598a7c326a
Retrofits all 39 skills to ADR-0020's description/body context contract, then fixes what six rounds of independent review found in that retrofit — including four ways the hot gate itself failed open. Closes #99, #107, #108, #110, #111, #114, #115, #120. ## The retrofit (waves 1-5) | | Start | Now | |---|---|---| | Description FAILs (>400 chars) | 26 | **0** | | Body FAILs (>900 words, body-only) | 9 | **0** | | Dangling routing targets | 2 | **0** | | `Kyberforge.CompositionNote` | 10 | **0** | | Preload tax | 21,005 chars | **~10,500** | Under the 12,000-char success criterion. Per-wave detail is on #99. ## The review fixes **The gate failed open four ways, three of them found after the retrofit shipped.** An unrecognised follower token made a dangling target vanish. A skill directory with no `SKILL.md` resolved as a valid target, so a commit could be green locally and red in a fresh clone — three existing fixtures were relying on that, one of which made the install-leak A/B pass vacuously. Then the free-standing `/name` sweep turned out to be gated on the sentence carrying a boundary marker, so route notation in any other sentence was invisible — not an ERROR, not a SUGGESTION, not an INFO — which left the documented "`/name` always blocks" promise false from a second direction. All four fixed and pinned. **Two checks were silently not running.** `validate-provenance.sh` checks 7-8 were dead across nine skills. Waking them exposed a deeper problem: they assume `Research doc:` names a source index, but 30 of 121 entries point at topic content documents, so every new check-7 INFO was a false positive and check 8 was saved from a false-FAIL flood only by an *unannounced* skip. Checks 7/8 are now scoped to source indexes and every skip announces itself (#121). **The retrofit's own anti-goal, four times.** ADR-0020 warns that a blunt gate gets satisfied by deleting content rather than relocating it. `diagnose` and `skill-audit` relocated prose and then read it unconditionally; `prototype` and `vale-config` deleted rules outright that survived nowhere. All four addressed. ## Verification - `bash tests/run-tests.sh --strict` — 24 suites, 0 skipped, 0 failed - `bash tests/run-bats.sh` — 325 tests, 0 failures - `pre-commit run --all-files` — 17/17 - `pre-commit run --hook-stage pre-push --all-files` — 16/16, with `apm marketplace check` and `apm pack --check-clean` run against the remote, not skipped - `scripts/skill-size-check.sh` over all 39 skills — rc 0, 0 ERROR/FAIL, SUGGESTION-only - Preload tax measured at **10,498 chars**, max description 390 — both inside budget - Every new test proven non-vacuous by a deliberate mutation of the behaviour it covers **Per-commit sync, stated accurately:** the ten commits from the latest review round each pass `check-plugin-content-sync` in isolation, verified by checking each out in a detached worktree with a clean between. The earlier gitea window (`dfacf05..bedbd1d`, nine commits) does **not** — its mirror was regenerated in one batch at `bbc7300`. An earlier revision of this description claimed the property held for every commit; it does not, and a bisect through that window lands on a red commit. **Squash-merge** to collapse it, or accept that this range is not bisectable. ## Version bump Six plugins and the catalog take a **patch**, not a minor. The branch is **89 commits — 40 `fix` / 30 `refactor` / 12 `docs` / 5 `chore` / 2 `test` — zero `feat`, zero `!`, zero `BREAKING CHANGE`** — and adds no skill, agent, command or hook. (Two earlier revisions of this section cited a stale histogram, most recently 78 commits; the figures above are measured at HEAD.) Both rules this repo ships (`forge/references/version-bump.md`, landing in this PR, and `git-commits/references/conventional-commits-spec.md`) make that a patch, and the catalog set is unchanged at 7 entries. Not settled by that: four published files were removed from the installed tree, three moved, and `caveman` gained `disable-model-invocation`, retiring its old triggers. Under a strict reading those are major-class and currently ship under `refactor:` with no marker. Whether the deployed skill surface is a public contract is written down nowhere — worth deciding, but it outlives this PR. ## Deliberately not in scope #112 (cherry-pick ownership, now resolved in favour of `git-commits`), #113 (`rtk git` normalisation), #116 (research fan-out), #101 (audit-skill merge), #122 (non-spec skill-root files), #123 (no PRD producer) stay open. #117 is the one worth reading: the contract's remedy is to move prose into `references/`, which is exactly where neither the size gate nor Vale looks — and the blind spot is wider than #117 currently records, since there is no root `.vale.ini` at all, so every ADR, `CONTEXT.md` and `README.md` is