Conventional Commit Validation

VerifiedSafe

Create a single Conventional Commit for the current changes, following the repo's commit-msg rules.

Sby Skills Guide Bot
DevelopmentBeginner
7/23/2026
Claude Code
#git#conventional-commits#commit-workflow#version-control

Recommended for

Automated summary

Creates a single Conventional Commit for the current set of changes in the OpenWorkspace repository, following the repo's commit-msg hook rules.

Strengths

  • Inspects status and diffs before composing the message and only includes a coherent file set
  • Refuses to commit directly on main/master and suggests creating a branch first
  • Strictly enforces the type(scope): subject format with repo-defined types and scopes
  • Explicitly forbids AI mentions or co-author trailers in the commit message

Limitations

  • Tied to OpenWorkspace: the allowed types and scopes are specific to that repo
  • Relies on the local commit-msg hook being installed for validation
  • Does not push or open a PR, even if the user implicitly expects it
When to use it

Use when you want to turn your current working changes into one clean commit that matches the repository's conventions.

When not to use it

Avoid it for multiple atomic commits, history rewrites, or if the commit-msg hook is unavailable to validate the message.

Security analysis

Safe
Quality score86/100

The allowed tools are restricted to git status/diff/log/add/commit, all local and non-destructive. The instructions explicitly tell the agent not to push or open PRs unless asked, not to bypass failing hooks, and to leave unrelated changes out. There is no exfiltration, no curl|sh, no destructive filesystem action, and no instruction to disable safety measures. The only mild risk is that a careless `git add` could stage unintended files, which is inherent to any commit helper and partially guarded against.

Findings
  • •Uses `git add` broadly, which could stage unintended files (e.g. secrets or unrelated edits) if the agent is careless; the skill mitigates this by requiring a diff review and a coherence check first.
  • •Scope is limited to local git read/commit operations: no push, no network calls, no history rewriting, and it explicitly forbids bypassing the commit-msg hook.
How this analysis is made

Examples

Commit staged work
Commit these changes in OpenWorkspace with an appropriate Conventional Commit message.
Hint the subject
Commit the auth refactor and use 'auth: drop legacy token path' as a subject hint.
Commit a specific change
Stage only the changes in crates/ui and commit them with a Conventional Commit message.

name: commit description: Stage and commit the current changes as a single Conventional Commit that passes this repo's commit-msg rules. Use when the user asks to commit work in OpenWorkspace. argument-hint: "[optional subject hint]" allowed-tools: "Bash(git status *) Bash(git diff *) Bash(git add *) Bash(git commit *) Bash(git log *)"

Create one Conventional Commit for the current change set in OpenWorkspace.

Steps

  1. Run git status and git diff --staged (and git diff for unstaged) to see exactly what will be committed. If nothing is staged, stage the intended files with git add — confirm the set is coherent and unrelated changes are left out.
  2. Confirm you are not on main/master. If you are, stop and tell the user to branch first (git checkout -b <type>/<topic>) — the hooks will reject a commit on main anyway.
  3. Compose the message:
    • type(scope): subject — type ∈ feat fix docs style refactor perf test build ci chore.
    • scope = the crate or app touched (domain db auth floorplan crypto i18n notify jobs ui config observability web worker app frontend server) or a cross-cutting scope (ci dev deps release).
    • subject: imperative mood, ≤50 chars, no trailing period.
    • Add a body only when the why isn't obvious from the subject. Use a BREAKING CHANGE: footer or ! after the scope for breaking changes (pre-V1: a breaking change bumps MINOR).
    • Never add an assistant/AI mention or any co-author/"generated with" trailer — commits are authored by the human only.
  4. Commit with git commit -m "..." (and -m again for a body). The local commit-msg hook validates the result; if it rejects, read the message and fix it rather than bypassing.
  5. Show the user the final git log -1 --stat.

Do not push or open a PR unless explicitly asked.

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/conventional-commit-validation-mrx3y013/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/conventional-commit-validation-mrx3y013' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/conventional-commit-validation-mrx3y013/download' --output '.skill-downloads/conventional-commit-validation-mrx3y013/SKILL.md.part' && mv '.skill-downloads/conventional-commit-validation-mrx3y013/SKILL.md.part' '.skill-downloads/conventional-commit-validation-mrx3y013/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

Tools declared by the author (check availability in your agent): Bash(git status *) Bash(git diff *) Bash(git add *) Bash(git commit *) Bash(git log *)

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code
test -f '.skill-downloads/conventional-commit-validation-mrx3y013/SKILL.md' && test -s '.skill-downloads/conventional-commit-validation-mrx3y013/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/commit' && cp -R '.skill-downloads/conventional-commit-validation-mrx3y013' '.claude/skills/commit'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation
openskills install './.skill-downloads/conventional-commit-validation-mrx3y013'

openskills read 'conventional-commit-validation-mrx3y013'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/conventional-commit-validation-mrx3y013/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills