메뉴
The routine for reviewing + evaluating the repo's agents and skills — quality, consistency, least-privilege tools, overlap, and drift vs the workflows — and opening one focused improvement PR.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
The autopilot engine for lifehacker.dev. Use when asked to "grow the site", "run the autopilot", "publish the next thing", "do an autopilot run", or to produce a new hack / tool review / field note. Reads the brand + backlog, drafts on-voice content with screenshots, files upstream bugs, and opens a PR for human review. Never pushes to main, never self-merges.
The repeatable flow for importing and REWRITING external/legacy articles into on-voice lifehacker.dev content. Use when asked to "import these posts", "rewrite the it-journey import", "bring in content from <source>", or to process a bulk-import PR (like #55) article-by-article. Triages every source file, routes it to the right collection, rewrites it through the content agents (never by hand), reuses preview images, preserves it-journey quest links, verifies with the harness, and opens ONE PR per collection in batches of 10. Never merges, never self-approves.
Reviews and improves a content pull request for lifehacker.dev. Use on a bot-authored content PR (hack/tool/post/doc) to analyze quality, completeness, and accuracy against the brand and the Prime Directive, apply small improvements directly to the PR, and backlog any larger ideas or follow-ups it surfaces. Comment-only on judgment calls; never merges, never self-approves.
The sister-site idea scout for lifehacker.dev. Use to "scout it-journey for ideas", "crawl the sister site for topics", "refill the content backlog from it-journey", or on a schedule before the content factory. Crawls a configured source site (it-journey.dev by default) along a seeded plan, reads pages via WebFetch, and — with no hand-picked topic — decides what fits the lifehacker.dev brand, proposing those topics into _data/backlog.yml each pinned to the source it-journey.dev page. Read-only on the source; opens ONE PR; never merges.
Turn a finished Claude Code thread into one honest, on-voice Field Note for the site — the narrative, the hard-won lessons, the durable concepts — then record it in the ledger. Reads the transcript, redacts every secret, opens one content PR, never merges.
Find theme UI/UX + accessibility issues and upstreamable local fixes in lifehacker.dev, and file deduped issues upstream to bamr87/zer0-mistakes so the site can focus on content.
| name | agent-skill-review |
| description | The routine for reviewing + evaluating the repo's agents and skills — quality, consistency, least-privilege tools, overlap, and drift vs the workflows — and opening one focused improvement PR. |
The automation runs on a set of agents (.claude/agents/<name>.md — the persona, tools, hard rules) that delegate to skills (.claude/skills/<name>/SKILL.md — the procedure). This routine keeps that set sharp. Run it periodically (the agent-review workflow) or on demand.
.claude/agents/*.md and .claude/skills/*/SKILL.md.ruby scripts/ci/lint_agents.rb — fix any structural finding (missing
frontmatter, name≠filename, a workflow agent: ref with no agent, a skill dir with no SKILL.md).grep -rn 'agent:' .github/workflows).For every agent + its skill, ask:
tools (and the workflow's --tools
allow-list) grant no more than the role needs. Flag anything that could merge, approve, or touch infra it shouldn't.lint_agents, the devops audit, and the simulation green..claude/agents/** and .claude/skills/**. Never weaken a guardrail,
never merge, never edit content/scripts/workflows. One PR per run.