oma-scm

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

Quality

80%

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

77%

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

A highly actionable, well-sequenced SCM skill with strong workflow guardrails, held back by some redundant/boilerplate structure and references that point to non-existent bundle files.

Suggestions

Move the duplicated commit format into one place and drop the abstract 'SSL primitive'/'Resource scope' tables to reduce token overhead.

Either create the referenced config/*.yaml and resources/*.md files or remove those references so navigation is one level deep and resolvable.

Consider extracting the CODEOWNERS checklist and onboarding risk scan into a separate reference file referenced once from the body.

Dimension	Reasoning	Score
Conciseness	Mostly actionable, but includes templated overhead (the 'SSL primitive' / 'Resource scope' tables) and duplicates the commit format in two places, so it could be tightened.	2 / 3
Actionability	Provides copy-paste-ready commands (git status -sb, explicit-path git add, heredoc and -F commit fallbacks, git worktree add) with specific examples.	3 / 3
Workflow Clarity	Clear sequencing via PREPARE→FINALIZE scenes and numbered CM workflows 1–6, with explicit guardrails and failure/recovery steps for risky operations like secrets and conflicts.	3 / 3
Progressive Disclosure	Sections are organized, but content that could be split (CODEOWNERS checklist, onboarding scan, Conventional Commits detail) is inline, and the referenced resources/.md and config/.yaml files do not exist in any bundle directory.	2 / 3
	Total	10 / 12 Passed

Description

82%

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 specific, well-triggered description with strong capability coverage and a clear SCM niche, weakened only by the absence of an explicit 'Use when...' trigger clause.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user asks to commit, branch, merge, resolve conflicts, manage worktrees, or apply Conventional Commits.'

Keep the existing concrete action list but pair it with the trigger guidance so both 'what' and 'when' are explicit.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'branching, merges, conflicts, worktrees, baselines, audit readiness, plus Conventional Commits and safe staging' — matching the highest anchor.	3 / 3
Completeness	Clearly answers 'what' but has no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 2 per the judging guidelines.	2 / 3
Trigger Term Quality	Covers natural terms users would say (Git, branching, merges, conflicts, worktrees, commits, staging) with good variation rather than abstract jargon.	3 / 3
Distinctiveness Conflict Risk	The CM/audit/governance plus Conventional Commits framing carves a clear niche unlikely to trigger for non-SCM skills.	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 — 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: 3021301

Reviewed: about 24 hours 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.