How this skill is triggered — by the user, by Claude, or both
Slash command
/meridian:commitThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
<HARD-GATE>
Clean commits. No surprises, no slop, no AI branding.
Run git status and git diff --staged. Understand what's about to be committed.
Check for files that shouldn't be committed:
.env, credentials, secrets, API keys.idea/, .vscode/, .DS_Store, Thumbs.db)If any staged files are ambiguous — could be intentional or accidental — ask:
"These are staged — should they be included?"
List the specific files. Don't assume.
If files appear to be local-only (personal config overrides, local dev scripts, iterative work):
git reset HEAD <file>git log --oneline -10 for the project's commit styleShow the user:
User approves, edits, or cancels.
Execute the commit with the approved message.
When subagents commit during execute, their prompts must include:
execute, debug, respond, or direct invocationnpx claudepluginhub kodingdev/meridian --plugin meridianStages intended git changes avoiding secrets and creates clear Conventional Commits like feat(scope): subject. Useful for clean, semantic commit history.
Stages files safely avoiding sensitive ones, infers conventional commit type from git diff, drafts message with scope, and executes after confirmation. Use anytime like post-planning or mid-TDD.
Creates semantic git commits with conventional commit format, stages changes, and pushes to remote. Handles pre-commit hooks and writes meaningful commit messages.