メニュー
Reads every documentation file in the project, cross-references the current diff, and updates everything that drifted. Catches stale READMEs, outdated ARCHITECTURE, and missing CHANGELOG entries.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Builds production-grade Claude Projects and CustomGPTs, improves AI output quality using meta-thinking prompts, and architects self-improving AI systems. Use proactively when a founder wants to build a reliable AI workflow, automate a repeatable task with AI, improve the quality of AI outputs they're getting, feels stuck with generic AI responses, or wants to build internal tools powered by Claude. Trigger for "build a Claude project", "my AI outputs are generic", "how do I make Claude more specific", "build an AI workflow", "automate this with AI", or "my prompts aren't working".
One-command review pipeline. Chains CEO review → design review → eng review automatically. Surfaces only taste decisions for PD approval. Everything else runs autonomously.
Performance baseline measurement. Captures page load times, Core Web Vitals, and resource sizes. Compare before/after on every PR.
Playbook for bootstrapped and early-stage SaaS founders based on proven case studies ($0 to $5M ARR with 6 people, and creator-to-business flywheel models). Use proactively when a founder is bootstrapped or capital-efficient, needs to grow without paid acquisition, is facing a churn crisis, wants to build a freemium or usage-based model, or asks "how do I grow without VC money". Also trigger for "PLG", "inbound-led outbound", "creator-led growth", "build in public", or "how did [bootstrapped company] grow".
Real browser automation for testing, QA, and demo verification. Provides Playwright-based browser control for navigating the live app, clicking elements, filling forms, taking screenshots, and verifying visual state.
Post-deploy monitoring. After release-engineer pushes to production, canary watches the live site for errors, performance regressions, and page failures.
| name | document-release |
| description | Reads every documentation file in the project, cross-references the current diff, and updates everything that drifted. Catches stale READMEs, outdated ARCHITECTURE, and missing CHANGELOG entries. |
| used_by | ["release-engineer","ceo-thinking-partner"] |
Run this as part of every release (release-engineer uses it before commit).
| File | Check against | Update if |
|---|---|---|
| docs/CHANGELOG.md | git log since last version tag | New entries needed |
| docs/SESSION_LOG.md | Current session agent completions | Missing entries |
| README.md | Current version, routes, features | Version outdated, routes changed, features added/removed |
| docs/ARCHITECTURE.md | Current API routes + database tables | New routes or tables added |
| docs/PRODUCT_ROADMAP.md | Completed Jira tickets | Features not ticked off |
| docs/DECISIONS.md | Any constraints hit this session | Undocumented decisions |
| VALIDATION_LOG.md | Consensus items | Missing sign-offs |
| docs/FRONTEND_ARCHITECTURE.md | src/ directory structure | New pages or components not listed |
| docs/BACKEND_ARCHITECTURE.md | backend/ directory structure | New routes or tables not listed |
| AGENT_REGISTRY.md | .claude/agents/ directory | New agents not registered |
Step 1 — Diff scan:
Run git diff main --stat (or git diff HEAD~N if on main) to see what files changed.
Step 2 — For each documentation file:
Step 3 — Version bump:
CLAUDE.md PROJECT STATUS tableCLAUDE.md, README.md, docs/CHANGELOG.md, package.json (if version field exists)Step 4 — Report:
Document Release Report — [date]
Files updated: [list]
Files already current: [list]
Version: [old] → [new]