git-master

MUST USE for ANY git operations. Atomic commits, rebase/squash, history search (blame, bisect, log -S). STRONGLY RECOMMENDED: Use with task(category='quick', load_skills=['git-master'], ...) to save context. Triggers: 'commit', 'rebase', 'squash', 'who wrote', 'when was X added', 'find the commit that'.

Install with Tessl CLI

npx tessl i github:code-yeongyu/oh-my-openagent --skill git-master

What are skills?

Quality

88%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

SKILL.md

Review

Evals

Quality

Discovery

100%

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

This is a strong skill description that excels across all dimensions. It provides specific git operations, includes natural trigger terms users would actually say, explicitly states both what it does and when to use it, and has a clear distinctive niche. The inclusion of implementation guidance (task category recommendation) adds practical value without detracting from clarity.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: 'Atomic commits, rebase/squash, history search (blame, bisect, log -S)' - these are precise git operations with specific command references.	3 / 3
Completeness	Clearly answers both what (git operations, atomic commits, rebase/squash, history search) AND when (explicit 'Triggers:' section with specific phrases, plus 'MUST USE for ANY git operations').	3 / 3
Trigger Term Quality	Excellent coverage of natural trigger terms users would say: 'commit', 'rebase', 'squash', 'who wrote', 'when was X added', 'find the commit that' - these match real user language patterns.	3 / 3
Distinctiveness Conflict Risk	Very clear niche focused specifically on git operations with distinct triggers like 'rebase', 'squash', 'blame', 'bisect' that are unlikely to conflict with other skills.	3 / 3
	Total	12 / 12 Passed

Implementation

77%

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

This is a highly actionable and well-structured git skill with excellent workflow clarity and concrete executable guidance. However, it suffers from verbosity through excessive repetition of warnings and rules, and would benefit from being split into multiple focused files rather than one massive document. The content is thorough but could be 40% shorter while maintaining the same utility.

Suggestions

Split into separate files: COMMIT.md, REBASE.md, HISTORY-SEARCH.md with SKILL.md as a brief overview pointing to each

Consolidate the repeated 'MUST SPLIT' warnings into a single prominent section rather than repeating throughout

Remove redundant formatting of the same rules (e.g., the minimum commit count formula appears in multiple formats)

Add a quick-reference card at the top for common operations, moving detailed phases to linked files

Dimension	Reasoning	Score
Conciseness	The skill is comprehensive but overly verbose in places, with repeated warnings (e.g., 'BLOCKING', 'MANDATORY', 'NON-NEGOTIABLE' appear excessively) and some redundant explanations. The core principle section repeats the same rules multiple times in different formats.	2 / 3
Actionability	Excellent actionability with fully executable git commands, specific examples, clear decision tables, and copy-paste ready code blocks. Every workflow has concrete commands with actual syntax.	3 / 3
Workflow Clarity	Outstanding workflow clarity with explicit phases (0-6, R1-R4, H1-H3), validation checkpoints ('BLOCKING - MUST OUTPUT BEFORE PROCEEDING'), clear decision trees, and explicit verification steps. Includes recovery procedures and anti-patterns.	3 / 3
Progressive Disclosure	The skill is a monolithic 700+ line document that could benefit from splitting into separate files (COMMIT.md, REBASE.md, HISTORY.md). While internally organized with clear sections, the sheer length makes navigation difficult and no external references are provided.	2 / 3
	Total	10 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1106 lines); consider splitting into references/ and linking	Warning

	Total	10 / 11 Passed

Reviewed: 3 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.