CtrlK
BlogDocsLog inGet started
Tessl Logo

tessleng/default-skill-review

The default Tessl review rubric. An agentic reviewer that reads a SKILL.md and scores it against rubrics for its description and its content, the same reviewer tessl review uses out of the box. Use it as the reference reviewer to score skills, or as the base to fork a custom rubric from.

68

Quality

85%

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

Overview
Quality
Evals
Security
Files

Quality

Content

75%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 highly actionable, clearly sequenced workflow with exact templates and formulas. Its main weakness is mild verbosity from a reminders section that recapitulates earlier constraints, and the absence of an explicit final validation checkpoint.

Suggestions

Remove or trim the 'Important reminders' section, since each bullet already appears in Steps 3 and 5, to reduce redundancy.

Add an explicit final validation step (e.g., 'Validate results.json against schemas/results.schema.json before finishing') to close the workflow with a checkpoint.

Consolidate the repeated 'every dimension id must appear in scores' and 'scores must be within scale.min–scale.max' notes into a single location.

DimensionReasoningScore

Conciseness

The body is mostly efficient and well-structured, but the closing 'Important reminders' section repeats constraints already stated in Steps 3 and 5 (every dimension must appear, scores within range, valid JSON), which could be tightened.

3 / 5

Actionability

It gives exact file paths, JSON output templates, and explicit formulas for weightedScore and normalizedScore — fully executable, copy-paste-ready guidance with no pseudocode.

5 / 5

Workflow Clarity

Steps 1–5 are clearly sequenced with explicit sub-steps and an error-recovery path ('If a judge fails... set success: false'), but there is no explicit final validation checkpoint confirming the output conforms before finishing.

4 / 5

Progressive Disclosure

Content is well-organized under clearly labeled section headers with no nested references and no monolithic wall of text; being self-contained and over 50 lines, it stops just short of the level-5 bar that assumes minimal content or well-signaled external references.

4 / 5

Total

16

/

20

Passed

Description

87%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 clearly names the skill's purpose, lists concrete actions, and provides an explicit 'Use when...' trigger with natural keywords. Minor gaps in trigger-term synonyms keep it just below a perfect mark on two dimensions.

DimensionReasoningScore

Specificity

Quotes 'dynamically discovers the rubric files', 'scores the skill against each', and 'producing one result per rubric' — several concrete actions, but not the comprehensive coverage of a level-5 example.

4 / 5

Completeness

It clearly states what it does ('Evaluate a SKILL.md for quality... scores the skill against each') and gives an explicit 'Use when running a skill review workflow or testing skill quality against configurable rubrics' trigger, answering both what and when with concrete phrases.

5 / 5

Trigger Term Quality

Natural terms like 'skill review workflow', 'skill quality', and 'configurable rubrics' are present and would be said by users, but synonyms/file extensions are missing, so it falls short of level 5.

4 / 5

Distinctiveness Conflict Risk

It targets a clear niche (skill-quality review against configurable rubrics) with distinct triggers, making conflict with other skills unlikely.

5 / 5

Total

18

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Reviewed

Table of Contents