agent-watchdog
Use when asked to watch, babysit, audit, review, compare, or fix another agent's work from a…
Experimental workflow for publishing and completing configured software delivery work. Use when the user or an enabled factory policy asks to ship.
$ npx -y skills add BuilderIO/skills --skill factory-ship --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/factory-shipContext preview
The summary Claude sees to decide when to auto-load this skill.
Experimental workflow for publishing and completing configured software delivery work. Use when the user or an enabled factory policy asks to ship.
name: factory-ship installer-group: factory description: >- Experimental workflow for publishing and completing configured software delivery work. Use when the user or an enabled factory policy asks to ship.
> Start with the [Factory guide](../../docs/factory/README.md) for workflow > setup and configuration.
Read `.agent-factory/config.yaml`, the optional `skill_prompts.factory-ship` entry, and the repository's instructions before publishing. See the [Factory configuration reference](https://github.com/BuilderIO/skills/blob/main/docs/factory/configuration.md). The prompt adds project guidance; editing code does not by itself authorize a PR update, approval, merge, or deployment.
1. **Confirm ownership.** Identify the target repository, task-owned worktree, branch, and complete task-related change set. Preserve unrelated changes. Use a clean automation-owned worktree when the scheduler provides one; never take over a peer's checkout. 2. **Verify changes.** Run the configured formatter, tests, and release checks. Report checks that were skipped or unavailable. 3. **Publish when enabled.** Open or update a PR only when authorized. Apply configured title, body, draft status, labels, and communication rules. Do not tag or message people unless enabled. 4. **Resolve feedback.** Compare comments with the code and current human direction. Make one coherent update, then rerun affected checks. 5. **Apply merge gates.** Merge only under its own enabled policy and while all criteria hold on the unchanged live head. Use a head-match guard when the host supports it. A head change invalidates tied evidence and resets the soak. 6. **Verify and close out.** Confirm the merge in the current base branch. Verify deployment only when configured; a merge is not live proof. Close issues, rotate worktrees, and notify only at their configured proof points.
Hold the work when ownership, authorization, a required check, or live host state is missing or unclear. State the exact next step; do not turn an inconclusive result into success.
Small, composable skills for your favorite agent.
Repo: BuilderIO/skills
Use when asked to watch, babysit, audit, review, compare, or fix another agent's work from a…
Open and operate Agent-Native workspace apps through Dispatch MCP, with inline app surfaces,…
Use when running Claude Fable on codebase-heavy or token-heavy work and the user wants Fable…
Apply the same orchestration as `/efficient-fable` to any high-cost frontier model: delegate…
Experimental workflow for babysitting one explicitly authorized pull or merge request. Use to…
Experimental workflow for collecting and triaging product feedback, product telemetry,…