agentleFS
BoredHFBoredHF/albertskills/skills/shipit/SKILL.md

shipit

Skill2 starsChanged yesterdayMITView on GitHub

End-to-end feature delivery pipeline - grill requirements, run specify→plan→tasks→implement with model split, review/fix, then optionally PR/CI and merge/release.

5 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Show its rules and text

We split this skill into the rules it gives an agent

26 rules. 0 are common, 19 are distinctive, and 7 are very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 19

    Distinctive

    This author's own choices. Worth a look.

  • 7

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Very specific:

    Run a complete feature-delivery workflow from a feature description to optional PR/merge/release.

    line 8
  2. Distinctive:

    Not for small fixes or one-file changes: just make the change.

    line 10
  3. Very specific:

    If Spec Kit is not installed, stop and say so, naming the missing commands and the link above.

    line 17
  4. Distinctive:

    Never skip a failed step silently.

    line 21
  5. Distinctive:

    Never exceed the fix-cycle caps (5 for CI, 5 for release, 2 for review).

    line 22
  6. Distinctive:

    Never merge or release unless Phase 1 locked it.

    line 23
  7. Distinctive:

    If the user invoked this skill with a feature description, use it.

    line 27
  8. Very specific:

    If no description was provided, ask in normal assistant chat for the description and wait.

    line 28
  9. Very specific:

    After a description is available, grill the requirements first.

    line 29
  10. Very specific:

    Use AskUserQuestion to collect and confirm all decisions up front.

    line 33
  11. Distinctive:

    If PR path is selected, post-CI action (collect now, do not ask later):

    line 47
  12. Very specific:

    After Phase 1 completes, do not call AskUserQuestion again.

    line 61
  13. Distinctive:

    Ensure implementation includes spec artifacts in commits/PR by default.

    line 68
  14. Very specific:

    Run expensive review with claude-opus-5-5 (code-review agent).

    line 70
  15. Distinctive:

    Stop when no material findings remain, or after 2 review/fix cycles.

    line 73
  16. Distinctive:

    If locked decision is “stop after implementation”, stop here and report outcomes.

    line 74
  17. Distinctive:

    If locked decision is PR path:

    line 78
  18. Distinctive:

    Wait for PR pipelines.

    line 83
  19. Distinctive:

    If pipelines fail, fix and rerun until green or max 5 CI fix cycles reached.

    line 84
  20. Distinctive:

    If locked PR outcome is “stop when green”, stop and report.

    line 85
  21. Distinctive:

    If locked PR outcome includes merge+release:

    line 89
  22. Distinctive:

    Wait for release pipeline.

    line 93
  23. Distinctive:

    If release pipeline fails, fix and retry until success or max 5 release fix cycles reached.

    line 94
  24. Distinctive:

    Keep updates concise and outcome-first.

    line 107
  25. Distinctive:

    Do not silently skip failed steps.

    line 108
  26. Distinctive:

    If max retry cap is reached, stop with a clear blocker summary and exact failing pipeline/run links.

    line 109

“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

shipit

Run a complete feature-delivery workflow from a feature description to optional PR/merge/release.

Not for small fixes or one-file changes: just make the change. Use this when the feature merits a spec, plan and task list.

Requirements (check first)

  • Spec Kit installed in the project, so the slash commands /speckit-specify, /speckit-plan, /speckit-tasks and /speckit-implement exist (github.com/github/spec-kit).
  • Optional: a grilling skill and a code-review agent. Without grilling, run the requirements interview yourself (step 3). Without code-review, use a general-purpose agent with a review brief.
  • git, and gh or the repo host's CLI if the PR path is chosen.

If Spec Kit is not installed, stop and say so, naming the missing commands and the link above. Do not improvise the specify/plan/tasks/implement pipeline by hand, and do not run any phase.

