CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

commit

Use when changes are ready to commit - generates conventional commit messages with scope detection and validation.

Quality

73%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/commit/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 delivers a clear, actionable five-step commit workflow with real commands, decision tables, and explicit pre-commit validation. Its weakest points are redundancy between the Rules section and the workflow steps, a motivational table that adds tokens without procedure, and one placeholder command plus a large-file check that does not actually check file size.

Suggestions

Remove or merge the Rules section with Steps 3-4, where every rule (validate first, conventional format, imperative mood, 72-char limit) is already stated, to cut redundant tokens.

Replace the placeholder "git add [relevant files]" with concrete guidance (e.g., stage the files identified in Step 1 with git add <paths>, or "git add -u" for tracked changes).

Fix the large-file validation: the current awk pipeline only prints filenames; use a command that actually tests size, e.g. "git diff --cached --numstat" plus a size check or "find . -size +1M" against staged paths.

DimensionReasoningScore

Conciseness

The body is mostly lean (tables, commands, example outputs), but the Rules section restates Step 3 and Step 4 content ("Always validate before committing", "Max 72 chars", "type(scope): description"), and the Anti-Rationalization table ("You won't. The context is fresh NOW.") is motivational padding. This matches "mostly efficient but could be tightened" rather than the minor-trims bar of 4.

3 / 5

Actionability

Concrete, executable commands appear throughout (git status --porcelain, grep -E '\.(env|pem|key)$', git commit -m "type(scope): description"), with precise constraints (scope max 15 chars, subject max 72 chars). It is not 5 because "git add [relevant files]" is a placeholder and the large-file check (git diff --cached --stat | awk '{print $NF}' | head -5) prints filenames without ever testing the stated 1MB threshold.

4 / 5

Workflow Clarity

A clear 5-step sequence (Analyze, Detect, Generate, Validate, Execute) with an explicit validation checkpoint in Step 4 and a warn/preview decision point ("Proceed anyway? Showing commit preview"). It is not 5 because there is no error-recovery feedback loop for execution failures such as rejected pre-commit hooks, and validation stops at the pre-commit stage.

4 / 5

Progressive Disclosure

A well-organized single-file skill with clear section headers (When to Use, Workflow, Output, Rules) and easy navigation, and no external references are needed. It is not 5 because at ~140 lines it exceeds the simple under-50-line case, and consolidated sections (duplicated Rules, Anti-Rationalization) leave minor organization gaps.

4 / 5

Total

15

/

20

Passed

Description

70%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 solid description that explicitly answers both what the skill does and when to use it, with natural trigger phrasing centered on "commit". Its main weaknesses are the compressed single-clause action listing and a single trigger scenario that omits common variations like "git".

Suggestions

List the concrete capabilities in parallel (e.g., "generates conventional commit messages, detects type and scope from changed files, validates for secrets and debug code") to raise specificity.

Add one or two more trigger variations, such as "Use when the user asks to commit, make a git commit, or write a commit message", to broaden trigger coverage and completeness.

DimensionReasoningScore

Specificity

"generates conventional commit messages with scope detection and validation" names the domain plus one primary action with two attached modifiers, matching the anchor for 1-2 concrete actions. It is not 4 because the capabilities are compressed into a single clause rather than listed as several parallel actions, and coverage gaps exist (staging and executing the commit are never mentioned).

3 / 5

Completeness

Both parts are explicit: the what ("generates conventional commit messages with scope detection and validation") and the when ("Use when changes are ready to commit"). It is not 5 because the 'when' clause offers only a single trigger situation without additional concrete trigger phrases or variations.

4 / 5

Trigger Term Quality

"ready to commit" and "commit messages" are natural phrases users would say, giving good keyword coverage. It falls short of 5 because common variations and synonyms such as "git", "make a commit", or "commit this" are missing.

4 / 5

Distinctiveness Conflict Risk

"conventional commit messages with scope detection and validation" carves a clear, mostly distinct niche. It is not 5 because "changes are ready to commit" carries minor overlap risk with generic git/version-control helper skills.

4 / 5

Total

15

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

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

Warning

Total

14

/

16

Passed

Repository

fernandezbaptiste/specialist-agent

Path

skills/commit/SKILL.md

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.