CtrlK
BlogDocsLog inGet started
Tessl Logo

oma-explanation

Create an offline HTML explanation of a code diff, PR, or branch. Use when an interactive code-change walkthrough is requested.

66

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/oma-explanation/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

81%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.

A well-engineered orchestration body: crisp scene flow with strong validation gates, secret-gate security, bounded retry loops, and concrete commands, with content appropriately split across resource contracts. The residual issues are redundancy (guardrails/control-flow/tools repeat each other) and referenced bundle files that are not present to verify.

Suggestions

Deduplicate the repeated archify-sidecar constraints (2 attempts / 5 minutes) and fold Control-flow features, Guardrails, and Tools-and-instruments overlaps into single sections to tighten the body.

Ensure the referenced contracts (`resources/document-structure.md`, `resources/html-contract.md`, `_shared/conditional/diagram-engine.md`) actually ship in the bundle, or note in the body that they are resolved from a shared skill root.

Inline the 'explainable diff' predicate (or a short version of it) instead of deferring to an external workflow file, so the skill remains self-contained on its own precondition.

DimensionReasoningScore

Conciseness

The body is dense and operational — resolution orders, tables, guardrails, concrete git/gh commands — with no explanations of concepts Claude already knows. However, several facts are stated multiple times (the archify sidecar's 2-attempt/5-minute cap appears in three places; guardrails largely restate Control-flow features; the Dependencies section repeats Tools and instruments), so it is 'efficient; minor instances... that could be trimmed' rather than fully lean.

4 / 5

Actionability

Concrete guidance is strong: exact commands (`gh pr diff`, `git diff main...{branch}`, `git diff --cached`, `oma explain validate [file]`), explicit output paths (`.agents/results/explain/{YYYY-MM-DD}-{slug}.html`), a numbered ref-resolution order, and a bounded fix loop. It is not copy-paste-ready end-to-end because the HTML authoring and grep checklist details live in `resources/html-contract.md`, and the 'explainable diff' predicate is deferred to an external workflow file — mostly executable with minor gaps, so 4 rather than 5.

4 / 5

Workflow Clarity

The scene sequence (RESOLVE → COLLECT → GATE → GENERATE → VALIDATE → DELIVER) is explicit with a pre-generation secret gate, a post-generation checklist validation loop bounded at 3 fix iterations, explicit stop conditions in Failure and recovery, and defined exit criteria (Success/Partial/Failure). This matches the anchor 'clear sequence with explicit validation steps; feedback loops for error recovery; checklists for complex processes' — nothing above it exists on the scale.

5 / 5

Progressive Disclosure

The body is a scheduling overview that cleanly defers WHAT to `resources/document-structure.md` and HOW to `resources/html-contract.md`, each annotated with its scope, plus a References section restating both — good one-level-deep structure. It scores 4 rather than 5 because none of the referenced files (`resources/*.md`, `_shared/conditional/diagram-engine.md`, `.agents/workflows/explain.md`) exist in the bundle, and the diagram-engine/conditional references are one step less clearly signaled than the two core contracts.

4 / 5

Total

17

/

20

Passed

Description

78%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 concise, third-person description that clearly states both what the skill produces and when to use it, with natural trigger terms. Its only weakness is limited action coverage — a single 'create an explanation' action rather than several specific capabilities (e.g., quiz generation, sidecar diagrams, validation).

DimensionReasoningScore

Specificity

"Create an offline HTML explanation of a code diff, PR, or branch" names the domain (diff/PR/branch, offline HTML) and one concrete action (create an explanation), but does not list several specific actions. It matches the 'names domain and 1-2 concrete actions' anchor; a 4 would require multiple distinct actions like the PDF extract/fill/merge example.

3 / 5

Completeness

It explicitly answers both: what — "Create an offline HTML explanation of a code diff, PR, or branch" — and when — "Use when an interactive code-change walkthrough is requested." Both are concrete and explicit with a clear trigger phrase, matching the anchor 5 example structure. A 4 would leave the 'when' weaker or less specific than this.

5 / 5

Trigger Term Quality

"code diff, PR, or branch" and "interactive code-change walkthrough" are natural phrases a user would plausibly say. A few common variations are missing (e.g., "explain this change", "commit", "walk me through") — good coverage but not comprehensive, matching the anchor 4 rather than 5.

4 / 5

Distinctiveness Conflict Risk

"offline HTML explanation of a code diff, PR, or branch" carves a fairly distinct niche (interactive explainer documents) that is unlikely to grab requests for code review, docs generation, or slide decks. Minor overlap risk remains with adjacent diff/document skills (e.g., docs-drift or PR review), so it fits 'mostly distinct; minor overlap risk' rather than the fully distinct anchor 5.

4 / 5

Total

16

/

20

Passed

Validation

100%

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
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.