Sweep the web for new chatter on a topic, skip what earlier runs already saw, verify what is left, and write one ranked, cited findings file to feed a blog post or a digest email.

Verify, triage, fix, and close review-bot GitHub issues one finding at a time.

The tool each agent harness (Claude Code, Codex, Grok, agy) uses to start, follow up with, or stop a sub-agent, and to ask the user a structured question. Use when a skill names one of these moves and points here, or when you are not sure which tool your harness has for it.

Run a conservative code-project housekeeping pass: one proven low-risk cleanup at a time.

Audit and clean Git repository state: branches, PRs, stashes, worktrees, and the local databases old worktrees left behind.

Run this session's waiting steps (a backfill after deploy, a command after commit or merge) once their trigger lands. Start the deploy, then run this: it confirms the steps, watches for the trigger, and runs them.

Sweep a dusty .scratch/: file research into docs/, remove finished efforts, and report the work still open.

Report what is still open across .scratch/ and the next skill to run for each effort. Read-only.

Turn a decision the user can't fully answer into a Markdown questionnaire for someone else to fill in, async or over a meeting.

Break a spec into tracer-bullet vertical-slice tickets with explicit blocking edges, settle the build's open decisions, and save one markdown file per ticket beside the spec. Use when the user asks to break a spec or map into tickets.

Plan a library or framework upgrade from the installed version to the latest. Finds what breaks, which local patches and workarounds can go, and what to adopt, sorted into must do, should do, and do later.

Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, creating credentials or CI secrets in a third-party dashboard, or running a one-off migration or cutover. For steps the agent can perform itself, perform them.