uinaf/skill-audit
Audit existing skills with Tessl scoring, trigger-coverage checks, repo conventions, or quick experiential feedback from a recent task. Use when revising skills, triaging weak activation, or turning observed skill guidance failures into scoped repo edits.
95
95%
Does it follow best practices?
Impact
95%
1.03xAverage score across 3 eval scenarios
Passed
No known issues
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, well-crafted description that clearly defines a specific niche (skill auditing), lists concrete actions, provides explicit trigger conditions with natural keywords, and includes boundary-setting 'Do not use' guidance. It uses proper third-person voice throughout and would be easily distinguishable from other skills in a large skill library.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Tessl scoring', 'metadata and trigger-coverage checks', 'repo conventions', and 'skill-authoring best practices'. These are concrete, identifiable audit activities rather than vague abstractions. | 3 / 3 |
Completeness | Clearly answers both 'what' (audit skills with scoring, metadata checks, conventions, best practices) and 'when' (creating/revising skills, triaging weak self-activation, comparing against repo guidance). Also includes explicit 'Do not use' guidance, which further clarifies boundaries. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'creating or revising a skill', 'weak self-activation', 'AGENTS.md', 'CLAUDE.md', 'repo rules', 'skill guidance', 'audit'. These cover multiple natural phrasings a user might employ when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche — auditing skills specifically with Tessl scoring and skill-authoring best practices. The 'Do not use' clause explicitly excludes general code verification and unrelated docs, reducing conflict risk with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
92%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-crafted skill that provides clear, actionable audit guidance with concrete CLI commands, specific failure patterns, and a well-sequenced workflow with validation checkpoints. It respects Claude's intelligence by avoiding unnecessary explanations and maintains good structure throughout. The main weakness is that progressive disclosure cannot be fully verified without bundle files, and the body could potentially be trimmed by moving some audit dimension details into references.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient throughout. It assumes Claude's competence, avoids explaining what skills or audits are, and every section earns its place with actionable guidance. The principles, handoffs, and workflow steps are all tightly written. | 3 / 3 |
Actionability | Provides concrete CLI commands (npx tessl skill review --json, --optimize flags), specific file paths to check, concrete examples of weak vs stronger metadata, explicit failure signs to look for, and a structured output format. The quick experiential feedback mode gives a clear alternative workflow with specific steps. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced (1-6) with explicit validation: run Tessl first to get a baseline score, audit discovery/shape/disclosure/repo-fit in order, then synthesize changes and rerun Tessl. The feedback loop (fix → rerun Tessl → report improvement) is explicit. The 'Before You Start' section establishes prerequisites, and the output section defines what 'done' looks like. | 3 / 3 |
Progressive Disclosure | The skill references two supporting files (references/scorecard.md and references/best-practices.md) with clear signals, and the body appropriately keeps the core workflow inline. However, no bundle files were provided, so we cannot verify these references exist. The skill itself could benefit from moving the detailed audit dimensions (steps 2-5) into a reference file, as the body is moderately long for a SKILL.md. | 2 / 3 |
Total | 11 / 12 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 — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
Reviewed
Table of Contents