unlinted too. That blind spot let this branch carry two `level: error` `Kyberforge.SentenceOpenerThereIs` violations into `references/` files it created — `provider-adapter-author/references/provider-matrix.md:31` and `agent-audit/references/finding-criteria.md:95`. Both are reworded in `afadaae`, confirmed by routing each file through the audit's own `vale-wrap.sh` (1 error each before, 0 after). Five further occurrences sit in `references/` files already on `main`; those are the pre-existing corpus and stay with #117, which is the real fix. Also unfixed and not this PR's: `apm install` appends a duplicate `SessionStart` entry to `.claude/settings.json`, so a fresh clone cannot get pre-push green without an edit AGENTS.md warns against. Reproduces identically on `main`. Co-authored-by: Defame1297 <gitea@rkdr.net> Reviewed-on: https://git.dev.rkdr.net/Defame1297/holocron/pulls/129 Co-authored-by: Claude Code AI - Gitea MCP <claude@noreply.git.dev.rkdr.net> Co-committed-by: Claude Code AI - Gitea MCP <claude@noreply.git.dev.rkdr.net>
3.9 KiB
3.9 KiB
name, description, compatibility, metadata, allowed-tools
| name | description | compatibility | metadata | allowed-tools | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| gitea-labels-milestones | Use when reading or writing Gitea labels or milestones — "create a label", "what labels does this repo have", "close the milestone" — or to resolve label names to IDs, or infer a Kind/Priority/Status label from context, even when the user does not say "Gitea". Not applying them to an issue -> `gitea-issues`. Not to a PR -> `gitea-prs`. | Requires Gitea MCP server configured with write:issue and write:repository token scopes. |
|
Bash mcp__gitea__label_read mcp__gitea__label_write mcp__gitea__milestone_read mcp__gitea__milestone_write |
Gotchas
- Applying a label takes a numeric ID, but issue/PR responses slim labels down to name strings. An issue's existing labels yield no IDs — resolve name → ID with
label_read. pull_request_readreturnsmilestoneas a bare title string whereissue_readreturns{id, title}— recover the milestone's ID by listing milestones and matching the title.- Never assume a
Kind/*/Priority/*/Status/*scope is exclusive — read each label's ownexclusivefield.list_repo_labelsreturns it on every repo label, so it is always readable per label;label_writedocuments it as "(org only)" because it is only settable through the org create methods. Where it istrueGitea enforces one-per-scope itself, and replacing rather than stacking on a label whoseexclusiveisfalsedestroys a valid label.
Step 1 — Resolve owner, repo and org
Before any tool call, extract owner and repo from the git remote (skip this if an orchestrating caller already passed them in):
git remote get-url origin
If origin is not set or the URL is not a Gitea URL, stop and report: "No Gitea remote found — set origin to your Gitea instance URL."
The *_org_label* methods take org, not owner/repo. Pass that same owner as org — it is the org name whenever the owner is an organisation, and the remote URL does not say whether it is one.
Read the failure text before interpreting it. list_org_labels needs the read:organization token scope, which this skill's declared scopes (write:issue, write:repository) do not carry, so it fails with token does not have at least one of required scope(s), required=[read:organization] before it ever determines org-vs-user. Report that: the org pool went unchecked, not empty. Only a not-found response is evidence the owner is a user account with no org pool.
Step 2 — Dispatch
| Task | Tool | method |
|---|---|---|
| Resolve a label name to its ID | label_read |
"list_repo_labels", then "list_org_labels" |
| List repo labels | label_read |
"list_repo_labels" |
| Get one repo label by ID | label_read |
"get_repo_label" |
| List org labels | label_read |
"list_org_labels" |
| Create a repo/org label | label_write |
"create_repo_label" / "create_org_label" |
| Edit a repo/org label | label_write |
"edit_repo_label" / "edit_org_label" |
| Delete a repo/org label | label_write |
"delete_repo_label" / "delete_org_label" |
| List milestones | milestone_read |
"list" |
| Get one milestone by ID | milestone_read |
"get" |
| Create a milestone | milestone_write |
"create" |
| Update / close a milestone | milestone_write |
"update" |
| Delete a milestone | milestone_write |
"delete" |
Every list method paginates manually — per_page defaults to 30, so iterate page: 1, 2, ... until a page returns fewer results than per_page. A truncated list silently breaks name → ID resolution.
If the task is a label operation, read references/labels.md; if a milestone operation, read references/milestones.md. If the label to apply has to be derived from conversation context rather than named, read references/label-inference.md.