workflow-research

name	workflow-research
version	1.0.0
description	[Workflow] Use when activating the Research & Synthesis workflow — research a topic via web sources, then synthesize per --output={synthesis|business-eval|marketing|course} (knowledge report, business evaluation, marketing strategy, or course material).
disable-model-invocation	false

Quick Summary

Goal: [Workflow] Trigger Research & Synthesis workflow — gather web sources, then synthesize into the target artifact selected by --output (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: /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:

--output	Terminal synthesis skill(s)	Full sequence
synthesis (default)	/knowledge-synthesis	/web-research → /deep-research → /knowledge-synthesis → /knowledge-review → /workflow-end
business-eval	/market-analysis + /business-evaluation	/web-research → /deep-research → /market-analysis → /business-evaluation → /knowledge-review → /workflow-end
marketing	/market-analysis + /strategy-builder	/web-research → /deep-research → /market-analysis → /strategy-builder → /knowledge-review → /workflow-end
course	/course-builder	/web-research → /deep-research → /course-builder → /knowledge-review → /workflow-end

[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) and execute the selected sequence from the dispatch table above: invoke each step skill in order via the Skill tool with the user's prompt as context. The workflow catalog also exposes a workflow-research id purely so the auto-router can detect research/business-eval/marketing/course intents; /start-workflow workflow-research is equally valid and injects the same OUTPUT DISPATCH table — either path executes the sequence for the selected --output.

[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. Before changing a constant, limit, flag, wording, or pattern, read nearby context and history. Surface ambiguity before acting — don't pick silently. Multiple valid interpretations require an explicit question or stated assumption with risk. 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
2. After each file/section reviewed: Append findings to report immediately — never hold in memory
3. Return to main agent: Summary only (per SYNC:subagent-return-contract) with Full report: path
4. Main agent: Reads report file only when resolving specific blockers

Why: Context cutoff mid-execution loses ALL in-memory findings. Each disk write survives compaction. Partial results are better than no results.

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 this structure. Main agent reads only this summary — NEVER requests full sub-agent output inline.

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

Status: ✅ PASS | ⚠️ PARTIAL | ❌ FAIL
Confidence: [0-100]%

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

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

### Actions Taken

- [file changed] [what changed]

### Blockers (if any)

- [blocker description]

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

Main agent reads Full report file ONLY when: (a) resolving a specific blocker, or (b) building a fix plan. Sub-agent writes full report incrementally (per SYNC:incremental-persistence) — not held in memory.

Context budget — the return payload is a SUMMARY, not a transcript: ≤10 finding bullets, no raw file contents / full diffs / verbatim logs inline, no re-pasted source. Everything beyond the summary lives in the Full report on disk. A sub-agent that would exceed the summary shape MUST write the detail to its report and return only the pointer — the orchestrator's context is the scarce resource the whole map-reduce protects.

• 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.

Closing Reminders

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.