aiskillstore/marketplace / skills/0xmsc/commit
commit
VerifiedHelps write conventional commit messages, create atomic commits, and follow git best practices. Use when the agent needs to help with git commits, commit message writing, or git workflow guidance.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 1016 B |
| assets/commit-template.txt | markdown | 128 B |
| references/conventional-commits.md | markdown | 1.9 KB |
| skill-report.json | config | 17.2 KB |
skill-report.json
View on GitHub{
"schema_version": "2.0",
"meta": {
"generated_at": "2026-07-06T00:56:00.277Z",
"slug": "0xmsc-commit",
"source_url": "https://github.com/0xmsc/coding_assistant/tree/master/src/coding_assistant/skills/commit",
"source_ref": "master",
"model": "codex",
"analysis_version": "3.0.0",
"source_type": "community",
"content_hash": "3ea8da94a2ba6effc2e5476f172d4348cdffbb8f4a1e2130e1a80d71b7dc2539",
"tree_hash": "691671182fa06a71caa20ef2cf651e6913d365afca3093446b8baf066cdf3371",
"provenance": {
"model_requested": "gpt-5.5:high",
"model_effective": "codex:gpt-5.5:high",
"fallback_chain": [
{
"agent": "codex",
"model": "gpt-5.5",
"effort": "high",
"outcome": "success"
}
],
"analysis_version": "3.0.0"
}
},
"skill": {
"name": "commit",
"description": "Helps write conventional commit messages, create atomic commits, and follow git best practices. Use when the agent needs to help with git commits, commit message writing, or git workflow guidance.",
"summary": "Helps create clear conventional commits and guides safe git workflows.",
"icon": "π¦",
"version": "1.0.0",
"author": "0xmsc",
"license": "MIT",
"category": "coding",
"tags": [
"git",
"conventional-commits",
"commit-messages",
"version-control",
"developer-workflow"
],
"supported_tools": [
"claude",
"codex",
"claude-code"
],
"risk_factors": [
"external_commands"
]
},
"security_audit": {
"risk_level": "safe",
"is_blocked": false,
"safe_to_publish": true,
"analysis_status": "ok",
"summary": "All static findings were reviewed against the referenced Markdown files. The backtick detections are documentation examples, and the system-reconnaissance finding is prose inside a commit message example. No prompt injection, exfiltration, or malicious intent was found.",
"remediation": [],
"risk_factor_evidence": [
{
"factor": "external_commands",
"evidence": [
{
"file": "references/conventional-commits.md",
"line_start": 55,
"line_end": 56
},
{
"file": "references/conventional-commits.md",
"line_start": 70,
"line_end": 73
},
{
"file": "SKILL.md",
"line_start": 9,
"line_end": 9
},
{
"file": "SKILL.md",
"line_start": 11,
"line_end": 11
},
{
"file": "SKILL.md",
"line_start": 15,
"line_end": 15
},
{
"file": "SKILL.md",
"line_start": 18,
"line_end": 18
},
{
"file": "SKILL.md",
"line_start": 19,
"line_end": 19
},
{
"file": "SKILL.md",
"line_start": 20,
"line_end": 20
},
{
"file": "SKILL.md",
"line_start": 21,
"line_end": 21
},
{
"file": "SKILL.md",
"line_start": 24,
"line_end": 24
}
]
}
],
"static_findings": [
{
"id": "external_commands:references/conventional-commits.md:55:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "references/conventional-commits.md",
"line_start": 55,
"line_end": 56,
"snippet": "BREAKING CHANGE: `extends` key in config file is now used for extending other config files"
},
{
"id": "external_commands:references/conventional-commits.md:70:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "references/conventional-commits.md",
"line_start": 70,
"line_end": 73,
"snippet": "BREAKING CHANGE: `window.addEventListener` no longer returns a promise"
},
{
"id": "blocker:references/conventional-commits.md:67:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "references/conventional-commits.md",
"line_start": 67,
"line_end": 67,
"snippet": "Introduce a request id and a reference to latest request. Dismiss"
},
{
"id": "external_commands:SKILL.md:9:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 9,
"line_end": 9,
"snippet": "1. **Analyze Results**: Review `git status` and `git diff --staged`."
