agentleFS
AWSKnown publisherawslabs/loom/.claude/skills/issue/SKILL.md

issue

Skill199 starsChanged 4 months agoApache-2.0View on GitHub

Implement a GitHub issue end-to-end — branch, code, test, docs, and commit.

We split this skill into the rules it gives an agent

16 rules. 0 are common, 13 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 40 edited versions we read keep these.

  • 13

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    Run gh issue view $ARGUMENTS --json title,body,labels to get the issue details.

    line 18
  2. Very specific:

    If no matching file exists, derive the branch name from the issue number and title: zero-pad the issue number to 3 digits, kebab-case the …

    line 28
  3. Very specific:

    Create and switch to the feature branch: git checkout -b <branch-name>.

    line 30
  4. Distinctive:

    Read the full issue body and any linked markdown file.

    line 34
  5. Distinctive:

    Create a task list using TaskCreate for each requirement so progress can be tracked.

    line 36
  6. Distinctive:

    Before writing any code, present the implementation plan to the user and wait for confirmation.

    line 38
  7. Distinctive:

    Use an agent team to parallelize independent work where possible:

    line 42
  8. Distinctive:

    Update TaskUpdate as each requirement is completed.

    line 49
  9. Distinctive:

    Run existing tests to check for regressions:

    line 53
  10. Distinctive:

    If the issue specifies new test cases, implement and run them.

    line 59
  11. Distinctive:

    All tests must pass before proceeding.

    line 61
  12. Distinctive:

    Update the following documentation files to reflect the new changes:

    line 65
  13. Distinctive:

    SPECIFICATIONS.md: Update any relevant specification files with the latest design decisions.

    line 67
  14. Distinctive:

    README.md: Update any relevant README files with the latest implementation details.

    line 68
  15. Distinctive:

    Run the full test suite one more time to confirm nothing was broken during documentation updates.

    line 72
  16. Distinctive:

    Do NOT push to remote. Only commit locally.

    line 87

“Common” is measured: kept by at least 6 in 10 of the 40 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

Issue Implementation

Implement a GitHub issue end-to-end: fetch the issue, create a feature branch, implement all requirements, test, update docs, and commit.

Input

$ARGUMENTS must be a GitHub issue number (e.g. 78). If missing or non-numeric, ask the user for the issue number.

Step 1: Fetch the Issue

Run gh issue view $ARGUMENTS --json title,body,labels to get the issue details.

Also check if a matching markdown file exists under tmp/issues/ by looking for files that start with a zero-padded version of the issue number (e.g. issue 78 maps to a file starting with 078-). If the file exists, read it for additional context.

Display the issue title and a brief summary to the user.

Step 2: Create Feature Branch

Determine the branch name from the matching issue markdown filename under tmp/issues/, but without the .md extension. For example, if the file is 078-my-feature.md, the branch name is 078-my-feature.

If no matching file exists, derive the branch name from the issue number and title: zero-pad the issue number to 3 digits, kebab-case the title, and join with a hyphen (e.g. 078-my-feature-title).

Create and switch to the feature branch: git checkout -b <branch-name>.

Step 3: Plan the Implementation

Read the full issue body and any linked markdown file. Identify all discrete requirements.

Create a task list using TaskCreate for each requirement so progress can be tracked.

Before writing any code, present the implementation plan to the user and wait for confirmation.

Step 4: Implement

Use an agent team to parallelize independent work where possible:

  • Backend changes: Implement in backend/ following project conventions (Python, FastAPI, type hints, SQLAlchemy).
  • Frontend changes: Implement in frontend/ following project conventions (TypeScript, ESM, shadcn, Tailwind, Vite).
  • Infrastructure changes: Implement in iac/ following AWS SAM / CloudFormation conventions.
  • Agent changes: Implement in agents/ with isolated virtual environments.

Update TaskUpdate as each requirement is completed.

Step 5: Test

Run existing tests to check for regressions:

  • Backend: cd backend && make test (or the appropriate makefile target)
  • Frontend: cd frontend && npm test (if test scripts exist)
  • Agent tests: Run tests within each modified agent directory.

If the issue specifies new test cases, implement and run them.

All tests must pass before proceeding.

Step 6: Update Documentation

Update the following documentation files to reflect the new changes:

  • SPECIFICATIONS.md: Update any relevant specification files with the latest design decisions. Search for SPECIFICATIONS.md files in all subdirectories.
  • README.md: Update any relevant README files with the latest implementation details. Ensure no sensitive or account-specific information is included (no ARNs, account IDs, tokens, or endpoint URLs).

Step 7: Final Validation

Run the full test suite one more time to confirm nothing was broken during documentation updates.

Review all changes with git diff to verify correctness and ensure no secrets or credentials are included.

Step 8: Commit

Stage and commit all changes locally using semantic commit messages. Group related changes into logical commits:

  • feat: for new features
  • fix: for bug fixes
  • docs: for documentation updates
  • test: for test additions
  • refactor: for code restructuring
  • chore: for build/config changes

Do NOT push to remote. Only commit locally.

Append Co-Authored-By: Claude <noreply@anthropic.com> to each commit message.

Report a summary of all commits created.

Download now (ZIP)

  • Other versions42 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 42

    1. remotion-dev/remotion★ 67ksame name
    2. tldraw/tldraw★ 51ksame name
    3. tokio-rs/toasty★ 3.2ksame name
    4. dataplat/dbatools★ 2.8ksame name
    5. aws/graph-explorer★ 486same name
    6. egregore-labs/egregore★ 293same name
    7. finos/git-proxy★ 257same name
    8. alamenai/terrae★ 245same name
    9. dedalus-labs/wingman★ 181same name
    10. team-attention/hoyeon★ 173same name

    32 more not listed

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • Used alongsideProjects with it also use branch, backlog and 10 more.

    Other files people use alongside this one.

    Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
    • MindgamesSkill

      branch

      Use when a user asks to create a new local git branch and start issue work (for example, "create branch" or "start working on issue XYZ"). Use this for issue-based branch naming in the `type/scope-short-description` pattern and for always syncing local `main` from `origin/main` before creating the new branch, creating the local tracking `main` branch first when needed.

      Also in 3 projects that use this

    • vertz-devSkill

      backlog

      Manages deferred/blocked work items as GitHub Issues with labels and blocker tracking

      Also in 3 projects that use this

    • SentrySkill

      commit

      Create commit messages following Sentry conventions. Use when committing code changes, writing commit messages, or formatting git history. Follows conventional commits with Sentry-specific issue references.

      Also in 17 projects that use this

    • Microsoft AzureSkill

      lint

      Run all linting and spell checking for TypeScript and Rust code. Run this before committing to catch style issues, clippy warnings, and misspellings.

      Also in 4 projects that use this

    • Microsoft AzureSkill

      test

      Also in 6 projects that use this

    • AnthropicSkill

      debug

      Structured debugging session — reproduce, isolate, diagnose, and fix. Trigger with an error message or stack trace, "this works in staging but not prod", "something broke after the deploy", or when behavior diverges from expected and the cause isn't obvious.

      Also in 4 projects that use this

    • +1 more from Azure
  • In this repository3 other files it gives its agents.

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.