CtrlK
BlogDocsLog inGet started
Tessl Logo

rich-skill

A skill with code blocks and imperative instructions for testing content and contamination analysis.

41

Quality

41%

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 ./crates/skill-validator-rs/tests/golden-corpus/fixtures/testdata/rich-skill/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%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 compact and cleanly sectioned with some executable code, but much of the prose is vague or hedged rather than instructive, and the workflow's steps lack commands and validation checkpoints. It reads as filler-rich test content rather than operational guidance. Structure is appropriate for a skill this size.

Suggestions

Replace hedged filler ('You may consider...', 'This is optional but suggested') with a single direct statement of the recommended configuration.

Attach concrete commands to each workflow step, e.g. an actual migration command and schema-validation command instead of 'Run migrations' / 'Validate the schema'.

Resolve the vague stack guidance ('Build the project with Node.js or Django depending on your stack') into specific, complete instructions per stack, and add an explicit validate-before-deploy checkpoint.

DimensionReasoningScore

Conciseness

Hedging filler such as 'You may consider using a .env file. It could simplify local development. This is optional but suggested' and 'Use the CLI to configure your environment. Install the required dependencies.' adds unnecessary tokens, though the code blocks themselves are lean.

3 / 5

Actionability

Executable snippets exist (npm install, MongoClient connection code) but key steps are vague or contradictory ('Run migrations', 'Build the project with Node.js or Django depending on your stack') with no commands, leaving guidance incomplete.

3 / 5

Workflow Clarity

A four-step sequence is listed and validation is mentioned ('Validate the schema', 'Run the tests before deploying') but no step includes commands or explicit checkpoints; per the rubric, database operations without explicit validation feedback loops are capped at 3.

3 / 5

Progressive Disclosure

The skill is under 50 lines with no bundle files and no content warranting external references, and its Setup/Usage/Configuration sections are well-organized, satisfying the simple-skill exception.

5 / 5

Total

14

/

20

Passed

Description

25%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 describes the skill file's composition rather than what the skill does for a user or when it should trigger. It lacks concrete actions, natural trigger terms, and any 'Use when' clause, making it nearly indistinguishable from other skills. This reads as an internal test artifact label, not a functional skill description.

Suggestions

Rewrite the description around concrete user-facing capabilities in third person (e.g., 'Performs X and Y on Z'), replacing the meta-description of the file's contents.

Add an explicit 'Use when...' clause naming the situations or user phrases that should trigger this skill.

Include natural trigger terms and synonyms (including relevant file extensions or tool names) that a user would actually say when they need this skill.

DimensionReasoningScore

Specificity

The description names a domain ('testing content and contamination analysis') but describes the skill artifact ('code blocks and imperative instructions') rather than any concrete user-facing action, matching the anchor for minimal or generic actions.

2 / 5

Completeness

It offers only a vague 'what' (what the file contains, not what it does) and entirely omits any 'when to use' guidance, matching the anchor for a vague 'what' with no 'when'.

2 / 5

Trigger Term Quality

Terms like 'code blocks', 'imperative instructions', and 'contamination analysis' are meta-descriptions of the file, not natural phrases a user would say when needing this skill; only generic keywords are present.

2 / 5

Distinctiveness Conflict Risk

Generic words like 'skill', 'code blocks', and 'instructions' would overlap with virtually any other skill description, giving high conflict risk.

2 / 5

Total

8

/

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.

Repository
pantheon-org/tekhne
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.