Workflow Research

Quick Summary

Goal: [Workflow] Trigger Research & Synthesis workflow — resolve the target artifact selected by --output to a complete canonical manifest variant, gather web sources, then synthesize the requested knowledge report, business evaluation, marketing strategy, or course material.

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.
• NEVER skip mandatory workflow or skill gates.

IMPORTANT MANDATORY Steps: resolve the workflow-research manifest variant for --output first, then invoke its exact ordered steps (default: /web-research -> /deep-research -> /knowledge-synthesis -> /knowledge-review -> /workflow-end).

These steps are the default --output=synthesis sequence (identical to the catalog workflow-research workflow sequence). For --output={business-eval|marketing|course} the terminal synthesis skill(s) swap per the Output Dispatch table below — the research scaffold and /knowledge-review -> /workflow-end closure are invariant.

Output Dispatch (--output)

All modes share the research scaffold /web-research → /deep-research → … → /knowledge-review → /workflow-end; only the terminal synthesis skill(s) swap per --output:

[BLOCKING] Each step MUST ATTENTION invoke its Skill tool — marking a task completed without skill invocation is a workflow violation. NEVER batch-complete validation gates.

This skill IS the canonical Research & Synthesis entry point — invoke it directly with --output=<mode> (default synthesis), resolve the matching complete variant through .claude/scripts/lib/workflow-manifest.cjs, and execute every returned occurrence in order via the Skill tool. The workflow catalog exposes the same four variants for auto-routing and /start-workflow workflow-research; never execute a prose-swapped sequence that differs from the resolved manifest.

[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.

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.

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.

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.

• 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.

Closing Reminders

IMPORTANT MUST ATTENTION Variant closure: record the selected --output mode, resolver fingerprint, ordered occurrence IDs, each invoked skill's evidence, and any conditional skip before /workflow-end; a variant mismatch is a workflow failure.

IMPORTANT MUST ATTENTION Protocols in force (concise digest of the SYNC/shared blocks this skill carries) — NEVER treat a digest line as the full rule; it signposts the canonical SYNC body above:

• Nested Task Creation: Expand child phases under the parent workflow row; link when nested.
• Critical Thinking: Apply critical + sequential thinking; cite proof, confidence >80% to act.
• AI Mistake Prevention: verify generated content against evidence, trace downstream references, verify all affected outputs, re-read after context loss, surface ambiguity.
• Incremental Persistence: Persist findings to plans/reports/ per file; survive context cutoff.
• Subagent Return Contract: Sub-agents return summary plus report pointer only, never inline transcript.

IMPORTANT MUST ATTENTION apply Phase 1 compression before structural enhancement; preserve semantic meaning. IMPORTANT MUST ATTENTION NEVER alter YAML frontmatter, code blocks, tables, or SYNC-tag bodies during optimization. IMPORTANT MUST ATTENTION keep evidence gates and mandatory workflow/skill steps explicit and enforceable. IMPORTANT MUST ATTENTION add a final review task to verify output quality and unresolved risks.