CtrlK
BlogDocsLog inGet started
Tessl Logo

commit

ALWAYS use this skill when committing code changes — never commit directly without it. Creates commits following Sentry conventions with proper conventional commit format and issue references. Trigger on any commit, git commit, save changes, or commit message task.

66

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is commit in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

82%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.

A well-structured, highly actionable instruction skill with concrete examples and a validated prerequisite workflow. Minor opportunities exist to trim the generic Principles section and possibly externalize the examples.

DimensionReasoningScore

Conciseness

The body is efficient and assumes Claude's competence (no explanation of git or commits), but the 'Principles' section restates widely-known commit best practices and could be trimmed, keeping it just below the top anchor.

4 / 5

Actionability

Fully actionable: a concrete format template, a commit-type table, explicit subject/body/footer rules, and copy-paste-ready worked examples (fix, feat, ref, breaking change, revert) covering the common cases.

5 / 5

Workflow Clarity

The Prerequisites section is a clear sequence with an explicit validation checkpoint (re-run 'git branch --show-current' and stop if still on main), but the core message-composition task is reference-style rather than a sequenced workflow with a post-commit feedback loop.

4 / 5

Progressive Disclosure

A single, well-organized file with clear section headers and one external reference link — no nested references — but at ~160 lines the large inline Examples block represents a minor organization gap rather than the ideal split structure.

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.

A strong description that clearly states both capability and explicit trigger conditions with natural keywords. Its main weakness is specificity: the concrete actions are described somewhat abstractly rather than enumerated.

Suggestions

Enumerate the concrete actions performed (e.g. 'drafts the conventional-commit header, writes the what/why body, and adds Fixes/Refs issue footers') instead of the abstract phrase 'proper conventional commit format and issue references'.

Soften the absolute 'ALWAYS use this skill' framing or scope it to Sentry projects to reduce conflict risk with generic commit skills.

DimensionReasoningScore

Specificity

Names the domain and a couple of concrete actions ('Creates commits following Sentry conventions with proper conventional commit format and issue references'), but the actions are framed abstractly ('proper conventional commit format') rather than enumerated, so coverage is not comprehensive.

3 / 5

Completeness

Explicitly answers both what ('Creates commits following Sentry conventions...') and when ('Trigger on any commit, git commit, save changes, or commit message task') with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Includes natural phrases users actually say — 'commit', 'git commit', 'save changes', 'commit message' — giving good keyword coverage, though a few synonyms (e.g. 'stage', 'push') are missing.

4 / 5

Distinctiveness Conflict Risk

The Sentry-conventions niche is mostly distinct, but the broad trigger terms ('commit', 'save changes') and the 'ALWAYS use this skill' framing create minor overlap risk with a generic git-commit skill.

4 / 5

Total

16

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
Reviewed

Table of Contents

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.