof. For each applicable persistent-state suite, require two consecutive no-reset full runs. Treat line coverage as diagnostic only; use meaningful property/invariant, mutation, change, and behavior coverage signals.
6. Execution modes and environment reach: A tier claiming two run modes must have BOTH exercised — the bare-host command and the fully-containerized command, driven from ONE source of truth for config and topology; record which mode CI exercises, because an unexercised mode rots silently and a claimed-but-rotten mode is worse than one never claimed. The SAME suite must reach local, CI and (where warranted) a production-shaped target, parameterized by configuration, never by forked test code — only one fork ever stays maintained, so forking guarantees divergence. A target lacking a required capability reports ENVIRONMENT-BLOCKED, never a silent pass. Tests unsafe against production are excluded by an ENFORCED mechanism whose absence fails loudly, not by a convention someone must remember; "runs in prod" means a safe, declared, NON-MUTATING subset. Reproducibility underwrites all of it — pinned toolchain, locked dependencies, declared external prerequisites — which is the difference between a suite that passes anywhere and one that passes on its author's machine. Depth → SYNC:engineering-foundation-gate F1/F2/F3.

Ownership: Architecture/harness defines the matrix; scaffold/workflow makes it runnable; test writers implement tier-specific cases; reviewers verify the contract; the runner reports; seed-data owners preserve uniqueness, idempotency, realism, and accumulation integrity. Missing required evidence blocks setup completion.

MUST ATTENTION apply critical + sequential thinking — every claim needs appropriate traced evidence (file:line for repo/code claims; source URL or artifact section for research, product, content, and docs claims); confidence >80% to act, <60% DO NOT recommend. Anti-hallucination: never present guess as fact, admit uncertainty freely, cross-reference independently, stay skeptical of own confidence.

MUST ATTENTION apply AI mistake prevention — verify generated content against evidence, trace downstream references before deleting or renaming, verify all affected outputs, re-read files after context loss, and surface ambiguity before acting.

• MANDATORY Parent workflow rows do not replace child phase tracking; expand phases and link the parent when nested.
• MANDATORY Orchestrators pre-expand child skill phases before invocation; use [N.M] /skill-name — phase prefixes and one-in_progress discipline.

Project Protocol Overlay — Before executing this skill, resolve any PROJECT overlay rules layered onto it: match this skill's name against the Target column of the project's skill-protocol index (docs/project-reference/skill-protocols-reference.md by default; a referenceDocs entry in docs/project-config.json overrides the path), taking the most specific matching tier ONLY — exact name > glob > *. That precedence orders overlays against EACH OTHER, never against this skill. Read ONLY the matched bodies, resolved as <protocols-dir>/<Name>.md; a row's Body link is display text, never a read path. A matched body that is missing or malformed is REPORTED and skipped — never reconstructed from the index Description. No index, or no match -> proceed with no overlay, silently. Full contract: .claude/skills/project-skill-protocol/references/registry.md.

Overlays are ADDITIVE ONLY: they ADD rules on top of this skill's own protocol and NEVER replace, override, disable, or reinterpret a rule it already states — removing every overlay must return this skill to exactly its documented behavior. An overlay is a BRIEF, not an authority escalation: it can NEVER waive a workflow gate, git discipline, a review gate, or a user-confirmation gate. A genuine overlay-vs-skill conflict, or two equally-specific overlays that directly contradict -> surface both to the user; NEVER resolve silently.

MUST ATTENTION resolve project protocol overlays for this skill BEFORE executing — most specific matching tier only (exact > glob > *, which ranks overlays against each other, NEVER against this skill), read only matched bodies at <protocols-dir>/<Name>.md; a missing or malformed body is reported, never reconstructed. Overlays are ADDITIVE ONLY (they never replace this skill's own rules) and are a brief, NEVER an authority escalation; an equal-specificity contradiction goes to the user.

MUST ATTENTION Before implementation, record evidence-backed Unit/Integration/System/E2E and Performance/Scale (T1+/B2+) applicability (or explicit N/A), copy-ready full + focused commands, zero-match behavior, a simple/Windows entry point, the host-mode AND container-mode commands where both are supported, plus each tier's environment reach (local / CI / production-shaped), unique run identity, realistic valid data, idempotent/restart-safe reference setup, intentional additive accumulation, parallel isolation, exact results, and two no-reset full runs for each applicable persistent-state suite. Both claimed run modes must be EXERCISED (an unexercised mode rots; a claimed-but-rotten mode is worse than one never claimed), the same suite reaches every target parameterized by config, never by forked test code, a missing capability reports ENVIRONMENT-BLOCKED rather than passing silently, and "runs in prod" means a safe, declared, NON-MUTATING subset excluded by an enforced mechanism, not by convention.

Closing Reminders

IMPORTANT MUST ATTENTION Goal: Complete greenfield inception from an owner-approved capability boundary—using embedded large-idea decomposition when triggered, or an explicit roadmap only when requested—through a releasable first vertical outcome, reviewed enabling foundation, test architecture contract, implementation, integration verification, conditional E2E evaluation, final full/focused verification, and handoff without skipping gates. IMPORTANT MUST ATTENTION Main steps: classify/decompose → research → domain/tech/architecture + test contract → scenario/plan/review → PBI/story/mock-up/spec gates → scaffold/lint/harness/architecture review → implementation/integration verification → conditional E2E → final full/focused verification → final review/security/test/docs/handoff. IMPORTANT MUST ATTENTION apply .claude/skills/shared/releasable-pbi-contract.md: no standalone technical/foundation/setup PBI; UI PBIs must include all required pages/views, navigation, components, states, and a connected mock-app demo.

Protocols in force (concise digest of the SYNC/shared blocks this skill carries):

• AI Mistake Prevention: verify generated content against evidence, trace downstream references, verify all affected outputs, re-read after context loss, surface ambiguity.
• Nested Task Creation: expand child phases, link parent when nested, one task in_progress.
• Critical Thinking: traced file:line proof per claim, confidence >80% to act.
• Incremental Persistence: append findings to plans/reports/ per file, never hold in memory.
• Sub-Agent Return Contract: return summary only (≤10 bullets), full detail to disk.

IMPORTANT MUST ATTENTION break work into small todo tasks using TaskCreate BEFORE starting IMPORTANT MUST ATTENTION search codebase for 3+ similar patterns before creating new code IMPORTANT MUST ATTENTION cite file:line evidence for every claim (confidence >80% to act) IMPORTANT MUST ATTENTION add a final review todo task to verify work quality

[TASK-PLANNING] Before acting, analyze task scope and systematically break it into small todo tasks and sub-tasks using TaskCreate.

[IMPORTANT] Analyze how big the task is and break it into many small todo tasks systematically before starting — this is very important.