semantic-git

Manage Git commits using conventional commit format with atomic staging. Always generate plain git commands before running them and offer to let the user run them manually.

Quality

58%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/semantic-git/SKILL.md

Quality

Discovery

32%

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 identifies its domain (Git/conventional commits) and mentions some behavioral constraints (generate commands first, offer manual execution), but lacks explicit trigger guidance and comprehensive action verbs. The absence of a 'Use when...' clause significantly weakens its utility for skill selection among many options.

Suggestions

Add a 'Use when...' clause with natural trigger terms like 'commit message', 'staged changes', 'git commit', 'conventional commit'

Replace vague 'Manage Git commits' with specific actions like 'Generate commit messages, stage files atomically, format commits using conventional commit standards'

Include common user phrases and variations: 'commit', 'committing code', 'write a commit message', 'review my changes'

Dimension	Reasoning	Score
Specificity	Names the domain (Git commits) and some actions (manage, staging, generate commands), but lacks comprehensive specific actions like 'create commit messages', 'stage files', 'review diffs'. The phrase 'manage Git commits' is somewhat vague.	2 / 3
Completeness	Describes what it does (manage commits, generate commands) but completely lacks a 'Use when...' clause or any explicit trigger guidance. Per rubric guidelines, missing explicit trigger guidance caps this at 2, and the 'what' is also weak, warranting a 1.	1 / 3
Trigger Term Quality	Includes relevant terms like 'Git commits', 'conventional commit', 'atomic staging', but misses common user phrases like 'commit message', 'staged changes', 'git diff', or file extensions. Users might say 'help me commit' which isn't explicitly covered.	2 / 3
Distinctiveness Conflict Risk	The 'conventional commit format' and 'atomic staging' provide some distinctiveness, but 'manage Git commits' could overlap with general Git skills. The lack of explicit file types or unique trigger terms increases conflict risk.	2 / 3
	Total	7 / 12 Passed

Implementation

85%

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

This is a well-structured skill with excellent workflow clarity and actionability. The main weakness is verbosity in explaining conventional commit concepts that Claude already knows (commit types, imperative mood, etc.). The zagi integration, stop-and-ask protocols, and automation mode are valuable additions that justify their token cost.

Suggestions

Remove or significantly condense the commit types list - Claude knows conventional commit types; a brief reminder or link to reference file would suffice

Trim the 'Subject Line' guidelines about imperative mood and formatting - these are standard knowledge that doesn't need explanation

Dimension	Reasoning	Score
Conciseness	The skill includes some unnecessary explanation (e.g., listing all commit types with descriptions Claude already knows, explaining imperative mood). The zagi-awareness section and workflow are valuable, but the conventional commit format details could be trimmed significantly.	2 / 3
Actionability	Provides concrete, executable git commands with exact syntax, clear examples of commit message formats, and specific workflow steps. The command examples are copy-paste ready and the workflow is explicit about what to run.	3 / 3
Workflow Clarity	Excellent multi-step workflow with explicit validation (CI checks before staging), clear sequencing (implement → verify → stage → suggest → generate → ask → commit → confirm), and feedback loops (stop if checks fail, confirm before next commit). Includes stop-and-ask protocols for destructive operations.	3 / 3
Progressive Disclosure	Well-structured with clear sections, appropriate inline content for quick reference, and one-level-deep references to detailed guidance files (conventional-commits.md, ci-verification.md, co-authors.md). Navigation is clear and content is appropriately split.	3 / 3
	Total	11 / 12 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: siviter-xyz/dot-agent
Commit: 3376255

Reviewed: 11 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.