agentleFS
TheAstroByteTheAstroByte/astrobyte-agent-skills/skills/astrobyte-pr-workflows/SKILL.md

astrobyte-pr-workflows

Skill1 starsChanged 14 days agoMITView on GitHub

Explicit PR completion, Sol review loops, councils, and continuation commands.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 2 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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. Distinctive:

    Run the operation the operator requests.

    line 11
  2. Very specific:

    Read repository instructions and resolve the current delivery mode and acceptance evidence through ../astrobyte-mode/SKILL.md.

    line 13
  3. Very specific:

    Run this package's scripts/workflow_state.py policy --project <repository> to read effective personal options.

    line 14
  4. Distinctive:

    Read only the requested branch:

    line 15
  5. Very specific:

    Use an operation inside another only when that requested workflow includes it.

    line 25
  6. Very specific:

    Use T3 integration only when the effective t3 option is true and the relevant tools are available.

    line 29

≈ “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

Optional PR workflows

Run the operation the operator requests. Installing this package, mentioning a command in discussion, or encountering a risky change does not invoke a finish command, council, or takeover. A selected personal review_method: sol-loop permits the existing review gate to read that method without starting another operation.

  1. Read repository instructions and resolve the current delivery mode and acceptance evidence through ../astrobyte-mode/SKILL.md.
  2. Run this package's scripts/workflow_state.py policy --project <repository> to read effective personal options. It uses the installed router's resolver; missing dependencies or malformed settings remain errors.
  3. Read only the requested branch:
OperationProcedure
full-stop, full-sendFinish the task. Both names currently leave work unmerged.
sol-loopRun scoped independent review.
councilSelect and run council.
takeover, modernizeContinue existing work.
babysit-pr, file-pr, leaving-pr-commentsHandle PR work.

Use an operation inside another only when that requested workflow includes it. full-stop and full-send include scoped Sol review and relevant PR feedback, but never add council. Reuse a current independent verdict instead of reviewing the same change twice.

For explore and prototype, prove the intended question or runnable path. Defer uncommon, unobserved error handling unless it blocks that goal or the operator requests it. Give reviewers the mode and acceptance evidence. A finish command preserves the quality mode.

Use T3 integration only when the effective t3 option is true and the relevant tools are available. Other hosts keep their supported native tools. This package does not configure providers, grant external authority, or establish T3 installation support.

Finish with the observed result, exact current revision when relevant, verification, and any remaining decision. Keep internal review ledgers and model statistics in the operator report rather than routine PR prose.

Adapted from the reviewed tstack source. Keep its source license with this package.

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.