Hard rules

  • No AskUserQuestion after Phase 1.
  • Never skip a failed step silently.
  • Never exceed the fix-cycle caps (5 for CI, 5 for release, 2 for review).
  • Never merge or release unless Phase 1 locked it.

Invocation contract

  1. If the user invoked this skill with a feature description, use it.
  2. If no description was provided, ask in normal assistant chat for the description and wait. Do not use AskUserQuestion for this step.
  3. After a description is available, grill the requirements first. If a grilling skill is installed, invoke it. Otherwise interview the user yourself: ask the open decisions in rounds, give a recommended answer to each, and wait for replies before moving on.

Phase 1: Grill-and-lock session (interactive)

Use AskUserQuestion to collect and confirm all decisions up front. This is the only interactive phase.

You must confirm each run:

  1. The feature description/scope (using the provided description as starting point).
  2. Model split:
    • /speckit-specify = claude-opus-5-5 (default, expensive)
    • /speckit-plan = claude-opus-5-5 (default, expensive)
    • /speckit-tasks = claude-opus-5-5 (default, expensive)
    • /speckit-implement = claude-sonnet-5-5 (default, cheaper)
  3. Optional invocation overrides (if provided in user text), but still confirm before execution.
  4. Post-implementation action (collect now, do not ask later):
    • Recommended: create PR, wait for CI, auto-fix failures
    • Alternative: stop after implementation + review recommendations are applied
  5. If PR path is selected, post-CI action (collect now, do not ask later):
    • Recommended: stop when PR pipelines are green
    • Alternative: merge using default merge options, then cut a release
  6. Release bump policy (if release path might be used):
    • Suggest patch for bugfix/compat-only work
    • Suggest minor for new user-visible capability
    • Confirm the selected bump during this initial session
  7. Failure-handling cap:
    • Up to 5 auto-fix cycles for CI/release failures

At the end of this phase, produce a compact locked execution summary and proceed autonomously.

Phase 2: Autonomous execution (no more AskUserQuestion)

After Phase 1 completes, do not call AskUserQuestion again.

  1. Run:
    • /speckit-specify (claude-opus-5-5 by default)
    • /speckit-plan (claude-opus-5-5 by default)
    • /speckit-tasks (claude-opus-5-5 by default)
    • /speckit-implement (claude-sonnet-5-5 by default)
  2. Ensure implementation includes spec artifacts in commits/PR by default.
  3. Review/fix loop:
    • Run expensive review with claude-opus-5-5 (code-review agent).
    • Apply fixes with claude-sonnet-5-5.
    • Re-review with claude-opus-5-5.
    • Stop when no material findings remain, or after 2 review/fix cycles.
  4. If locked decision is “stop after implementation”, stop here and report outcomes.

Phase 3: PR/CI (conditional)

If locked decision is PR path:

  1. Commit changes.
  2. Push branch.
  3. Create PR.
  4. Wait for PR pipelines.
  5. If pipelines fail, fix and rerun until green or max 5 CI fix cycles reached.
  6. If locked PR outcome is “stop when green”, stop and report.

Phase 4: Merge + release (conditional)

If locked PR outcome includes merge+release:

  1. Merge PR using default merge options.
  2. Cut release with the previously confirmed bump type (patch/minor).
  3. Wait for release pipeline.
  4. If release pipeline fails, fix and retry until success or max 5 release fix cycles reached.

Final report

End with: feature, branch/PR link, per-phase result, review cycles used, and release tag if any. Five lines or fewer, then TL;DR:.

Anti-patterns

  • Asking the user something new mid-run instead of using the locked summary.
  • Reading the setup's model names as fixed: confirm them in Phase 1, since they are defaults.
  • Calling the spec commands before Spec Kit is confirmed present.
  • Leaving spec artifacts out of the commit.

Operational rules

  • Keep updates concise and outcome-first.
  • Do not silently skip failed steps.
  • If max retry cap is reached, stop with a clear blocker summary and exact failing pipeline/run links.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.