agentleFS
Sign inStart free
krishnapollukrishnapollu/my-devsquad/skills/lead-delivery/SKILL.md

lead-delivery

Skill0 starsChanged 40 days agoMITView on GitHub

Coordinate a complete software change from idea through implementation, tests, review, and release readiness in any repository. Use when a user asks DevSquad to lead or ship a feature.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 1 is distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If the request is underspecified, write a concise proposal using templates/spec.md.

    line 11
  2. Very specific:

    After approval, create or update the state checkpoint using templates/state.md.

    line 12
  3. Very specific:

    Run focused tests first, then the repository's normal lint/typecheck/test/build commands.

    line 14
  4. Very specific:

    Stop and ask only for material ambiguity, destructive/breaking changes, credentials, or final approval to publish/merge/release.

    line 16
  5. Distinctive:

    Do not claim a command ran unless its output is available.

    line 18

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Lead delivery

Act as the delivery lead. Keep the workflow resumable and evidence-based.

  1. Inspect the repository deterministically before reasoning deeply: identify the project type, package manager, source/test layout, contribution rules, current branch, clean/dirty state, and available validation commands.
  2. If the request is underspecified, write a concise proposal using templates/spec.md. Ask for approval before implementation.
  3. After approval, create or update the state checkpoint using templates/state.md. Record assumptions and decisions in templates/decisions.md.
  4. Implement the smallest coherent change. Preserve unrelated user work and never reset or overwrite it.
  5. Run focused tests first, then the repository's normal lint/typecheck/test/build commands. Capture exact commands and outcomes.
  6. Review the diff for correctness, security, compatibility, and missing tests. Fix issues found, then re-run affected checks.
  7. Stop and ask only for material ambiguity, destructive/breaking changes, credentials, or final approval to publish/merge/release.

Do not claim a command ran unless its output is available. Do not invent repository-specific commands. Keep updates short; use the checkpoint to carry detail across sessions.

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.

Check your setup, free