CtrlK
BlogDocsLog inGet started
Tessl Logo

tessl/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.

75

Quality

94%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Risky

Do not use without reviewing

Overview
Quality
Evals
Security
Files

Quality

Content

85%

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 clear, actionable, well-sequenced workflow with concrete templates and validation checkpoints. Its only weakness is mild redundancy in the reminders section, which restates earlier constraints.

Suggestions

Remove or deduplicate the "Important reminders" bullets that restate Step 3 and Step 5 (every dimension id must appear, scores within scale range, schema conformance) to improve conciseness.

Consolidate the score-range and dimension-id requirements into a single statement near Step 3 instead of repeating them in the closing reminders.

DimensionReasoningScore

Conciseness

The body is largely efficient with exact paths and templates, but the "Important reminders" section restates constraints already given in Steps 3 and 5 (every dimension id must appear, scores within range, schema conformance), so it could be tightened. Not a 1 because there is no concept-explaining fluff; not a 3 because of the duplicated reminder content.

2 / 3

Actionability

Provides concrete, executable guidance — exact file paths, the precise JSON output shape with required fields, and explicit formulas like "sum(dimension.score * dimension.weight)". Not a 2 because the templates are complete and copy-paste ready rather than pseudocode.

3 / 3

Workflow Clarity

Five clearly sequenced steps with explicit validation checkpoints (schema conformance, score-range checks) and a feedback loop for the judge-failure branch ("set success: false and populate errorMessage"). Not a 2 because checkpoints are explicit rather than implicit.

3 / 3

Progressive Disclosure

Single self-contained, well-sectioned document with one-level-deep references (./rubrics/, ./config.json, ./references/, schemas/results.schema.json) that were verified to exist. Not a 2 because there is no inline wall of text or nested 2+ level reference chain.

3 / 3

Total

11

/

12

Passed

Description

100%

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 specific, complete, and uses an explicit third-person "Use when..." trigger with natural terms. It clearly defines both capability and activation context with minimal fluff.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "dynamically discovers the rubric files", "scores the skill against each", "producing one result per rubric" — matching the anchor for multiple specific concrete actions. It is not a 2 because the actions are comprehensive for the task rather than partial.

3 / 3

Completeness

Explicitly answers what ("dynamically discovers the rubric files and scores the skill against each, producing one result per rubric") and when via an explicit "Use when running a skill review workflow or testing skill quality against configurable rubrics" clause. Not a 2 because the trigger is explicit rather than implied.

3 / 3

Trigger Term Quality

Includes natural phrases a user would say — "skill review workflow", "testing skill quality", "against configurable rubrics" — giving good coverage. Not a 2 because common natural variations are present rather than only jargon.

3 / 3

Distinctiveness Conflict Risk

Targets a clear niche (skill-quality evaluation via rubric files) with distinct triggers unlikely to fire for unrelated skills. Not a 2 because it does not merely name a broad domain like "Works with document files".

3 / 3

Total

12

/

12

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