commit

Create a well-formed git commit from current changes using session history for rationale and summary; use when asked to commit, prepare a commit message, or finalize staged work.

1.00x

Quality

80%

Does it follow best practices?

Impact

56%

1.00x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.codex/skills/commit/SKILL.md

Quality

Content

81%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.

The content is a well-structured, actionable commit workflow with explicit validation checkpoints that appropriately handle the destructive nature of committing. It is token-efficient and avoids over-explaining git basics, with only minor room for a worked example and tighter Goals.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence, avoiding explanations of git concepts; the Goals section lightly restates the description and a few steps could be tightened, keeping it just below the 'every token earns its place' anchor at 5.	4 / 5
Actionability	Concrete commands (`git status`, `git diff --staged`, `git add -A`, `git commit -F <file>`) and specific rules (<=72 char subject, imperative mood, 72-char wrap) plus a fill-in template give mostly executable guidance, but no fully worked example message with real content leaves a minor gap.	4 / 5
Workflow Clarity	Twelve clearly sequenced steps include explicit validation/feedback loops (step 4 sanity-checking added files, step 5 fixing incomplete/unrelated staging, step 12 ensuring the message matches the staged diff before committing), satisfying the destructive-operation validation requirement.	5 / 5
Progressive Disclosure	A single well-organized SKILL.md with clear sections (Goals, Inputs, Steps, Output, Template) and no unnecessary external references; slightly over the ~50-line simple-skill threshold, so it sits just below the top anchor.	4 / 5
	Total	17 / 20 Passed

Description

78%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.

The description is strong: it clearly states what the skill does and gives concrete natural-language triggers for when to use it. It is concise and free of vague fluff, with only minor room to broaden trigger synonyms and reduce overlap with general git skills.

Dimension	Reasoning	Score
Specificity	Names the domain (git commits) and the concrete action of creating a well-formed commit with rationale/summary, but does not list several distinct actions, fitting the '1-2 concrete actions' anchor rather than the 'several specific actions' anchor at 4.	3 / 5
Completeness	Explicitly answers both what ('Create a well-formed git commit from current changes using session history for rationale and summary') and when ('use when asked to commit, prepare a commit message, or finalize staged work') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural phrases like 'asked to commit', 'prepare a commit message', and 'finalize staged work' are things users would actually say; coverage is good but lacks a few synonyms/variations that would push it to 5.	4 / 5
Distinctiveness Conflict Risk	The commit-creation niche is distinct with specific triggers, but there is minor overlap risk with broader git/version-control skills, keeping it just below the minimal-conflict anchor at 5.	4 / 5
	Total	16 / 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: openai/symphony
Path: .codex/skills/commit/SKILL.md
Commit: 8001b52

Reviewed: 23 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.