en un clic
house-skills
house-skills contient 10 skills collectées depuis basecamp, avec une couverture métier par dépôt et des pages de détail sur le site.
Skills dans ce dépôt
Use when resolving zizmor warnings in GitHub Actions workflows, hardening CI pipelines, or pinning actions to SHA hashes. Covers artipacked, template-injection, excessive-permissions, secrets-outside-env, dependabot-execution, and when to suppress vs fix.
Fetch Basecamp project or person activity into day-cached JSON atoms. Uses the Basecamp API with pagination and rate-limit backoff. Part of the recap plugin's activity fetcher pipeline.
Fetch git log from local repos into day-cached JSON atoms. Simplest activity fetcher — no API calls, no pagination. Part of the recap plugin's activity fetcher pipeline.
Fetch GitHub PRs, reviews, issues, and commits into day-cached JSON atoms. Uses the gh CLI for authentication and API calls. Part of the recap plugin's activity fetcher pipeline.
Activity digests — pluggable source fetchers, progressive timescale synthesis, audience-aware composition. Discovers recap:*-activity fetchers, gathers cached activity, synthesizes narrative at daily/weekly/monthly timescales, and composes output for the target audience.
Create install.md files optimized for AI agent execution. Use for ANY question about install.md files or request to create/review installation documentation for autonomous agent use.
Create, edit, and refine agent skills through co-development and eval loops. Use for ANY question about skills or request to create/modify them.
Address PR review comments - fix issues, reply to threads, mark resolved
Get a second opinion via Codex MCP. Use for stress-testing ideas, getting fresh perspective, steelmanning arguments, or iteratively refining work through expert back-and-forth. Invoke for ANY request involving external review, feedback, or consultation.
Automated plan-implement loop with expert review. Orchestrator dispatches subagents for planning/implementation and self-review, Codex for external review. The human steers. A single rope-length knob (0-5) controls interruption frequency. Subagent architecture keeps the orchestrator's context window lean for completing tasks in a single session. Use for any planning, development, or implementation task that benefits from structured review.