agentleFS
kyto64kyto64/aidd-template-scale/.agents/skills/start-ticket/SKILL.md

start-ticket

Skill0 starsChanged 2 months agoMITView on GitHub

Start a GitHub Issue: fetch details, label in-progress, create worktree from origin/main,

  • Commits and pushes

8 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

9 rules. 0 are common, 6 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 6

    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
  • could be automatic: a setting could enforce it
  1. Very specific:

    Ensure label in-progress exists.

    line 19
  2. Distinctive:

    Create or reuse worktree:

    line 29
  3. Distinctive:

    All further edits run in this worktree.

    line 37
  4. Very specific:

    Read relevant docs/ (docs/_inventory.md → area index → detail files).

    line 43
  5. Distinctive:

    Update docs in the same PR when behavior or SSOT changes.

    line 50
  6. Distinctive:

    Run only what exists in the repo:

    line 54
  7. Very specific:

    If lint/test scripts exist (package.json, Makefile, etc.), run them and report results.

    line 56
  8. Distinctive:

    If none exist, skip and state "no lint/test toolchain configured" in the PR.

    line 57
  9. Distinctive:

    Commit with explicit git add (no git add -A).

    line 61

“Common” is measured: kept by at least 6 in 10 of the 7 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

Start ticket workflow

Issue number: $ARGUMENTS

Execute phases in order. Report completion after each phase.

Phase 1: Issue and worktree

  1. gh issue view $ARGUMENTS — read title, body, labels, acceptance criteria
  2. Ensure label in-progress exists; create if missing (gh label create in-progress ...). On permission error, stop.
  3. gh issue edit $ARGUMENTS --add-label in-progress
  4. Resolve main repo root (see git-worktree.md):
    COMMON=$(git rev-parse --git-common-dir)
    MAIN_ROOT=$(cd "$COMMON/.." && pwd)
    REPO=$(basename "$MAIN_ROOT")
    WORKTREES_ROOT="$(dirname "$MAIN_ROOT")/${REPO}-worktrees"
  5. git fetch origin
  6. Create or reuse worktree:
    BRANCH="feature/$ARGUMENTS"
    DIR=$(echo "$BRANCH" | tr '/' '-')
    mkdir -p "$WORKTREES_ROOT"
    git worktree add -b "$BRANCH" "${WORKTREES_ROOT}/${DIR}" origin/main 2>/dev/null || cd "${WORKTREES_ROOT}/${DIR}"
    cd "${WORKTREES_ROOT}/${DIR}"
  7. All further edits run in this worktree.

Report: issue summary to the user.

Phase 2: Plan

  1. Read relevant docs/ (docs/_inventory.md → area index → detail files). Use /spec-lookup for quick lookups.
  2. Grep/Glob for affected code paths.
  3. Present implementation plan; wait for user approval if scope is unclear.

Phase 3: Implement

  1. Implement per plan and acceptance criteria.
  2. Update docs in the same PR when behavior or SSOT changes.

Phase 4: Quality gates

Run only what exists in the repo:

  • If lint/test scripts exist (package.json, Makefile, etc.), run them and report results.
  • If none exist, skip and state "no lint/test toolchain configured" in the PR.

Phase 5: PR

  1. Commit with explicit git add (no git add -A).
  2. Push branch.
  3. Open PR to main with body containing Fixes #$ARGUMENTS and template sections filled in.
  4. gh pr create --base main ...

Report: PR URL.

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.