CtrlK
BlogDocsLog inGet started
Tessl Logo

skill-judge

Evaluate Agent Skill design quality against official specifications and best practices. Use when reviewing, auditing, or improving SKILL.md files and skill packages. Provides multi-dimensional scoring and actionable improvement suggestions.

79

1.61x
Quality

70%

Does it follow best practices?

Impact

100%

1.61x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./dist/plugins/skill-judge/skills/skill-judge/SKILL.md

The canonical home for this skill is skill-judge in softaworks/agent-toolkit

SKILL.md
Quality
Evals
Security

Quality

Content

56%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 body is a well-instrumented meta-skill with strong actionability and a clear evaluation workflow, but it is significantly over-long and explains foundational concepts Claude already knows, hurting token efficiency. Splitting the rubric details, failure-pattern catalog, and quick-reference checklist into references/ files would materially improve progressive disclosure.

Suggestions

Trim or move foundational exposition ("What is a Skill", training-vs-educating analogy, token-waste philosophy) since Claude already knows this; keep only the non-obvious evaluation criteria.

Move the detailed D1-D8 rubric anchors, the Common Failure Patterns catalog, and the Quick Reference Checklist into separate files under references/ and load them on demand to cut the ~750-line body well under 300 lines.

Replace implicit checkpoints in the Evaluation Protocol with explicit pass/fail validation gates (e.g., "only proceed to scoring once the E:A:R ratio is computed") to strengthen workflow clarity.

DimensionReasoningScore

Conciseness

At ~750 lines the body is noticeably verbose, re-explaining concepts Claude largely knows (what a Skill is, training-vs-educating analogies, token-waste philosophy) and padding with repeated ASCII diagrams and checklists, matching the anchor for several unnecessary padded sections.

2 / 5

Actionability

Provides concrete, usable evaluation instruments (D1-D8 rubrics with point anchors, an evaluation protocol, a report template, decision trees) that an evaluator can apply directly, with only minor gaps, fitting the "mostly actionable" anchor for an instruction-only skill.

4 / 5

Workflow Clarity

The Evaluation Protocol lays out a clear sequenced Steps 1-5 (Knowledge Delta Scan, Structure Analysis, Score, Calculate, Generate Report); checkpoints are mostly present though somewhat implicit rather than enforced, matching the "clear sequence with minor validation gaps" anchor.

4 / 5

Progressive Disclosure

The skill is self-contained with no bundle files, but ~750 lines of inlined rubrics, failure patterns, and a quick-reference checklist are content that should be split into reference files; structure is present but monolithic, matching the "some structure, content that should be separate is inline" anchor.

3 / 5

Total

13

/

20

Passed

Description

83%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 strong: it states concrete capabilities, gives an explicit "Use when..." trigger, and is clearly scoped to Agent Skill design quality. Its only weakness is slightly limited natural-keyword variation, which keeps trigger term quality and distinctiveness at 4 rather than 5.

DimensionReasoningScore

Specificity

Lists several concrete actions ("Evaluate", "reviewing, auditing, or improving", "multi-dimensional scoring and actionable improvement suggestions") with only minor coverage gaps, matching the anchor for several specific actions.

4 / 5

Completeness

Clearly answers WHAT (evaluate Skill design quality, multi-dimensional scoring, suggestions) and an explicit WHEN ("Use when reviewing, auditing, or improving SKILL.md files and skill packages"), matching the anchor that requires concrete trigger phrases for both.

5 / 5

Trigger Term Quality

Natural phrases like "reviewing, auditing, or improving SKILL.md files and skill packages" give good keyword coverage, though a few natural synonyms a user might say (e.g. "skill quality", "lint a skill", "rate a skill") are missing.

4 / 5

Distinctiveness Conflict Risk

The "SKILL.md files and skill packages" niche is mostly distinct with only minor overlap risk against generic code-review skills, fitting the "mostly distinct" anchor rather than a fully clear niche.

4 / 5

Total

17

/

20

Passed

Validation

81%

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

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (753 lines); consider splitting into references/ and linking

Warning

relative_links

Relative link issues: 1 missing

Warning

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

13

/

16

Passed

Repository
softaworks/agent-toolkit
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.