agentleFS
redicherediche/skills/auto-complete-task/SKILL.md

auto-complete-task

Skill3 starsChanged 39 days agoMITView on GitHub

Completes requested work autonomously through investigation, subtask planning, implementation, testing, and GitHub PR creation. Use when the user explicitly invokes auto-complete-task to complete a feature, bug fix, optimization, GitHub issue, or plain-text request.

The file

Show its rules and text

We split this skill into the rules it gives an agent

25 rules. About 0 are common, 23 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈23

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    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. Distinctive:

    Run this skill only when the user explicitly invokes it.

    line 22
  2. Distinctive:

    Do not invoke this skill automatically from another skill or agent.

    line 23
  3. Distinctive:

    Treat invocation as authorization to implement, test, commit, push, and create a PR for the request.

    line 24
  4. Distinctive:

    Do not merge the PR.

    line 25
  5. Distinctive:

    Follow repository instructions, tool permissions, and higher-priority restrictions.

    line 26
  6. Distinctive:

    Treat features, bugs, and optimizations as valid requests.

    line 33
  7. Distinctive:

    Ask what to work on only when no request was supplied.

    line 34
  8. Distinctive:

    Read applicable repository instructions.

    line 35
  9. Distinctive:

    Check the working tree with git status --short.

    line 36
  10. Distinctive:

    Stop on dirty files unless the user explicitly authorized continuing despite them.

    line 38
  11. Distinctive:

    Never modify, revert, or stage unrelated changes.

    line 39
  12. Distinctive:

    Never create another worktree.

    line 41
  13. Very specific:

    Default the target branch to main on origin.

    line 45
  14. Distinctive:

    Use another target branch or remote when the user explicitly specifies one.

    line 46
  15. Distinctive:

    Stop if the target is missing or fetching fails.

    line 51
  16. Distinctive:

    Never substitute stale local branches or the current branch for the selected target.

    line 52
  17. Very specific:

    Start a read-only subagent and instruct it to load investigate-issue.

    line 56
  18. Distinctive:

    Use read-only Git commands to inspect target files when the current checkout differs.

    line 59
  19. Distinctive:

    Do not authorize file edits or implementation in the investigation subagent.

    line 61
  20. Distinctive:

    Ask only when missing access, conflicting requirements, or consequential ambiguity prevents safe progress.

    line 69
  21. Distinctive:

    Do not invent requirements to avoid asking a necessary question.

    line 70
  22. Distinctive:

    Use its autonomous handoff instead of requesting subtask approval.

    line 73
  23. Distinctive:

    Follow its implementation, testing, separate-commit, push, and PR verification rules.

    line 84
  24. Distinctive:

    Do not push partial work or create a PR before all subtasks and required checks pass.

    line 86
  25. Distinctive:

    If blocked, report completed work and the exact action needed to continue.

    line 88

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Auto Complete Task

Quick start

Example: Auto-complete-task: fix the search timeout described in #123.

  1. Accept the work request.
  2. Delegate investigation to a subagent using investigate-issue.
  3. Load to-subtasks and generate implementation subtasks.
  4. Load to-pr and execute the subtasks without separate approval.
  5. Return the PR URL and validation results.

Authorization

  • Run this skill only when the user explicitly invokes it.
  • Do not invoke this skill automatically from another skill or agent.
  • Treat invocation as authorization to implement, test, commit, push, and create a PR for the request.
  • Do not merge the PR.
  • Follow repository instructions, tool permissions, and higher-priority restrictions.

Workflow

1) Intake and preflight

  • Accept a GitHub issue URL, issue number, or plain-text work request.
  • Treat features, bugs, and optimizations as valid requests.
  • Ask what to work on only when no request was supplied.
  • Read applicable repository instructions.
  • Check the working tree with git status --short.
  • Preserve the dirty-file safeguards from to-pr.
  • Stop on dirty files unless the user explicitly authorized continuing despite them.
  • Never modify, revert, or stage unrelated changes.
  • Stay in the current directory, including when it is already a worktree.
  • Never create another worktree.

2) Resolve the target

  • Default the target branch to main on origin.
  • Use another target branch or remote when the user explicitly specifies one.
  • Fetch the selected target before investigation.
  • For the default, run git fetch origin main.
  • Resolve the fetched target commit with git rev-parse FETCH_HEAD.
  • Record the target branch name, remote, and fetched commit separately.
  • Stop if the target is missing or fetching fails.
  • Never substitute stale local branches or the current branch for the selected target.

3) Investigate in a subagent

  • Start a read-only subagent and instruct it to load investigate-issue.
  • Supply the request, repository path, target commit, constraints, and relevant conversation context.
  • Require investigation against the fetched target commit.
  • Use read-only Git commands to inspect target files when the current checkout differs.
  • Require evidence, acceptance criteria, proposed changes, validation options, and blockers.
  • Do not authorize file edits or implementation in the investigation subagent.
  • Continue factual investigation when findings are insufficient.

4) Plan autonomously

  • Resolve routine uncertainty from repository evidence and established project conventions.
  • Choose the smallest supported change that satisfies the request.
  • Record reasonable, non-blocking assumptions.
  • Ask only when missing access, conflicting requirements, or consequential ambiguity prevents safe progress.
  • Do not invent requirements to avoid asking a necessary question.
  • Load to-subtasks with the request, investigation findings, acceptance criteria, and constraints.
  • Identify this as an explicitly user-invoked auto-complete-task workflow.
  • Use its autonomous handoff instead of requesting subtask approval.
  • Include relevant regression coverage and validation checks in the implementation subtasks.

5) Implement and open the PR

  • Load to-pr with the authorized subtasks.
  • Explicitly supply the fetched commit as the work branch starting point.
  • Explicitly supply the selected branch name as the PR base, such as main, not origin/main.
  • Supply the selected remote and original GitHub issue reference when applicable.
  • Apply these branch instructions only to this run.
  • Preserve the standalone current-branch default in to-pr.
  • Follow its implementation, testing, separate-commit, push, and PR verification rules.
  • Preserve its safeguards, including dirty-file, label-selection, and validation blockers.
  • Do not push partial work or create a PR before all subtasks and required checks pass.
  • Return the PR URL, completed work, validation results, assumptions, and blast-radius rationale.
  • If blocked, report completed work and the exact action needed to continue.

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.