Files
holocron/plugins/git/skills/git-commits/SKILL.md
Defame1297 38f1ba4e03 fix(kyberforge): bridge apm content to Claude Code's flat plugin discovery
Claude Code's (and Copilot's) native plugin installer has zero awareness of
.apm/ nesting -- it convention-scans only flat skills/, agents/, commands/,
hooks.json at each plugin's root. Confirmed via strings on the installed
claude binary and live installs of git@holocron/gitea@holocron/kyberforge@
holocron, all reporting Skills(0) Agents(0) Hooks(0) post ADR-0015's apm
conversion. Root cause (apm_cli/core/plugin_manifest.py): apm's plugin.json
compiler deliberately strips skills/agents/commands keys, assuming the host
already auto-discovers those convention directories -- it has no model of
.apm/ being host-visible at all. Separately, apm's own bundle exporter
(apm_cli/bundle/plugin_exporter.py, behind `apm pack --format plugin`)
implements the correct .apm/ -> flat mapping, but only ever targeted
build/<name>-<version>/, a path nothing in marketplace.json's source: points
at.

scripts/sync-plugin-content.sh wraps that bundle exporter and copies its
agents/, skills/, commands/, instructions/, extensions/, and merged
hooks.json back into each plugin's own root as a second tracked
compiled-output category -- same governance status as
.claude-plugin/plugin.json: generated from .apm/, never hand-edited. tests/
subdirectories are excluded from the mirror (dev fixtures, not host-visible
runtime content; several hardcode a relative repo-root walk-up sized for the
.apm/-nested depth, which breaks when duplicated one level shallower).
Applied for real across all 6 plugins and verified two ways: `claude plugin
validate --strict` passes on every real plugin directory, and a live
`claude --plugin-dir <path> -p "list skills/agents"` behavioral test
confirms content is now actually discovered.

Also, from the same issue #90 review round:
- scripts/check-manifests.sh pointed at each plugin's root-level plugin.json
  (checking skills/hooks/mcpServers/agents pointer fields) -- that file was a
  stale near-duplicate of .claude-plugin/plugin.json nothing else read or
  wrote, now deleted across all 6 plugins. check-manifests.sh is rewritten to
  validate .claude-plugin/plugin.json instead, and drops the pointer-field
  checks entirely (nothing to check -- those fields are correctly absent by
  design). Content-presence drift is now check-plugin-content-sync's job, a
  new pre-push hook wired in .pre-commit-config.yaml.

docs/adr/0017 records the root cause and decision in full, including two
rejected alternatives (patching plugin.json's path fields directly -- apm's
compiler strips them on every run; pointing marketplace.json at apm pack's
build/ output -- a version-suffixed non-source directory nothing can install
from without an extra build step). ADR-0015 and CONTEXT.md are updated to
point at it.

Refs: #90
2026-08-13 16:59:03 +00:00

116 lines
8.5 KiB
Markdown

---
name: git-commits
description: >
Use when creating, amending, squashing, or cherry-picking commits.
Generates well-formatted commit messages following Conventional Commits spec (type, scope, description, body, footers).
Validates against commitlint config-conventional constraints (header max 100 chars, lowercase subject, no trailing periods, type must be one of 11 standard types).
Communicates SemVer impact (MAJOR for breaking changes, MINOR for features, PATCH for fixes).
Handles confirmation gates for history-altering operations (amend, rebase, squash).
Provides interactive guidance for humans, structured JSON output for agents.
Do not use for: inspecting git history, branch management, or repository state inspection — those are separate skills.
metadata:
version: "0.1.2"
category: git
source_keys:
- conventional-commits-spec
- commitlint-config-conventional
- org-commit-conventions
- context7-git-htmldocs
allowed-tools: Bash
---
## Gotchas
- **Type must be one of 11 standard types** — `feat`, `fix`, `perf`, `revert`, `docs`, `style`, `refactor`, `test`, `build`, `ci`, `chore`. Non-standard types will fail commitlint validation. Note: the Conventional Commits spec itself only mandates `feat`/`fix` — the 11-type set is a commitlint/Angular convention this skill validates against, not a spec requirement.
- **Scope is optional but should be used** — helps identify which part of the system changed. Examples: `api`, `db`, `cli`, `config`.
- **Header max 100 characters** — type + scope + colon + description must fit. If longer, move detail to body.
- **BREAKING CHANGE notation** — use `!` before the colon (`feat!: drop Node 6`) for visibility in `git log --oneline`. Footer notation (`BREAKING CHANGE: ...`) is machine-readable but hidden in log.
- **SemVer mapping is not optional** — agents must communicate: `feat` → MINOR bump, `fix`/`perf`/`revert` → PATCH, any with breaking change → MAJOR.
- **Confirmation gates are mandatory for destructive operations** — amend, rebase, squash require explicit user/agent approval before execution.
- **Never skip hooks with `--no-verify`** — hooks are the automated QA gate; bypassing them breaks the pipeline. Do not add this flag to any commit command unless the user explicitly demands it, and warn them if they do.
- **Never force-push `main`/`master`** — even after an amend or interactive rebase, refuse to force-push a protected branch (`main`, `master`) and explain why; force-push is only safe on branches no one else has based work on.
- **Command examples use the `rtk git` wrapper** — this org's convention routes all git invocations through `rtk git <subcommand>` instead of bare `git <subcommand>`. Follow this prefix in any command you actually run.
- **Never commit secrets, credentials, or environment-specific config** — if staged changes contain what looks like an API key, token, password, or connection string, stop and flag it before committing rather than committing it.
- **Commits must be atomic and leave the repo working** — each commit should be one logical, independently reviewable and reversible change, and should leave the repository in a buildable/testable state. If staged changes bundle unrelated work, suggest splitting before committing.
- **Commit messages explain why, not what** — the diff already shows what changed; the message's job is to capture context the diff can't (motivation, root cause, tradeoffs). See `references/commit-template.md` for the structure this maps to.
## Workflow
### For creating a new commit:
1. **Gather context** — what changed and why? (from staged changes, PR description, issue context). Verify the staged diff is one logical, atomic change and that the repo would still build/test at this commit — if not, suggest splitting before proceeding.
2. **Check for secrets** — scan the staged diff for anything that looks like a credential, API key, token, or environment-specific config. Stop and flag it rather than committing.
3. **Determine type** — is this a feature (`feat`), bug fix (`fix`), or other? Default: check the change itself.
4. **Determine scope** — which system/module? Use scope from plugin config if set, otherwise infer from files changed.
5. **Write description** — imperative mood, no period. Neither source spec sets a length target below the 100-char header max, but convention favors keeping it to ~50 characters where possible for `git log --oneline` readability. Examples: "add user authentication", "fix race condition in cache".
6. **Add body if needed** — explain why (not what). Blank line before body, wrap at 100 chars. For non-trivial changes, follow the Why / Implementation Notes / Impact structure in `references/commit-template.md`.
7. **Add footers if needed** — `Fixes: #123`, `Refs: #123`, `ADR: 0012`, `RFC: 0003`, `Design: <link>`, `Reviewed-by: Name`, `Co-authored-by: Name <email>`, `Signed-off-by: Name <email>`, `BREAKING CHANGE: description`. See `references/commit-template.md` for the full trailer list.
8. **Validate** — check header length, type correctness, no trailing periods, lowercase.
9. **Confirm and execute** — for agents, require explicit approval; for humans, show preview and ask. Never add `--no-verify` to skip hooks.
### For amending a commit:
1. **Stage new changes** (or changes to undo)
2. **Run amend operation** — executes `rtk git commit --amend [--no-edit]` based on user intent
3. **Offer message edit** — if user wants to change commit message, show current message and prompt for new one
4. **Confirm before force-push** — amending is only safe on non-shared branches; if the current branch is `main`/`master`, refuse to force-push and explain why rather than warning and proceeding
### For squashing commits (interactive rebase):
1. **Identify commits to squash** — typically the last N commits on current branch
2. **Confirm operation** — squashing rewrites history; get explicit approval
3. **Execute rebase** — `rtk git rebase -i HEAD~N`, mark older commits as `squash` or `fixup`
4. **Handle merge conflicts** — if rebase halts, offer conflict resolution options or abort; do not resolve automatically without confirmation
5. **Offer message composition** — if squashing interactive, allow message editing
### For squashing commits (autosquash — preferred when tagging at commit time):
Prefer this over manual interactive rebase when a commit is written to be folded into an earlier one, since it removes the manual "mark as squash/fixup" step and the risk of reordering the wrong line:
1. **Create the fixup/squash commit** — `rtk git commit --fixup=<commit>` (keeps target's message) or `rtk git commit --squash=<commit>` (lets you edit the combined message later). Both prefix the message with `fixup!`/`squash!` and target `<commit>`.
2. **Confirm operation** — rewriting history still requires explicit approval before the rebase runs.
3. **Execute** — `rtk git rebase --autosquash HEAD~N` (or `-i --autosquash` to review the plan first); git reorders and marks the `fixup!`/`squash!` commits against their targets automatically.
4. **Handle merge conflicts** — same as manual rebase: offer resolution or abort, never resolve automatically without confirmation.
### For cherry-picking:
1. **Identify source commit(s)** — hash or branch reference
2. **Confirm destination branch** — cherry-pick will replay commits on current branch
3. **Execute cherry-pick** — `rtk git cherry-pick <commit-hash>`
4. **Handle conflicts** — offer conflict resolution or abort
5. **Report outcome** — successful replays, conflicts, or rejected commits
## Output format (for agent consumption)
Return structured JSON:
```json
{
"operation": "create|amend|squash|cherry-pick",
"status": "success|conflict|rejected",
"message": "Commit message or error description",
"commit_hash": "abc1234",
"semver_impact": "MAJOR|MINOR|PATCH|none",
"breaking_change": true|false,
"confirmation_required": true|false,
"details": {
"type": "feat",
"scope": "api",
"description": "add user authentication",
"body": "optional body text",
"footers": ["Fixes: #123", "Refs: #456", "ADR: 0012", "Reviewed-by: Alice", "Co-authored-by: Bob <bob@example.com>", "Signed-off-by: Alice <alice@example.com>"]
}
}
```
For interactive human use, format as readable prose with clear prompts and previews.
## Reference
If a footer or type/scope edge case isn't covered above, read `references/conventional-commits-spec.md` for the full specification.
For the Why / Implementation Notes / Impact body structure and the full trailer list, read `references/commit-template.md`.