Files

Claude Code AI - Gitea MCP 598a7c326a refactor(skills): retrofit the corpus to the ADR-0020 context contract (#129 )

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>

2026-09-01 13:47:46 +00:00

5.1 KiB

Raw Blame History

topic, source_keys

topic

source_keys

enrichments

gitea-mcp-repo

gitea-mcp-slim-go

context7-websites-gitea

Create-flow enrichments

Closes out the four enrichments deferred from issue #6 comment #848. Run in this order before the issue_write method: "create" call in SKILL.md's create dispatch: labels → milestone → assignee → dependency link. Each step is independent and skippable on its own — a missing milestone fit doesn't block label inference, and so on — but this is the order that lets later steps use context established earlier (e.g. the inferred Kind/* label can inform which milestone plausibly fits).

Cross-skill composition note: none of the steps below read gitea-labels-milestones's reference files directly by path. A plugin install copies each skill's directory into an isolated cache — any file path that leaves this skill's own directory breaks post-install. Instead, compose gitea-labels-milestones as a skill: describe the task to it (its own SKILL.md and description trigger it) and consume the resolved IDs it returns.

1. Label inference

Delegate the entire signal-to-label mapping to gitea-labels-milestones — this skill does not duplicate the Kind/*/Priority/*/Status/* taxonomy table.

Compose gitea-labels-milestones to resolve labels for the issue being created: give it the draft title/body and ask it to infer and resolve applicable labels (it calls label_read method: "list_repo_labels" internally and runs its own inference procedure).
Take back the resolved label IDs (and which scope groups, if any, need replacing — not relevant yet on a brand-new issue, since there's nothing to replace).
If gitea-labels-milestones reports low confidence and omits a Kind/* label, pass no Kind/* ID rather than guessing one yourself. Priority/Medium is the one label its own inference procedure defaults to when no urgency signal is present — that's expected, not a gap.
Pass the resulting label IDs to issue_write's labels parameter (omit the parameter entirely if the resolved list is empty).

2. Milestone assignment on create

Compose gitea-labels-milestones to list open milestones (it calls milestone_read method: "list" state: "open" internally).
Compare the issue's inferred scope (title, body, and any Kind/* label from step 1) against each open milestone's title/description. Assign a milestone only when the fit is clear — a milestone literally named for the feature area, or one whose description explicitly covers this kind of work. A milestone that's merely "the current one" without a clear scope match is not a confident fit.
If a milestone clearly fits, pass its numeric ID (never the title) as issue_write's milestone parameter. issue_write's milestone field only accepts the ID — see references/issues.md.
If no milestone clearly fits, omit milestone entirely. Guessing a milestone assignment is worse than leaving it unset — an issue can always be milestoned later, but a wrong milestone assignment pollutes that milestone's issue count and scope.

3. Assignee on create — the `get_me` workaround

issue_write accepts assignees: [<login>], but there is no way to discover the current user's own login to self-assign: get_me requires the read:user scope, and this repo's Gitea MCP token is scoped to write:issue + write:repository only, with no read:user grant. This is a hard capability gap, not something to work around with a guess.

Workaround: support an optional user-configured default assignee login, supplied one of two ways:

A config value the caller or orchestrator (e.g. gitea-workflow) already resolved and passes in when invoking this skill.
A login explicitly stated in the conversation ("assign this to alice") — use that login directly, no lookup needed, since Gitea accepts a login string without requiring you to resolve an ID first.

If neither is available, omit assignees entirely. Do not guess a login, do not fail the create over a missing assignee, and do not attempt get_me/search_users as a fallback — both are blocked by the same scope gap and will only produce a confusing secondary error.

4. Dependency-linking convention

gitea-mcp has no native issue-dependency field (no "blocks"/"blocked by" relationship in the API surface this skill has access to). The convention is to write "Depends on #N" as a line in the issue body.

This is not just a text convention with no effect — Gitea auto-renders #N (and !N for PRs) as a real clickable cross-reference with no separate API call, a documented platform behavior (see references/sources.md for the backing research). This works because issues and PRs share one repo-scoped number space. Use the bare #N form for same-repo dependencies; use owner/repo#N for a dependency in a different repo.

When creating an issue that depends on another, append a line like:

Depends on #42

to the body before calling issue_write method: "create". No separate field or follow-up call is involved — the rendering happens automatically once the body is saved.

5.1 KiB Raw Blame History