Best for
- ALWAYS use this skill when the user asks to commit, save changes, or create a commit.
NintendaDev/unikit-ai/skills/unikit-commit/SKILL.md
Create conventional commit messages for {{engine_name}} projects by analyzing staged changes. Handles engine-specific concerns like companion file pairing, binary assets, and plan task references. ALWAYS use this skill when the user asks to commit, save changes, or create a commit. Trigger phrases include "commit", "create commit", "commit this", "save changes", "save my work". Even if the user simply says "commit" or asks you to commit after finishing a task — invoke this skill, do NOT commit m
Decision brief
Generate commit messages following the Conventional Commits specification, with {{enginename}}-specific safety checks.
Compatibility matrix
| Platform | Status | Evidence | What to check |
|---|---|---|---|
| Codex | Not declared | No explicit evidence | Portability before use |
| Claude Code | Not declared | No explicit evidence | Portability before use |
| Cursor | Not declared | No explicit evidence | Portability before use |
| Gemini CLI | Not declared | No explicit evidence | Portability before use |
Installation
The source command is displayed only when detected. A safe inspection prompt is always available so your agent can explain every action before execution.
npx skills add https://github.com/NintendaDev/unikit-ai --skill "skills/unikit-commit"Inspect the Agent Skill "unikit-commit" from https://github.com/NintendaDev/unikit-ai/blob/b6fd42c24aaadd46e91c6c94da9cc0078b5ecb8c/skills/unikit-commit/SKILL.md at commit b6fd42c24aaadd46e91c6c94da9cc0078b5ecb8c. List every install step, command, network request, credential, file read/write, external action, and rollback step. Explain whether it fits my task. Do not install or execute anything until I approve.
Workflow
1. Analyze Changes - Run git status to see staged files - Run git diff --cached to see staged changes - If nothing staged, show warning and suggest staging
BEFORE producing ANY output, silently read .unikit/system/LANGUAGERULES.md and apply its rules to ALL subsequent output. If the file is missing or unreadable, fall back to English. Do not produce any user-facing output until language rules are loaded. Do not announce, confirm, o…
Review the “Format” section in the pinned source before continuing.
Refactor with plan reference:
1. Check for staged changes 2. Run {{enginename}} safety checks (meta pairing, ignored dirs, binary assets, secrets) 3. Run lightweight context checks against .unikit/ docs 4. If errors found — list them and ask user whether to proceed or fix first 5. Propose a commit message 6.…
Permission review
The documentation asks the agent to run terminal commands or scripts.
**Push now** → execute push command based on upstream status:Evidence record
| Signal | Value | Evidence type | Meaning |
|---|---|---|---|
| Quality score | 92/100 | Computed | Documentation, specificity, maintenance, and trust rules |
| Repository stars | 16 | Source | Repository attention, not individual Skill quality |
| Compatibility | 0 platforms | Source | Declared in the catalog source record |
| Usage guide | automated source guide | Editorial | Generated or reviewed according to the visible evidence level |
Pinned source
Generate commit messages following the Conventional Commits specification, with {{engine_name}}-specific safety checks.
BEFORE producing ANY output, silently read .unikit/system/LANGUAGE_RULES.md
and apply its rules to ALL subsequent output.
If the file is missing or unreadable, fall back to English.
Do not produce any user-facing output until language rules are loaded.
Do not announce, confirm, or mention the language setting.
Analyze Changes
git status to see staged filesgit diff --cached to see staged changes{{engine_name}} Safety Checks
Run these checks before generating the commit message. Report findings as WARN or ERROR.
a) Engine companion files
Some engines require companion/metadata files for every asset.
Read .unikit/DESCRIPTION.md to determine if the current engine has such a mechanism. If yes:
ERROR, suggest staging the missing counterpart or removing the orphanERROR, suggest staging it
If the engine has no companion file mechanism — skip this check.b) Engine-ignored directories
If any staged file matches a path that should be ignored by the engine (check the project's .gitignore) → ERROR. These are engine-generated directories that should never be committed. Suggest unstaging them.
c) Binary asset awareness
Run git diff --cached --numstat — files shown as - - <path> are binary.
If staged changes include binary files, warn the user about binary content in the commit. These files don't diff well — just note their presence so the user is aware.
d) Secrets check
Never commit files that likely contain secrets (.env, credentials.json, API keys in config files). If detected → ERROR.
