CtrlK
BlogDocsLog inGet started
Tessl Logo

vannifr/nfr-gap-audit

Use when running a systematic, self-directed skill-and-NFR audit on a website/web-app project — discovering skills from Tessl and VoltAgent, identifying non-functional-requirement gaps (performance, accessibility, security, SEO, testing, privacy, i18n, ...), and planning/implementing improvements in small, verified, committed phases. Trigger on "skill audit", "NFR audit", "audit this project for skills/gaps", "what skills am I missing", or before starting a multi-phase quality-improvement effort on a site.

75

Quality

94%

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

Overview
Quality
Evals
Security
Files

Quality

Content

85%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 content is a well-organized multi-phase audit workflow with strong sequencing, explicit verification gates, and clean progressive disclosure into real reference files. It is slightly verbose in places and a few baseline steps could be more copy-paste ready, but overall it is high quality.

Suggestions

Tighten rationale prose (e.g., 'because severity outranks domain', the privacy-exception explanation) into terser notes to lift conciseness toward the lean anchor.

Replace the high-level 'Run build, tests, lint, CSS/HTML validation, link check...' bullet with concrete per-stack command snippets to match the fully-executable anchor.

Consider a one-line table of contents mapping each phase to its reference file to make navigation even more explicit.

DimensionReasoningScore

Conciseness

The body is efficient and assumes Claude's competence (no basic concept explanations), but contains purposeful-yet-trimmable rationale prose such as 'because severity outranks domain' and the privacy-exception explanation, keeping it just below the lean anchor.

4 / 5

Actionability

Concrete, per-stack commands are given ('npx lighthouse <url> --output json', 'npx axe <url>', 'npm audit', 'pip-audit', 'pytest --cov', 'cargo audit', tessl_search examples) plus a baseline table template, but several steps remain at the 'run build, tests, lint...' level rather than fully copy-paste ready.

4 / 5

Workflow Clarity

Phases 0–6 are clearly sequenced and Phase 5 gives an explicit validation loop — 'Run tests', 'Verify the build', 'Check scores against the Phase 2 baseline — no regression allowed', 'Verify CI — all gates green before moving to the next change' — with feedback checkpoints, satisfying the top anchor and avoiding the destructive/batch cap.

5 / 5

Progressive Disclosure

The body is a clear overview pointing to five one-level-deep, clearly signaled reference files (nfr-domains.md, project-type-reference.md, skill-discovery-searches.md, gap-checklists.md, improvement-plan-template.md), all verified to exist; content is appropriately split and easy to navigate.

5 / 5

Total

18

/

20

Passed

Description

100%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 is a strong, model example: it states concrete capabilities, gives an explicit 'Use when' plus 'Trigger on' clause with natural phrasings, and carves out a distinct niche. It is concise yet comprehensive and does not over-claim.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'discovering skills from Tessl and VoltAgent', 'identifying non-functional-requirement gaps (performance, accessibility, security, SEO, testing, privacy, i18n, ...)', and 'planning/implementing improvements in small, verified, committed phases' — giving comprehensive coverage.

5 / 5

Completeness

Clearly answers both what (a systematic self-directed skill-and-NFR audit) and when (the 'Use when...' and 'Trigger on...' clauses with concrete trigger phrases), matching the top anchor.

5 / 5

Trigger Term Quality

An explicit 'Trigger on' clause supplies natural phrases a user would say — 'skill audit', 'NFR audit', 'audit this project for skills/gaps', 'what skills am I missing' — with several synonymous phrasings; the domain has no file extensions to cover.

5 / 5

Distinctiveness Conflict Risk

The 'skill-and-NFR audit' niche plus distinctive trigger phrases ('skill audit', 'NFR audit') make it unlikely to fire for unrelated skills; conflict risk is minimal.

5 / 5

Total

20

/

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.

Reviewed

Table of Contents