Menu
Deep outward-facing research. Investigates external documentation, APIs, industry patterns, and best practices. Produces validated research briefs.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Specwright health check. Validates shared config, anchor docs, workflow and session state, commands, gates, and hooks. May backfill shipped PR metadata when it can prove the mapping safely.
Detects project stack and existing guardrails, then interactively configures deterministic quality checks across session, commit, push, and CI/CD layers.
Initializes Specwright in a project. Detects stack, asks about practices, creates constitution and charter, configures quality gates and hooks.
Shows current Specwright state for this worktree, the attached work, repo-wide active works, gate results, and lock status. Supports --reset, --cleanup, and --repair {unitId}.
Periodic codebase health check. Analyzes architecture, complexity, consistency, and debt across the full codebase. Produces persistent findings in AUDIT.md.
TDD implementation of one work unit. Delegates test writing to the tester agent and implementation to the executor agent. Commits per task.
| name | sw-research |
| description | Deep outward-facing research. Investigates external documentation, APIs, industry patterns, and best practices. Produces validated research briefs. |
| argument-hint | [topic or question to research] |
| allowed-tools | ["Read","Write","Glob","Grep","Task"] |
Produce validated, referenced research briefs as input to the design phase. Focus is outward — external docs, APIs, SDKs, industry patterns. Output is facts and evidence, never design opinions. Operates fully autonomously — briefs are consumed by sw-design (which has its own gate).
{projectArtifactsRoot}/research/ — existing briefs (for deepening or refresh){projectArtifactsRoot}/CHARTER.md — technology vision (for relevance filtering){projectArtifactsRoot}/research/{topic-id}-{YYYYMMDD}.md per protocols/research.mdStage boundary (LOW freedom):
Reads and researches. NEVER writes code, branches, mutates workflow state,
or produces design artifacts. No currentWork, no lock. Can run anytime.
It is not a core workflow stage and never claims top-level work ownership.
Triage (MEDIUM freedom):
protocols/decision.md DISAMBIGUATION if topic is ambiguous.Research (HIGH freedom):
Delegate to specwright-researcher per protocols/delegation.md. One call per track.
Parallel if Agent Teams available. Cite all sources with URLs. UNFETCHED → noted, not fabricated.
Synthesis (MEDIUM freedom): Merge findings. Score confidence: HIGH (official docs, multiple sources), MEDIUM (reputable secondary), LOW (single, unverified). Tag LOW/MEDIUM as potential assumptions. Flag open questions honestly.
Auto-approval (MEDIUM freedom): If all tracks have ≥MEDIUM confidence: auto-approve and persist the brief. Low-confidence tracks noted in the brief for consumer awareness. Briefs are consumed by sw-design which validates findings at its own gate.
Persistence (LOW freedom):
Write to {projectArtifactsRoot}/research/{topic-id}-{YYYYMMDD}.md. Overwrite same topic+date.
Max 10 briefs. If at cap: log warning, list by date, suggest cleanup.
Briefs older than 90 days are STALE — warn when loading.
protocols/decision.md -- autonomous decision framework (DISAMBIGUATION, auto-approval)protocols/research.md — brief format, staleness, lifecycleprotocols/delegation.md — agent delegation| Condition | Action |
|---|---|
| No topic | Infer from conversation context. If undetermined, STOP. |
| Researcher returns no findings | Note as "no results" for that track |
| Source cannot be fetched | Mark UNFETCHED; do not fabricate |
| All tracks LOW confidence | Persist with prominent warning. Consumer decides. |
| Research directory at cap | Log warning, list briefs by date |
| Compaction | Re-run from scratch |