agentleFS
Sign inStart free
bostonaholicbostonaholic/team/skills/team-pr/SKILL.md

team-pr

Skill11 starsChanged 4 months agoMITView on GitHub

Use for opening PRs only on explicit request. Never infer from passed verification. Includes project terms, evidence, and risk.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before each consuming step, read its linked shared rules from this installed skill directory.

    line 10
  2. Distinctive:

    If a required read fails, stop that step with the exact path.

    line 11
  3. Very specific:

    Before finalizing prose you author, read the writing standards.

    line 13
  4. Distinctive:

    Update an existing CHANGELOG.md: after step 3 binds the review and security statuses, and commit before opening any PR.

    line 24
  5. Distinctive:

    After each push, refresh the body with exactly one closing line: never duplicated, never dropped (step 10).

    line 27
  6. Distinctive:

    Read each reference completely when reaching that stage, in order.

    line 36
  7. Distinctive:

    Read and apply: focused work rules.

    line 48

≈ “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

Team PR — Create the Pull Request

Before each consuming step, read its linked shared rules from this installed skill directory. If a required read fails, stop that step with the exact path. Never use checkout fallback or recursive loading.

Before finalizing prose you author, read the writing standards; for the PR body, apply its ## One busy reader rule and its ## Self-lint. Preserve exact commands, tokens, and templates.

Two modes:

  • Resume mode — $ARGUMENTS/1-task.md and $ARGUMENTS/6-design.md exist. Execution step 3 binds one review status from the newest review-<n>.md and one security status from the newest security-review-<n>.md.
  • Standalone mode — no matching artifact directory, but the working tree has commits or staged changes ready to ship. The current branch is the work source.

Core contracts

Each is detailed in Execution at the step named.

  1. Update an existing CHANGELOG.md after step 3 binds the review and security statuses, and commit before opening any PR; never create one unrequested (step 6).
  2. Open a draft PR automatically — do not stop to ask (step 7), then report it and how to mark it ready for review.
  3. Multi-repo: one draft PR per repo, with ## Companion PRs links. Tracking rules own the in-review transition and the home-only closing rule.
  4. After each push, refresh the body with exactly one closing line: never duplicated, never dropped (step 10).
  5. A branch that impacts a UI always carries screenshots (step 4).
  6. Deferred findings and cross-model dispositions are comments on the home PR, never the body: run review comments after open and after each refresh; a refresh posts only missing comments.
  7. Subagents and inline work split per Execution ## Step dispatch.

Apply the body authoring rules to initial drafts and every refresh.

Procedure references

Read each reference completely when reaching that stage, in order.

  1. Input
  2. Execution
  3. PR Body Template
  4. Screenshot Upload
  5. Changelog Update
  6. Commit Discipline
  7. Review Comments

Applied principles

Read and apply: focused work rules.

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