agentleFS
maksutovicmaksutovic/joycraft/.agents/skills/joycraft-spec-done/SKILL.md

joycraft-spec-done

Skill15 starsChanged 54 days agoMITView on GitHub

Lightweight per-spec wrap-up — bump status to in-review, terse discovery if surprised, commit. Run after each spec in checkpoint/isolated mode; no validation, no push, no PR.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    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:

    Do not graduate to done. The agent never self-certifies — done is reached only by joycraft-session-end (or, later, an independent verify).

    line 27
  2. Distinctive:

    Commit the spec's implementation changes plus the status edits (and the stub, if any) with the convention:

    line 38
  3. Distinctive:

    Keep scope disciplined — commit the spec's changes and its status edits, not unrelated working-tree noise.

    line 44
  4. Distinctive:

    If more specs remain in this feature (checkpoint/isolated mode), continue to the next one:

    line 52
  5. Distinctive:

    When the feature's last spec is done, run the feature finisher once:

    line 58

≈ “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

At skill entry, run node docs/.joycraft/check.mjs check --json --session <session-id> once, reusing JOYCRAFT_SESSION_ID if supplied or one ID chosen for this conversation. If the checker is missing or fails, continue the requested skill quietly without retrying setup. Offer updates only for display: true; current, postponed, off, and unknown stay quiet. If automaticUpdate is present, finish this skill, then run its exact command once from the project root: the candidate must verify every safety gate before applying. Other updates require approval. After an offer or automatic attempt, record it with node docs/.joycraft/check.mjs acknowledge <available-version> --session <session-id>. Apply updates only at this workflow boundary; after success, reinvoke the skill or restart the session to load changed instructions.

Spec Done (Lightweight Per-Spec Wrap-Up)

You just finished implementing one atomic spec. This is the fast handshake that runs once per spec, before context clears — the todo → in-review transition in the lifecycle (docs/reference/spec-status-lifecycle.md). It is deliberately tiny: it does exactly four things and nothing more.

This is NOT session-end. It does not run validation, push, or open a PR. It trusts the TDD you just did in joycraft-implement. The heavy once-per-feature wrap-up (full validation + consolidate discoveries + push + PR) is joycraft-session-end, which runs once at the end of the feature.

Usually you don't run this by hand: joycraft-implement performs these four steps itself at the end of every checkpoint/isolated spec (and joycraft-implement-feature drives whole queues). This skill remains the canonical definition of the wrap-up — run it manually after ad-hoc work done outside the implement skill, or when an implement run was interrupted before wrapping up.

Step 1: Bump status to in-review — in BOTH systems

A spec's status lives in two places that must never disagree (the desync this feature exists to kill): the queue JSON and the spec's frontmatter. Update both to in-review.

  1. Queue JSON — use the script, not a bespoke sed:
    joycraft-mark-done <spec-id> --to in-review <specs-dir>
    Find <spec-id> by reading <specs-dir>/.joycraft-spec-queue.json and matching the entry whose file is the spec you just implemented. <specs-dir> is the folder containing the spec (e.g. docs/features/<slug>/specs). If the spec isn't in the manifest, joycraft-mark-done exits non-zero with a clear error — surface that error, don't silently skip the bump.
  2. Frontmatter — edit the spec file's YAML status: field to in-review.

Do not graduate to done. The agent never self-certifies — done is reached only by joycraft-session-end (or, later, an independent verify). spec-done only ever reaches in-review.

Step 2: Terse discovery stub — ONLY if something surprised you

Did anything during implementation contradict the spec or surprise you (an assumption that was wrong, an external API that behaved differently, an edge case the spec missed)?

  • No → skip this step entirely. A spec that went as written needs no discovery. This is the common case.
  • Yes → write a 2-line stub (not a full discovery doc) at docs/discoveries/YYYY-MM-DD-topic.md: one line on what contradicted the spec, one line pointing at the spec/file. joycraft-session-end's consolidation pass later expands these stubs into proper discovery docs — keep it terse here.

Step 3: Commit

Commit the spec's implementation changes plus the status edits (and the stub, if any) with the convention:

spec: <spec-name>

Keep scope disciplined — commit the spec's changes and its status edits, not unrelated working-tree noise.

Step 4: Stop

That's it. No validation re-run, no push, no PR — those belong to joycraft-session-end at feature end. Hand off and keep the loop moving.

Recommended Next Steps

If more specs remain in this feature (checkpoint/isolated mode), continue to the next one:

$joycraft-implement docs/features/<slug>/specs/<next-spec>.md

When the feature's last spec is done, run the feature finisher once:

$joycraft-session-end

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.