CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

review-fix-violations

Use when architecture violations were found and need automated fixing by priority.

Quality

74%

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

Fix and improve this skill with Tessl

tessl review fix ./packs/vue/skills/review-fix-violations/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

86%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 lean, highly actionable body with concrete fix directives, a copy-paste validation command, and a clear priority-ordered workflow. Only minor gaps — a couple of generic fix directives and no explicit failure-recovery loop — keep actionability and workflow clarity at 4.

DimensionReasoningScore

Conciseness

Every line is an instruction ('try/catch in services → remove, move error handling to composable') with no padding and no explanation of concepts Claude already knows. This matches anchor 5: lean, assumes competence, every token earns its place.

5 / 5

Actionability

Provides a copy-paste validation command ('npx tsc --noEmit && npx vite build && npx vitest run --passWithNoTests') and specific fix targets with delegation ('Options API → migrate to script setup (/migration-migrate-component)'). A few directives like 'any types → type correctly' and 'TODO/FIXME → resolve or create issue' remain generic, keeping it below anchor 5.

4 / 5

Workflow Clarity

Steps 1–4 are clearly sequenced with an explicit 'Validate after each fix' checkpoint, satisfying the destructive/batch-operation validation requirement (no cap applies). It falls short of anchor 5 only because there is no explicit error-recovery loop for what to do when validation fails.

4 / 5

Progressive Disclosure

The body is roughly 35 lines (under 50), organized into clear priority tiers, needs no external reference files (the bundle contains none), and only invokes sibling skills by name. This matches the simple-skill exception where well-organized sections alone warrant a 5.

5 / 5

Total

18

/

20

Passed

Description

53%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 has an explicit 'Use when' trigger and a specific niche, but it front-loads the 'when' and never states the 'what' as a standalone capability, and its keyword coverage is thin on synonyms and file anchors. It reads more as a trigger for a companion skill than a self-contained description.

Suggestions

Lead with a dedicated capability statement (e.g., 'Fixes docs/ARCHITECTURE.md violations in priority order: critical, important, improvements.') before the 'Use when' clause so the 'what' is explicit.

Add natural trigger synonyms and concrete anchors such as 'architecture review findings', 'ARCHITECTURE.md violations', or 'fix violations by priority' to broaden keyword coverage.

Name the concrete fix categories (error handling in services, v-html sanitization, hardcoded secrets, Options API migration) so capability coverage is comprehensive rather than a single action.

DimensionReasoningScore

Specificity

Names the domain ('architecture violations') and one concrete action ('automated fixing by priority') but lists no specific fix capabilities, matching the anchor-3 coverage level. It is not a 2 because the action is domain-tied with a mechanism rather than purely generic like 'Processes PDF files', and not a 4 because anchor 4 requires several specific actions.

3 / 5

Completeness

The 'when' is explicit ('Use when architecture violations were found'), but the 'what' is only embedded inside the trigger clause ('need automated fixing by priority') rather than stated as a dedicated capability statement like the anchor-4 example. It scores above anchor 2 because the trigger clause does convey a specific what.

3 / 5

Trigger Term Quality

'architecture violations', 'fixing', and 'priority' are natural terms a user would plausibly say, but common variations and synonyms ('architectural issues', 'fix the review findings', 'ARCHITECTURE.md violations') are absent. This fits anchor 3 (some relevant keywords, missing common variations) rather than anchor 4's good coverage.

3 / 5

Distinctiveness Conflict Risk

'architecture violations were found' presupposes a prior review and names a clear niche (automated fixing by priority), leaving only minor overlap risk with closely related review/fix skills. Not a 5 because no file or tool reference (e.g., ARCHITECTURE.md) further distinguishes it from neighboring skills.

4 / 5

Total

13

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository

fernandezbaptiste/specialist-agent

Path

packs/vue/skills/review-fix-violations/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.