CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

coverage-check

Audits an already-written use case (UC-XXX) or test case (TC-XXX) against its specification and reports a coverage matrix: which main success scenario steps, alternative flows, business rules, preconditions, and postconditions have code and tests behind them, which are still open, and which code or tests have drifted away from the specification. Use when the user asks to "check coverage", "run a coverage check", "is UC-001 fully implemented", "is UC-001 completely tested", "audit the use case", "show me the coverage matrix", "do a traceability check", "what is still missing for UC-001", or "can I set the status to Tested". This is specification coverage, not line coverage from a coverage report. It reports only — it writes no code, no tests, and no files. When the user wants the gaps closed rather than listed, use /implement, /implement-hilla, /browserless-test, /hilla-test, /karibu-test, or /playwright-test instead.

Quality

97%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is ai-unified-process/aiup-vaadin-jooq

SKILL.md
Quality
Evals
Security

Quality

Content

92%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 tightly engineered delegation skill: concrete parsing rules, exact delegation payloads, explicit stop-and-ask validation checkpoints, and textbook progressive disclosure that keeps the audit checklist in a single referenced file to prevent drift. The only cost is a handful of rhetorical asides that could be trimmed for token efficiency.

DimensionReasoningScore

Conciseness

The body never explains concepts Claude already knows and every section carries rules, but a handful of rhetorical flourishes could be trimmed — 'Silently narrowing to implementation recreates the very gap this skill exists to close', 'is what sends /spec-review and /coverage-check round in circles', 'is the fastest way to turn an audit into a rubber stamp'. This is anchor 4 (efficient, minor over-explanation); not 5 because not every token is load-bearing, and clearly not 3 since nothing is unnecessary in bulk.

4 / 5

Actionability

Fully concrete, copy-paste-ready instruction guidance: an argument token table with normalization rules, exact delegation payloads ('UC-001 both', 'UC-001 implementation work in progress'), exact path/glob patterns ('docs/use_cases/**/UC-XXX-*.md', '**/agents/uc-coverage.md'), per-gap-type commands, and a ready-to-emit '### Since the last run' markdown template. As an instruction-only skill, the absence of code is not penalized; this matches anchor 5.

5 / 5

Workflow Clarity

Six sequenced steps with explicit validation checkpoints: verify the specification exists and 'Stop and ask if it does not' (with near-match listing), state resolved arguments in one line before delegating so a wrong parse costs one rerun, present the report unchanged, and add a comparison on repeated runs. The batch sweep operation has full guardrails — pre-pass first, publish the triage table, cap of five full audits, and 'Ask before exceeding the cap, naming the number' — so the batch-operation cap does not apply. Anchor 5's explicit-validation and feedback-loop pattern is met.

5 / 5

Progressive Disclosure

The skill is deliberately a front door: the audit checklist 'lives in agents/uc-coverage.md ... and is deliberately not repeated here', a single well-signaled one-level-deep reference with navigation instructions (a glob for hosts that do not expose the plugin root, plus an inline fallback section). No bulk content is inlined that belongs elsewhere, and sections are clearly headed. This matches anchor 5's clear-overview-plus-referenced-detail pattern.

5 / 5

Total

19

/

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.

An exemplary description: concrete third-person capability statement, comprehensive verbatim trigger phrases, explicit what/when, and deliberate disambiguation against both line-coverage tooling and sibling gap-closing skills. Long, but every clause is load-bearing — no fluff to trim.

DimensionReasoningScore

Specificity

Multiple concrete actions with comprehensive coverage: 'Audits an already-written use case (UC-XXX) or test case (TC-XXX) against its specification and reports a coverage matrix' enumerating 'main success scenario steps, alternative flows, business rules, preconditions, and postconditions', which are 'open', and which 'drifted away from the specification'. It sits at the anchor-5 example's level; no action in the skill's domain is missing, so 4's 'minor gaps' does not apply.

5 / 5

Completeness

Explicitly answers 'what' ('Audits ... and reports a coverage matrix ... It reports only — it writes no code, no tests, and no files') and 'when' with an explicit 'Use when the user asks to ...' clause listing concrete trigger phrases, plus boundary disambiguation ('specification coverage, not line coverage') and routing to /implement-style skills for gap closing. This is the anchor-5 pattern exactly; the 'when' is as explicit as it can be, so 4 does not fit.

5 / 5

Trigger Term Quality

Full-sentence natural user utterances are quoted verbatim as triggers — 'check coverage', 'is UC-001 fully implemented', 'audit the use case', 'show me the coverage matrix', 'do a traceability check', 'what is still missing for UC-001', 'can I set the status to Tested' — covering synonyms (coverage check / traceability check / audit). Matches anchor 5's comprehensiveness; 4's 'a few natural terms missing' would understate the coverage.

5 / 5

Distinctiveness Conflict Risk

Clear niche (specification-coverage auditing keyed to UC-XXX/TC-XXX identifiers) with distinct triggers, and active conflict prevention: 'This is specification coverage, not line coverage from a coverage report' and 'When the user wants the gaps closed rather than listed, use /implement, /implement-hilla, ... instead'. Minimal conflict risk per anchor 5.

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.

Repository

AI-Unified-Process/marketplace

Path

aiup-vaadin-jooq/skills/coverage-check/SKILL.md

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.