},
{
"id": "external_commands:SKILL.md:11:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 11,
"line_end": 11,
"snippet": "- `feat`, `fix`, `docs`, `style`, `refactor`, `test`, `chore`."
},
{
"id": "external_commands:SKILL.md:15:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 15,
"line_end": 15,
"snippet": "4. **Templates**: Use `assets/commit-template.txt` for consistency."
},
{
"id": "external_commands:SKILL.md:18:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 18,
"line_end": 18,
"snippet": "- `git add <files>`"
},
{
"id": "external_commands:SKILL.md:19:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 19,
"line_end": 19,
"snippet": "- `git commit -m \"message\"`"
},
{
"id": "external_commands:SKILL.md:20:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 20,
"line_end": 20,
"snippet": "- `git diff --staged`"
},
{
"id": "external_commands:SKILL.md:21:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 21,
"line_end": 21,
"snippet": "- `git status`, `git show`, `git log --oneline`"
},
{
"id": "external_commands:SKILL.md:24:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 24,
"line_end": 24,
"snippet": "- No interactive commands (`git add -p`, `git rebase -i`)."
}
],
"finding_verdicts": [
{
"id": "external_commands:references/conventional-commits.md:55:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "Line 55 is a Conventional Commits example footer with an inline backticked configuration key. It is Markdown documentation, not Ruby or shell execution."
},
{
"id": "external_commands:references/conventional-commits.md:70:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "Line 70 is a sample commit footer that mentions an API name inside Markdown backticks. It does not invoke a command or evaluate code."
},
{
"id": "blocker:references/conventional-commits.md:67:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "Line 67 describes request handling inside an example commit body. It contains no system enumeration, host inspection, or reconnaissance instruction."
},
{
"id": "external_commands:SKILL.md:9:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.95,
"reason": "Line 9 is Markdown guidance to review git status and staged diff output. The backticks format command names and do not execute a shell."
},
{
"id": "external_commands:SKILL.md:11:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "Line 11 lists Conventional Commits type names in inline code formatting. These are labels, not executable commands."
},
{
"id": "external_commands:SKILL.md:15:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "Line 15 references a local template path in Markdown backticks. It is not a shell command and does not request execution."
},
{
"id": "external_commands:SKILL.md:18:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.88,
"reason": "Line 18 lists git add as a safe git workflow command, not executable code embedded in the skill. It stages user-selected files and is constrained by the skill's confirmation guidance."
},
{
"id": "external_commands:SKILL.md:19:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.88,
"reason": "Line 19 documents a standard git commit command rather than a hidden shell invocation. The skill requires confirmation before final commit or push."
},
{
"id": "external_commands:SKILL.md:20:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.94,
"reason": "Line 20 lists git diff --staged as a read-only inspection command. Markdown backticks triggered the pattern, but no code executes."
},
{
"id": "external_commands:SKILL.md:21:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.93,
"reason": "Line 21 lists read-only git inspection commands for reviewing repository state. The text is documentation and contains no command injection vector."
},
{
"id": "external_commands:SKILL.md:24:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "Line 24 prohibits interactive commands and mentions them only as examples. This is a safety limitation, not an instruction to execute backticked shell code."
}
],
"semantic_findings": [],
"critical_findings": [],
"high_findings": [],
"medium_findings": [],
"low_findings": [],
"dangerous_patterns": [],
"files_scanned": 3,
"total_lines": 108,
"audit_model": "codex",
"audited_at": "2026-07-06T00:56:00.277Z",
"agent_auto_install_policy": "allowed",
"manual_install_policy": "allowed"
},
"content": {
"user_title": "Write Conventional Git Commits",
"value_statement": "Developers often lose time turning staged changes into clear commit history. This skill guides Conventional Commits, atomic changes, and safe git review steps.",
"seo_keywords": [
"Claude",
"Codex",
"Claude Code",
"git commit",
"conventional commits",
"commit message helper",
"atomic commits",
"version control",
"developer workflow",
"commit template"
],
"actual_capabilities": [
"Reviews git status and staged diff output before drafting a message.",
"Applies Conventional Commits type, scope, subject, body, and footer guidance.",
"Encourages one logical change per commit.",
"Uses the included commit template for consistent structure.",
"Identifies safe git commands and avoids interactive commit workflows.",
"Requires confirmation before final commit or push."
],
"limitations": [
"Does not replace human review of staged changes.",
"Does not automate interactive git operations.",
"Does not allow force pushes or amend operations without explicit user guidance.",
"Depends on accurate git status and staged diff output."
],
"use_cases": [
{
"title": "Prepare feature commits",
"description": "Turn staged feature changes into a clear Conventional Commits message with subject, optional body, and footer guidance.",
"target_user": "Application developer"
},
{
"title": "Keep team history consistent",
"description": "Apply shared commit types and atomic commit rules across routine repository work.",
"target_user": "Engineering lead"
},
{
"title": "Document non-code updates",
"description": "Create concise commit messages for documentation, configuration, and maintenance changes.",
"target_user": "Technical writer"
}
],
"prompt_templates": [
{
"title": "Draft a commit message",
"prompt": "Review my staged changes and suggest one Conventional Commits message. Keep the subject under 50 characters.",
"scenario": "Beginner commit drafting"
},
{
"title": "Check commit scope",
"prompt": "Use git status and git diff --staged to identify the best type and optional scope. Explain the choice before suggesting the message.",
"scenario": "Intermediate message refinement"
},
{
"title": "Plan atomic commits",
"prompt": "Review the staged and unstaged changes. Recommend separate atomic commits with file groups and proposed messages before any commit is created.",
"scenario": "Intermediate commit planning"
},
{
"title": "Validate release commit",
"prompt": "Audit the final message for Conventional Commits format, breaking-change footer quality, body clarity, and safe git workflow before commit creation.",
"scenario": "Advanced release preparation"
}
],
"output_examples": [
{
"input": "Staged files update login validation and add tests.",
"output": "Suggested message: fix(auth): reject invalid login payloads. Body notes validation behavior and added tests."
},
{
"input": "Documentation changes clarify setup steps.",
"output": "Suggested message: docs(readme): clarify setup steps. The output keeps the subject concise and omits an unnecessary body."
},
{
"input": "A public API option was renamed and migration notes were added.",
"output": "Suggested message: feat(api): rename config option. Footer explains the breaking change and migration path."
}
],
"best_practices": [
"Review staged diff output before writing the final message.",
"Keep each commit focused on one logical change.",
"Ask for confirmation before creating or pushing commits."
],
"anti_patterns": [
"Committing changes that were not reviewed.",
"Using vague subjects such as update files or misc changes.",
"Force pushing, amending, or rebasing without explicit approval."
],
"faq": [
{
"question": "Which commit format does this skill use?",
"answer": "It uses Conventional Commits with type, optional scope, subject, body, and footer guidance."
},
{
"question": "Does this skill create commits automatically?",
"answer": "It guides commit creation, but it requires confirmation before final commit or push."
},
{
"question": "Can it help split large changes?",
"answer": "Yes. It encourages atomic commits and can recommend separate logical commits before creation."
},
{
"question": "Which AI tools are supported?",
"answer": "The skill is compatible with Claude, Codex, and Claude Code."
},
{
"question": "Does it inspect unstaged changes?",
"answer": "It can review git status and staged diff guidance, but the final message should match staged changes."
},
{
"question": "Can it handle breaking changes?",
"answer": "Yes. It includes BREAKING CHANGE footer guidance and migration context when needed."
}
]
},
"file_structure": [
{
"name": "assets",
"type": "dir",
"path": "assets",
"children": [
{
"name": "commit-template.txt",
"type": "file",
"path": "assets/commit-template.txt",
"lines": 7
}
]
},
{
"name": "references",
"type": "dir",
"path": "references",
"children": [
{
"name": "conventional-commits.md",
"type": "file",
"path": "references/conventional-commits.md",
"lines": 74
}
]
},
{
"name": "SKILL.md",
"type": "file",
"path": "SKILL.md",
"lines": 27
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why β repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" β or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself β your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |