Menu
Scripts directory contract — canonical build/test/install/release.sh patterns for deployable projects. Triggers on: scripts/, release.sh, build.sh, deploy, publish.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Gotchas for the agents-cli headless release. The macOS home base signs, notarizes, and npm-publishes over SSH with no GUI and no Touch ID — three things must be primed or the release stalls. Triggers on: release stuck at sign/publish, errSecInternalComponent, "no npmjs.com bundle", "Missing embedded.provisionprofile", making the release autonomous.
Search, browse, and read agent conversation transcripts across Claude, Codex, Gemini, and OpenCode. Use this skill to find previous sessions, recover context, or inspect what agents have done.
Organize AI coding agents into teams that collaborate on a shared task. Create teams, add teammates, start them, monitor progress, and collect results. Use this skill when you need parallel agent execution. For single-agent dispatch, use `agents run` instead.
Use FIRST for any question about THIS codebase's structure, symbols, or relationships — where a function/class/file is defined, what calls or imports it, what breaks if you change it, how two parts connect, or to load focused source context before editing or reviewing. Routes to the cgraph MCP tools (graph_query / graph_explain / graph_impact / graph_path / graph_context), which serve ranked file:line results, node neighborhoods, transitive blast radius, and token-budgeted source bundles from a resident per-project graph daemon in ~10ms — far cheaper than grepping and reading files. Prefer over blind grep/read for code navigation, dependency tracing, and impact analysis.
Register and connect to your machines over Tailscale SSH with agents-cli. Use this skill to sync devices from the tailnet, list them, open a shell on another machine, or see agent sessions running across your whole fleet.
Schedule agents to run on a cron schedule or one-shot at a specific time. The scheduler auto-starts on first add. Triggers on: 'schedule an agent', 'recurring job', 'cron', 'daily', 'every weekday', 'run at 2pm'.
| name | scripts |
| description | Scripts directory contract — canonical build/test/install/release.sh patterns for deployable projects. Triggers on: scripts/, release.sh, build.sh, deploy, publish. |
| user-invocable | false |
Every deployable project keeps a scripts/ directory with a small set of canonical scripts. Use them. Don't reinvent.
scripts/build.sh — compile/bundle and run the test suite. Green build means tests passed.scripts/test.sh — full test suite, runnable on its own.scripts/install.sh — install dependencies, set up local config.scripts/release.sh — ship the artifact (npm publish, docker push, deploy, etc.). Use release as the canonical name — covers all forms of shipping.--confirm, the script prints exactly what it would do and exits 0. Nothing mutates.--confirm is required to actually release. No other flag substitutes.--skip-build and --skip-tests are escape hatches for re-runs after a verified-elsewhere build, or hotfixes. Default: run both.--skip-tests was explicitly passed. If you find yourself adding || true to silence a check, stop.npm view <pkg> versions --json against package.json) before bun test. Missing-secrets check before git push. Cheap failures fast.release.sh is interrupted between version-bump and the actual publish, re-running converges — no double-bump, no double-tag.A release isn't done until the package version shows up on the registry (or the deploy URL serves the new build). Code merged is not released.
release.sh that publishes without running tests by default.git log subject lines instead of the registry.deploy.sh with no dry-run mode that hits production on every invocation.