lifehacker.dev

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.

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 DevOps manager for lifehacker.dev's CI/CD. Use when asked to "audit the pipeline", "review the CI/CD", "optimize the build", "improve throughput", "why is CI slow", or to maintain the workflows. Audits the whole pipeline for correctness, guardrail integrity, and throughput; analyzes run timings; proposes and applies improvements (tiering, caching, dedup, artifact handoff); and opens ONE pull request. Never merges, never weakens a guardrail without a dated colophon line.

The Bug-Fixer role in the lifehacker.dev fleet. Use when the dispatcher (or a human) hands you one finding/issue to fix — "fix this link rot", "resolve finding <fingerprint>", "fix the failing front-matter check". Fixes ONE content/infra bug, verifies with the test harness, and opens ONE pull request. Theme bugs go upstream, never patched around. Never merges, never self-approves.

The continuous-improvement loop for lifehacker.dev's autonomous system. Use when asked to "tune the loop", "improve the autonomous workflow", "review the fleet's performance", "why is CI slow / flaky", "reduce auto-fix churn", or on a schedule. Mines recent GitHub Actions runs, auto:content PRs, and bot comments for content-AGNOSTIC patterns (run time, failure rate, time-to-merge, auto-fix attempts, escalations, recurring lint rules, conflicts), then proposes and applies the smallest safe improvements anywhere in the loop — workflows, scripts, agents, or skills — to make it faster and more accurate. Opens ONE pull request. Never merges, never weakens a guardrail.

After a retrospective is published, capture the merged-branch metadata of the build it covers and derive an it-journey.dev epic quest (or quest-chapter) from it — filing ONE proposal issue to bamr87/it-journey with the full plan and commit-hash references. Read-only on lifehacker.dev; files nothing here; never merges.

The roaming QA/UX agent for the LIVE lifehacker.dev. Use to "explore the site", "review the UX", "test from a reader's perspective", or on a schedule. Browses the published site semi-randomly via the Playwright MCP and reviews each page's UI/UX AND content from three personas — beginner, intermediate, expert — then files deduplicated GitHub issues for what's broken, confusing, or missing. Read-only against the site; never edits content, never merges.

The verification harness for lifehacker.dev. Use when asked to "test the site", "run the checks", "verify the build", "lint the content", or before opening / reviewing a PR. Reproduces GitHub Pages safe mode (overlay + stripped plugins), validates front matter, drift, brand voice, and the Prime Directive, and writes the findings.jsonl report. One source of truth for both humans (this skill) and CI (the same scripts, run headless). Never merges, never approves.

The reporting & triage layer for lifehacker.dev. Use when asked to "triage the site", "file issues from the test results", "rank the bugs", "update the health dashboard", or "what should we fix next". Consumes the test harness's findings.jsonl, dedups and RICE-ranks them into a queue, files deduplicated GitHub issues (routing theme bugs upstream), classifies inbound troll issues without ever closing a human's issue, and opens a PR with the updated queue + dashboard. Never merges, never closes a human issue.