assay-end-fast
Skill0 starsChanged 3 days agoApache-2.0View on GitHub
Use when finishing local work on an Assay unit of work after the PR is merged and you want to clean up without generating a completion report. Triggers on "assay-end-fast", "aef", "aef bug 12", "aef feat skill-ingest", "end fast".
In this repository10 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- assay-begin-fastSkill
- assay-beginSkill
- assay-endSkill
- assay-nextSkill
- assay-reportSkill
- assay-worktreesSkill
- prd-generatorSkill
- prd-interviewSkill
- tech-planSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
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
- Very specific: line 62
When release machinery lands (its own unit of work), this phase becomes ALWAYS-run: feat/feature → minor, bug/chore/task → patch.
- Very specific: line 63
ALWAYS-run: feat/feature → minor, bug/chore/task → patch.
- Very specific: line 71
Ask first. Draft 2-4 sentences, no em dashes, no jargon.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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.
Files
Assay End (Fast Track)
Overview
Closes out a unit of work's local state after the PR has merged: master → pull →
remove worktree → delete branch, with a release phase that is deferred until
Assay has release machinery. No report (use assay-end / ae for that).
Invocation: aef <type> <id> — e.g. aef bug 12, aef feat skill-ingest.
type∈bug | feat | feature | task | chore(normalizefeature→feat)id= the GitHub issue number, or the slug used at begin time- Owner is
aliz - Branch:
<type>/<id>/aliz; worktree dir:.claude/worktrees/<type>-<id>
Assay's base branch is master.
Pipeline
Phase 0 — Safety check
- Worktree clean?
git -C <worktree> status --porcelainmust be empty. - Branch merged? Confirm the PR is merged if reachable.
git branch -drefuses an unmerged branch; don't bypass with-Dwithout explicit user OK.
Phase 1 — Main, pulled
PRIMARY=$(git worktree list | head -1 | awk '{print $1}')
git -C "$PRIMARY" checkout master
git -C "$PRIMARY" pull --ff-only origin masterPhase 2 — Remove worktree, delete branch
WORKTREE_NAME="<type>-<id>"
BRANCH="<type>/<id>/aliz"
git -C "$PRIMARY" worktree remove ".claude/worktrees/$WORKTREE_NAME"
git -C "$PRIMARY" branch -d "$BRANCH"Verify:
git -C "$PRIMARY" worktree list
git -C "$PRIMARY" branch --list "$BRANCH"Phase 3 — Release a new version (DEFERRED — no machinery yet)
Assay has no release machinery today. Cleanup ends at Phase 2. Do not hand-craft a release, tag, or publish anything.
When release machinery lands (its own unit of work), this phase becomes
ALWAYS-run: feat/feature → minor, bug/chore/task → patch; bump +
changelog on master; CI green before tagging; tag and push to trigger the
workflow; verify each channel is live before calling it done. Release identity:
the haqaliz account. PyPI distribution name: assay is taken; assayhq was
free when checked — settle it in the release-machinery unit.
Phase 4 — Comment on the issue (optional)
Ask first. Draft 2-4 sentences, no em dashes, no jargon. Confirm with the user,
then gh issue comment "$ID" --body "<confirmed text>".
Common mistakes
| Mistake | Fix |
| Running from inside the worktree being removed | Resolve PRIMARY first |
Checking out / pulling master | Assay's base branch is master |
Using git pull (allowing merge) | Use --ff-only |
Forcing branch delete with -D | Only after explicit user OK |
| Cutting a release | Deferred — no machinery yet |
| Posting the issue comment without confirmation | Draft first, confirm, then post |
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
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.

