commit-changes

Create a git commit for the current changes. Use when asked to commit changes, make a commit, generate a commit message, or commit the current worktree with optional user-provided context.

Quality

95%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

92%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

An exemplary lean skill body: fully executable commands, an explicit sequence with early-exit and hook-failure feedback loops, and clean sectioning that needs no external files. The single gap is the absence of a worked commit-message example.

Suggestions

Add one worked example commit message (e.g. 'feat(auth): implement JWT-based authentication') showing the type(scope) format applied, since the message is the skill's main output.

Clarify what 'stage the relevant files' means when unstaged changes exist — e.g. stage files related to the change being committed rather than everything via 'git add -A'.

Dimension	Reasoning	Score
Conciseness	The 44-line body contains no git tutorials, no filler, and no concepts Claude doesn't already know — every line instructs ('Keep the first line under 72 characters', 'Do not push'). Matches anchor 5; there is nothing to trim, so anchor 4 does not apply.	5 / 5
Actionability	Commands are concrete and executable throughout ('git status --short', 'git diff --cached --stat', 'git commit -m "message"') plus a message template and an enumerated allowed-types list. It falls short of anchor 5 because no worked example commit message is provided, even though the message is the skill's core deliverable.	4 / 5
Workflow Clarity	A clearly numbered sequence with explicit checkpoints: an early exit ('If there are no changes to commit, tell the user and stop') and a validate-fix-retry feedback loop for hook failures with escalation ('stop and ask the user'). Matches anchor 5's explicit validation and error-recovery pattern.	5 / 5
Progressive Disclosure	Under 50 lines, single-purpose, with no need for external references; the body has no bundle files and none are warranted. Clean sectioning (Workflow / Message guidelines / Commit rules) meets the rubric's simple-skill exception for anchor 5.	5 / 5
	Total	19 / 20 Passed

Description

95%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A tight, well-formed description: concrete actions, explicit what and when, and natural trigger phrasing with synonym coverage. The only soft spot is that the listed actions are all variants of a single commit task, leaving minor coverage gaps.

Dimension	Reasoning	Score
Specificity	Names several concrete actions — 'Create a git commit', 'generate a commit message', 'commit the current worktree' — with minor gaps (staging and message conventions are unmentioned). It exceeds anchor 3's '1-2 concrete actions' but the actions are variants of one task rather than the comprehensive coverage of anchor 5.	4 / 5
Completeness	Explicitly answers both what ('Create a git commit for the current changes') and when, via a concrete 'Use when asked to...' clause listing trigger phrases. This matches anchor 5 exactly; anchor 4 would require the when-clause to be less explicit.	5 / 5
Trigger Term Quality	'commit changes', 'make a commit', 'generate a commit message', 'commit the current worktree' are the natural phrasings users say for this task, with synonym coverage. Only marginal variants ('save my changes') are absent, so it fits anchor 5 rather than anchor 4's 'a few natural terms missing'.	5 / 5
Distinctiveness Conflict Risk	Clear niche (git commit creation) with triggers that only apply to this task; the commit-message trigger describes a sub-capability of this same skill rather than an overlap risk. Minimal conflict risk fits anchor 5.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: tldraw/tldraw
Path: skills/commit-changes/SKILL.md
Commit: db1c86e

Reviewed: 9 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.