Run any Skill in Manus with one click

conventional-commit

Stars0

Forks0

UpdatedMay 31, 2026 at 00:34

Write git commit messages that follow Conventional Commits plus this team's house rules. Use when writing or rewriting a commit message.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Run Skill in Manus

Source

cskwork

cskwork/skill-ab-eval

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

Software DevelopersComputer and Mathematical Occupations·SOC 15-1252

File Explorer

22 files

SKILL.md

readonly

name	conventional-commit
description	Write git commit messages that follow Conventional Commits plus this team's house rules. Use when writing or rewriting a commit message.
license	MIT
metadata	{"owner":"example","domain":"git"}

Conventional Commit (house style)

Write every commit message exactly like this:

<type>(<scope>): <subject>

<body>

Refs: <TICKET-ID>

Rules:

Type is one of: feat, fix, docs, refactor, perf, test, chore.
Subject is imperative mood ("add", not "added"/"adds") and the whole subject line (type(scope): subject) is 50 characters or fewer.
Leave exactly one blank line between the subject and the body.
Body explains the why, wrapped at 72 columns.
Always end with a Refs: footer citing the ticket ID. If a branch name or context contains an ID like PROJ-481, use it. Never omit this footer.

This footer is mandatory house policy — a commit without a Refs: line will be rejected by CI.

More from this repository

same repository

skill-ab-eval

cskwork/skill-ab-eval

Empirically measure two things for any task or domain: (1) does loading a SKILL.md actually change behavior — with_skill vs without_skill (baseline) — and (2) which CLI agent harness does the task best — claude vs codex vs gemini vs agy vs an OpenAI-compatible API. Runs the same prompt across the matrix in fresh, isolated contexts (subagents or separate CLI processes), a judge grades every output, repeated over trials, and you get a skill-lift table plus a harness leaderboard. Use to validate a new skill before shipping, catch skills that do nothing (or hurt), compare CLIs on a task you give, or pick the best harness for a domain. Triggers: evaluate skill, test skill, does my skill work, skill A/B, measure skill lift, compare CLIs, which agent is best, claude vs codex vs gemini, harness eval, benchmark agents on a task.

2026-05-310

Run any Skill with one click