Verwendung
- Installationsbefehl kopieren und das Quellpaket vor der Installation in der eigenen Agentenumgebung prüfen.
- Benötigte Werkzeuge, Zugangsdaten und Hosts im Original prüfen.
- Eingabe und gewünschtes Ergebnis beschreiben und die Ausgabe mit den Quellen abgleichen.
npx skills add https://github.com/jimweller/clanker-skills --skill commitVor dem Start
- Die Installation umfasst weder Modellabo noch API-Kontingent oder Dateizugriffsrechte.
- Sterne und Installationen zeigen Aktivität, keine unabhängige Qualitäts- oder Sicherheitsprüfung.
Originales Skill-Dokument
Aus dem Quell-Repository gerendert; Überschriften, Beispiele, Code, Tabellen, Links und Bilder bleiben erhalten.
<!-- markdownlint-disable-file MD041 -->
STARTER_CHARACTER = 📌
Commit Changes
Process
1. Review Changes
bash
git status
git diff HEAD
git diff --stat HEADCheck for new untracked files:
bash
git ls-files --others --exclude-standard2. Stage Files
Add the untracked and changed files relevant to the current work.
Do NOT stage:
.envor credential files- Large binary files
- Files unrelated to the current task
3. Create Commit
Write an atomic commit message with a conventional commit tag:
feat:-- New capability or featurefix:-- Bug fixrefactor:-- Code restructure without behavior changedocs:-- Documentation onlytest:-- Test additions or fixeschore:-- Build, CI, tooling changesperf:-- Performance improvement
For monorepo changes spanning multiple packages, note the primary package in the scope:
text
feat(workflows): add DAG condition evaluator
fix(web): resolve SSE reconnection on navigation
refactor(isolation): simplify worktree resolution orderCommit message format:
text
tag(scope): concise description of what changed
[Optional body explaining WHY this change was made,
not just what changed. Include context changes that aren't
obvious from the diff.]
[Optional: Fixes #123, Closes #456]4. Capture AI Context Changes
If any AI context assets were modified in this commit, add a Context: section to the commit body:
text
feat(orchestrator): add retry logic for session recovery
Added exponential backoff when SDK subprocess crashes mid-session.
Previously a single crash would fail the entire workflow.
Context:
- Updated .claude/rules/orchestrator.md with retry conventions
- Added .claude/commands/debug-session.md for session state inspection
- Surfaced issue: mock.module() in retry tests needs isolated batch
Fixes #482What counts as AI context changes:
.claude/rules/-- on-demand conventions added, updated, or removed.claude/commands/-- slash commands created or modified.claude/skills/-- slash commands created or modified.llmdocs/-- reference docs added or updatedCLAUDE.md-- global rules changes**/CLAUDE.md-- folder local rules changes
Git log is long-term memory for future sessions.
