agentleFS
jamie8johnsonjamie8johnson/cqs/.claude/skills/land/SKILL.md

land

Skill18 starsChanged 5 months agoMITView on GitHub

Land a ready branch - push, PR, pinned CI watch, squash-merge, issue verification, cleanup. Use for every PR landing; encodes the run-ID pinning and cleanup discipline.

  • Commits and pushes

27 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use drift-audit, ship and 4 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.
  • mr-fumanchuSkill

    drift-audit

    Audit a project's CLAUDE.md against its memory files to find duplicated or drifting rules, then consolidate them into a single source of truth. Use when Tony says "drift audit", "check for drift", "audit memory vs CLAUDE.md", "find duplicated rules", "clean up memory duplication", or wants to reconcile CLAUDE.md and memory so a rule never lives in two places. Read-only by default; never edits or deletes anything without explicit approval.

    Also in 3 projects that use this

  • AWSSkill

    ship

    Finalize dev work on an issue branch — update docs, push, and open a PR.

    Also in 5 projects that use this

  • Google CloudSkill

    triage

    Gather context on a change or bug and plan the implementation.

    Also in 3 projects that use this

  • SentrySkill

    review

    Fixture review skill.

    Also in 3 projects that use this

  • GoogleSkill

    tdd

    Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

    Also in 3 projects that use this

  • GoogleSkill

    code-review

    Adversarial systems, concurrency, memory-model, and architecture code review protocol. Use this skill whenever asked to review code, PRs, diffs, or branches in Filament.

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 26 edited versions we read keep these.

  • 0

    Distinctive

    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. Very specific:

    Read the failing job log before touching anything (gh run view <id> --log-failed).

    line 51

“Common” is measured: kept by at least 6 in 10 of the 26 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

Land a Branch

Take a committed branch through push → PR → CI → merge → cleanup. One invocation per branch; serialize when branches share files.

Arguments

  • $ARGUMENTS — branch name; optionally the worktree path holding it (default: search git worktree list).

Pre-flight

  1. pwd + git branch --show-current in the branch's checkout — CWD drift is real: finished background agents move the orchestrator's shell CWD. Anchor every command with explicit cd.
  2. Branch is committed and clean (git status --short empty).
  3. Merge current main in: git fetch origin main && git merge origin/main. On conflict in triage tables → union-of-flips; in tests → usually keep both.
  4. Re-gate after the merge: targeted tests for touched modules (cargo test --features cuda-index --lib <filter> with a private CARGO_TARGET_DIR), and the provenance lint:
    git diff origin/main...HEAD -- '*.rs' | python3 scripts/check_comment_provenance.py
    CI diffs the merge ref, so MOVED comment lines count as added — a local pass on the pre-merge diff can be a false negative.

Push and PR

  1. Push: git push origin <branch> (direct WSL usually works; on "could not read Username" fall back to powershell.exe -Command "cd C:\Projects\cqs; git push origin <branch>").
  2. Body to /mnt/c/Projects/cqs/pr_body.md (NEVER inline; must live on C: for Windows gh). Include closes #N for every issue the branch resolves. Delete the file after.
  3. powershell.exe -Command 'cd C:\Projects\cqs; gh pr create --head <branch> --title "..." --body-file pr_body.md'

CI — pin the run ID

gh pr checks --watch latches onto the PREVIOUS commit's completed run. Always:

sleep 50   # new run needs ~45s to register
powershell.exe -Command 'gh run watch $(gh run list -R jamie8johnson/cqs --branch <branch> --workflow CI --limit 1 --json databaseId --jq ".[0].databaseId") -R jamie8johnson/cqs --exit-status'

Background this (run_in_background) and do other work; the notification carries the exit code.

Merge and verify

  1. On green: powershell.exe -Command 'gh pr merge <N> -R jamie8johnson/cqs --squash --delete-branch', then confirm gh pr view <N> --json state == MERGED.
  2. Verify every linked issue actually closed (gh issue view <N> --json state); close manually with a PR pointer if GitHub missed it. "Partially addresses" PRs: comment the remaining scope on the issue instead.
  3. Cleanup: cd /mnt/c/Projects/cqs && git pull origin main --ff-only, git worktree remove <path> --force, git branch -D <branch>, cqs index (inotify misses bulk git ops on /mnt/c).

On CI failure

Read the failing job log before touching anything (gh run view <id> --log-failed). Provenance-lint failures → scrub audit IDs from comments (state the invariant instead). Don't retry CI blind.

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.