oma-scm

SCM (software configuration management) and Git: branching, merges, conflicts, worktrees, baselines, audit readiness, plus Conventional Commits and safe staging.

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/oma-scm/SKILL.md

Quality

Content

70%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 body is highly actionable with clear, validated multi-step workflows for risky Git operations, but it is over-long for an overview and inlines content that the references section implies lives in separate files. Several referenced resource files are absent from the bundle.

Suggestions

Actually provide resources/conventional-commits.md, resources/onboarding-risk-signals.md, and resources/codeowners-playbook.md, or remove the dangling references, so navigation is not dead-ended.

Move the inlined CM process map, onboarding risk scan, and CODEOWNERS checklist into their referenced files and keep SKILL.md a concise overview pointing to them, improving both conciseness and progressive disclosure.

Trim the abstract meta-framework scaffolding (Structural Flow / Logical Operations / SSL-primitive table) that restates process in generic terms Claude does not need, to reduce token cost.

Dimension	Reasoning	Score
Conciseness	The body is mostly actionable reference material with little concept-over-explanation, but the abstract meta-framework sections ("Structural Flow", "Logical Operations", SSL-primitive table) and a duplicated co-author warning add scaffolding that could be tightened to reach 4.	3 / 5
Actionability	Concrete, executable commands abound (git status -sb, commit heredoc, fixup/autosquash, worktree add, gitleaks, gh pr create), but the commit examples rely on placeholders like <specific-files> and <type>(<scope>): <description> rather than being literally copy-paste ready, keeping it just below 5.	4 / 5
Workflow Clarity	Multi-step processes (CM workflows 1-6, commit workflow Steps 1-5, push/amend flows) are explicitly sequenced with validation checkpoints (VERIFY scene, amend must-not-absorb check, --force-with-lease, secret scan), satisfying the destructive-operation bar rather than triggering the cap at 3.	5 / 5
Progressive Disclosure	Sections are organized and references are signaled, but the referenced resources/*.md files do not exist in the bundle and large blocks (CM process map, onboarding risk scan, CODEOWNERS checklist, Conventional Commits guide) are inlined rather than split into the one-level-deep files the structure implies.	3 / 5
	Total	15 / 20 Passed

Description

66%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 names a specific, recognizable domain with strong natural trigger terms, but it omits any explicit "Use when..." guidance, which caps its completeness. It is concise and not padded.

Suggestions

Add an explicit "Use when..." clause listing concrete trigger phrases (e.g., "Use when the user asks to commit, branch, merge, resolve conflicts, manage worktrees, or write Conventional Commits") to lift completeness from 3 to 5.

Include common synonyms users say (commit, rebase, pull request, PR) alongside Git to broaden trigger-term coverage.

Reframe a few domain topics as verb-actions (e.g., "create branches, resolve merge conflicts, manage worktrees") to nudge specificity toward 5.

Dimension	Reasoning	Score
Specificity	Lists several concrete capability areas ("branching, merges, conflicts, worktrees, baselines, audit readiness, plus Conventional Commits and safe staging") but they are domain topics rather than verb-actions, so it falls just short of the comprehensive-anchor 5.	4 / 5
Completeness	It clearly answers the "what" but contains no "Use when..." trigger clause, and the rubric caps completeness at 3 when explicit trigger guidance is missing.	3 / 5
Trigger Term Quality	Strong natural terms (Git, branching, merges, conflicts, worktrees, Conventional Commits, staging) that users would actually say, but misses common synonyms like commit, rebase, PR, or .git extensions that would push it to a 5.	4 / 5
Distinctiveness Conflict Risk	The SCM/Git niche is clear and distinct with minimal conflict risk against other skills, though the absence of explicit trigger phrases leaves minor ambiguity versus adjacent oma-* skills.	4 / 5
	Total	15 / 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: first-fluke/oh-my-agent
Path: .agents/skills/oma-scm/SKILL.md
Commit: 3ff31bd

Reviewed: 1 day 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.