Context Check (Read-Only)
.unikit/ARCHITECTURE.md (if present) to verify staged changes don't violate module boundaries or dependency rules defined there.unikit/ROADMAP.md (if present) to check milestone alignment — for feat/fix/perf commits, check if changes relate to an unchecked milestone and suggest mentioning it in the commit body.unikit/skill-context/unikit-commit/SKILL.md (if present) — project-specific rules accumulated by /unikit-evolve. Treat as overrides: skill-context wins over general rules on conflictROADMAP.md) are WARN, not blockersWARN, don't block the commitPlan Task Linkage
.unikit/code/plans/ contains an active plan (look for TASKS.md)Determine Commit Type
feat: New featurefix: Bug fixdocs: Documentation onlystyle: Code style (formatting, semicolons)refactor: Code change that neither fixes a bug nor adds a featureperf: Performance improvementtest: Adding or modifying testsbuild: Build system or dependenciesci: CI configurationchore: Maintenance tasksIdentify Scope
.unikit/ARCHITECTURE.md):
Wallets/ → wallets, MiniGames/ → mini-games)Gameplay/ → gameplay, Application/ → app)Generate Message
type(scope):) is always in English — only the description text after the colon uses the configured language<type>(<scope>): <subject>
<body>
<footer>
Simple feature:
feat(wallets): add currency conversion system
Bug fix with body:
fix(mini-games): handle null item reference in slider game
The slider mini-game could crash when item config was missing
the difficulty curve. Added null check with fallback to default.
Fixes #42
Refactor with plan reference:
refactor(characters): extract customer behavior into state machine
Migrated customer logic from monolithic Update to NodeCanvas FSM.
Phase 3, tasks 3.1-3.4
Breaking change:
feat(inventory)!: migrate to Opsive UIS item categories
BREAKING CHANGE: item definitions now use CategoryID instead of TypeEnum
When invoked:
Check for staged changes
Run {{engine_name}} safety checks (meta pairing, ignored dirs, binary assets, secrets)
Run lightweight context checks against .unikit/ docs
If errors found — list them and ask user whether to proceed or fix first
Propose a commit message
Confirm with the user before committing:
AskUserQuestion: 💾 Proposed commit message:
<type>(<scope>): <subject>
Options:
1. Commit as is
2. Edit message
3. Cancel
Based on choice:
AskUserQuestion, then return to step 6 with the new messageExecute git commit with the confirmed message
Post-commit push handling:
If git.skip_push_after_commit = true in .unikit/config.yaml:
Otherwise (default behavior), offer to push:
git status -sbgit push -u origin <branch>git pushAskUserQuestion: Push to remote?
Options:
1. 🔄 Push now
2. Skip push
git push -u origin <branch>git pushIf argument provided (e.g., /unikit-commit wallets):
If staged changes contain unrelated work (e.g., a feature + a bugfix, or changes to independent modules), suggest splitting into separate commits:
Show which files/hunks belong to which commit
Confirm split plan with the user:
AskUserQuestion: Split into separate commits?
Options:
1. ✅ Yes, split as suggested
2. No, commit everything together
3. Let me adjust the grouping
Based on choice:
AskUserQuestion, then return to step 2 with the new planUnstage all: git reset HEAD
Stage and commit each group separately using git add <files> + git commit
After all commits are done, run Post-commit push handling (Step 8) — respects git.skip_push_after_commit
.unikit/ARCHITECTURE.md as read-only contextCo-Authored-By or any other trailer attributing authorship to the AI. Commits must not contain AI co-author linestype(scope):) is always in English; the subject and body text use the language from .unikit/config.yaml (language.artifacts)Frequently asked questions
Generate commit messages following the Conventional Commits specification, with {{enginename}}-specific safety checks.
The source record exposes this install command: npx skills add https://github.com/NintendaDev/unikit-ai --skill "skills/unikit-commit". Inspect the command and pinned source before running it.
Static rules flagged exec-script in the source; the page lists the matching lines and excerpts.
Alternatives
garrytan/gbrain
End-to-end discipline for turning any large data source (audio libraries, email takeouts, document corpora, chat exports, API dumps) into brain pages at scale. The lifecycle spine: SCHEMA → ACCESS → TRIAL → EVALUATE → IMPROVE → CODIFY → TEST → SKILLIFY → BULK → MONITOR. State is tracked in a durable JSON manifest (see MANIFEST-PATTERN.md) so any crash, session boundary, or subagent fan-out resumes from ground truth instead of memory.
alirezarezvani/claude-skills
App Store Optimization (ASO) toolkit for researching keywords, analyzing competitor rankings, generating metadata suggestions, and improving app visibility on Apple App Store and Google Play Store. Use when the user asks about ASO, app store rankings, app metadata, app titles and descriptions, app store listings, app visibility, or mobile app marketing on iOS or Android. Supports keyword research and scoring, competitor keyword analysis, metadata optimization, A/B test planning, launch checklist
wanshuiyin/Auto-claude-code-research-in-sleep
Use it for operations and research tasks; the detail page covers purpose, installation, and practical steps.
prowler-cloud/prowler
PostgreSQL indexing best practices for Prowler: index design, partial indexes, partitioned table indexing, EXPLAIN ANALYZE validation, concurrent operations, monitoring, and maintenance. Trigger: When creating or modifying PostgreSQL indexes, analyzing query performance with EXPLAIN, debugging slow queries, reviewing index usage statistics, reindexing, dropping indexes, or working with partitioned table indexes. Also trigger when discussing index strategies, partial indexes, or index maintenance