modify template

2026-04-24 08:34:53 +09:00
parent e2c2beae1a
commit 246d164827
68 changed files with 2378 additions and 0 deletions
@@ -0,0 +1,46 @@
+---
+description: Run the Report Harness planning workflow for this repository.
+---
+
+# /harness
+
+## Preflight
+
+- Read `/AGENTS.md`, `/docs/PRD.md`, `/docs/ARCHITECTURE.md`, `/docs/ADR.md`, `/docs/UI_GUIDE.md`, `/docs/RESEARCH_LOG.md`, `/docs/REPORT_DRAFT.md`, and `/docs/FEEDBACK.md` if they exist.
+- Confirm whether the user wants discussion only, a draft report plan, or file generation under `phases/`.
+- Check that the report topic, purpose, keywords, direction, audience, and output format are available.
+- Note whether the user explicitly asked for subagents; only then consider `phase_planner` or built-in explorers/workers.
+
+## Plan
+
+- State what will be created or updated before editing files.
+- If a plan already exists under `phases/`, say whether you are extending it or replacing part of it.
+- Keep each proposed step small, self-contained, and independently executable.
+- Separate source discovery, deep research, source review, outline, draft, and feedback steps.
+
+## Commands
+
+- Invoke `$harness-workflow` and follow it.
+- When file generation is requested, create or update:
+  - `phases/index.json`
+  - `phases/{phase}/index.json`
+  - `phases/{phase}/stepN.md`
+- Use `python scripts/execute.py <phase>` as the runtime target when you need to reference execution.
+
+## Verification
+
+- Re-read the generated phase files for consistency.
+- Check that step numbering, phase names, report artifacts, and acceptance commands line up.
+- Confirm that research steps require web search and `docs/RESEARCH_LOG.md` updates.
+- If the repo has a validator, prefer `python scripts/validate_workspace.py` as the default acceptance command unless the user specified a narrower command.
+
+## Summary
+
+## Result
+- **Action**: planned or generated Report Harness phase files
+- **Status**: success | partial | failed
+- **Details**: phase name, step count, report artifacts, and any blockers
+
+## Next Steps
+
+- Suggest the next natural command, usually `python scripts/execute.py <phase>` or a focused edit to one generated step.
@@ -0,0 +1,38 @@
+---
+description: Review report changes against Report Harness repository rules and docs.
+---
+
+# /review
+
+## Preflight
+
+- Read `/AGENTS.md`, `/docs/PRD.md`, `/docs/ARCHITECTURE.md`, `/docs/ADR.md`, `/docs/UI_GUIDE.md`, `/docs/RESEARCH_LOG.md`, `/docs/REPORT_DRAFT.md`, and `/docs/FEEDBACK.md` if they exist.
+- Identify the changed report files, research logs, feedback files, or generated `phases/` artifacts that need review.
+- If the user wants a delegated review, use the read-only custom agent `harness_reviewer` only when they explicitly asked for subagents.
+
+## Plan
+
+- State what evidence will be checked: brief alignment, research coverage, source quality, unsupported claims, feedback handling, generated phase files, and validation output if available.
+- Prioritize factual support, source freshness, CRITICAL rule violations, and missing counterarguments over style commentary.
+
+## Commands
+
+- Invoke `$harness-review`.
+- Use Codex built-in `/review` when the user specifically wants a review-style pass over the working tree or generated report artifacts.
+- If validation is relevant, run `python scripts/validate_workspace.py` or explain why it was not run.
+
+## Verification
+
+- Confirm that every finding is tied to a file and an actual rule or report-quality risk.
+- If no findings remain, say so explicitly and mention residual risks or missing evidence.
+
+## Summary
+
+## Result
+- **Action**: reviewed Report Harness changes
+- **Status**: success | partial | failed
+- **Details**: findings, docs checked, and validation status
+
+## Next Steps
+
+- Suggest the smallest follow-up: fix the top finding, rerun validation, or execute a pending phase.