CtrlK
BlogDocsLog inGet started
Tessl Logo

skill-check

Validate Claude Code skills against the agentskills specification. Catches structural, semantic, and naming issues before users do.

54

Quality

61%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/skill-check/SKILL.md

The canonical home for this skill is skill-check in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

60%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 skill is well-structured with a clear workflow and useful examples, but it under-specifies the actual validation rules (only labels them) and carries marketing padding for the paid tier. Defining the checks concretely and trimming upsell content would materially improve actionability and conciseness.

Suggestions

Replace the category labels in the checks table with concrete pass/fail rules (e.g., "1.2: description must contain a WHEN clause; flag if absent") so Claude can execute each check unambiguously.

Remove or de-emphasize the repeated SkillCheck Pro upsell mentions from the When-to-Use and Limitations sections to reduce token noise.

Move the worked Examples and/or Common Pitfalls into a references file (EXAMPLES.md) and link to it, keeping SKILL.md as a lean overview.

DimensionReasoningScore

Conciseness

The body is well-sectioned and mostly efficient, but repeated "SkillCheck Pro" upsell references (When-to-Use and Limitations) are marketing padding that doesn't help Claude act. Not a 4 because the upsell content is genuine noise.

3 / 5

Actionability

The 4-step process and scoring penalties (−20/−5/−1) are concrete, but the checks table only labels categories without defining the actual validation rules, leaving Claude to infer how to evaluate each rule. Missing key details caps this at 3.

3 / 5

Workflow Clarity

A clear numbered sequence (Parse→Validate→Score→Report) with a checks table acting as a checklist and a "re-run after fixes" feedback loop in Best Practices. Not a 5 because Step 2 lacks explicit per-check validation checkpoints.

4 / 5

Progressive Disclosure

Self-contained with well-signaled section headers and no nested references; single-file organization is appropriate. Not a 5 because at ~95 lines it exceeds the under-50-line simple-skill exception and the Examples/Pitfalls could live in reference files.

4 / 5

Total

14

/

20

Passed

Description

62%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 clearly states what the skill does and carves out a distinct, low-conflict niche, but it omits any explicit trigger guidance and leans on a few generic keywords rather than the natural phrases a user would say. Adding a "Use when..." clause with concrete trigger phrases would lift completeness and trigger-term quality.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user says 'check skill', 'skillcheck', or 'validate SKILL.md', or before publishing a skill to a marketplace."

Add natural synonyms users actually say ("check skill", "skillcheck", "lint a skill") to improve trigger-term coverage.

Mention the scoring/grading output (0–100, grade) to round out the capability list.

DimensionReasoningScore

Specificity

"Validate Claude Code skills against the agentskills specification" and "Catches structural, semantic, and naming issues" list several concrete actions over a named domain. Not a 5 because coverage isn't comprehensive (no mention of scoring/grading the body advertises).

4 / 5

Completeness

The "what" is clear (validate skills, catch structural/semantic/naming issues) but there is no "Use when..." clause or equivalent trigger guidance, so per the boundary guidance completeness is capped at 3.

3 / 5

Trigger Term Quality

Contains "Validate", "skills", "agentskills" but omits natural user phrases like "check my skill" or "skillcheck" and common synonyms. Falls between anchor 3 and 4 but the missing everyday phrasings pull it down to 3.

3 / 5

Distinctiveness Conflict Risk

The niche is narrow and specific — validating skills against a particular spec — so it is clearly distinguishable from other skills with minimal conflict risk.

5 / 5

Total

15

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.