CtrlK
BlogDocsLog inGet started
Tessl Logo

skill-alpha

A valid skill for multi-skill testing.

28

Quality

19%

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/multi-skill/skill-alpha/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

30%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 token-efficient but substantively empty — it describes nothing the skill actually does and offers no executable guidance or workflow. The one reference link is correctly structured but points to a stub file, so progressive disclosure is present in form only.

Suggestions

State the skill's actual procedure concretely (steps, commands, or decision rules) instead of the meta sentence about demonstrating a valid skill.

If the skill has any multi-step or batch/destructive operation, add an explicit sequence with a validation checkpoint; otherwise at minimum describe the single task unambiguously.

Populate references/guide.md with the promised step-by-step instructions so the referenced path delivers content, and drop or replace the meta 'demonstrates a valid skill' sentence.

DimensionReasoningScore

Conciseness

The body is extremely lean with no padding or explanations of known concepts, but "This skill demonstrates a valid skill inside a multi-skill directory" is unnecessary meta-explanation that does not earn its tokens. It is not 5 because that sentence could be cut without losing anything, and not 3 because there is no verbosity beyond it.

4 / 5

Actionability

The body only describes the skill's purpose ("demonstrates a valid skill inside a multi-skill directory") and points to a reference 'for details'; it provides no concrete steps, commands, or guidance, matching the anchor 'Entirely vague or abstract; no concrete code or commands'. It cannot score 2 because not even high-level actionable hints are given.

1 / 5

Workflow Clarity

There are no steps or sequence of any kind in the body, matching the anchor 'Steps missing or incoherent; no sequence'. It does not score 2 because even a rough incomplete sequence is absent.

1 / 5

Progressive Disclosure

The single reference "[reference guide](references/guide.md)" is clearly signaled, one level deep, and resolves to a real bundle file, but the split is superficial: the body has no overview content and references/guide.md is a near-empty stub ("Step-by-step instructions for skill-alpha." with no steps), so navigation leads nowhere. This fits 'some structure but could be better organized' rather than 4, whose referenced content actually carries the payload.

3 / 5

Total

9

/

20

Passed

Description

8%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 a placeholder that describes the skill's role in a test fixture rather than any capability. It fails to say what the skill does or when to use it, and contains no trigger terms, making it unusable for skill selection.

Suggestions

Replace the meta statement with concrete capabilities written in third person (e.g., 'Validates SKILL.md structure and scores skills against rubric files'),

Add an explicit 'Use when...' clause naming the natural phrases a user would say that should trigger this skill.

Include natural trigger keywords and synonyms (including file extensions if applicable) so the skill is distinct from and does not collide with other validation or testing skills.

DimensionReasoningScore

Specificity

"A valid skill for multi-skill testing" contains no concrete actions and is pure abstract meta-language, exactly matching the anchor 'Entirely vague; no concrete actions'. It does not score 2 because it does not even name a real domain or a minimal generic action like 'Processes PDF files'.

1 / 5

Completeness

A vague 'what' is present ("A valid skill for multi-skill testing") but no 'when' clause or trigger guidance exists, matching the anchor 'Has a vague "what" and no "when"'. It is not 1 because a 'what' is stated, and not 3 because the 'when' is absent rather than weakly implied.

2 / 5

Trigger Term Quality

"multi-skill testing" is meta jargon about skill packaging, not a phrase a user would naturally say when needing this skill; there are no natural keywords at all. It cannot score 2 because not even one generic user-facing keyword is present.

1 / 5

Distinctiveness Conflict Risk

The description is entirely generic meta-commentary with no differentiating capability or triggers, so it is indistinguishable from any placeholder skill and would conflict with virtually any other skill. It does not score 2 because there is no broad-but-real domain like 'document files' to create meaningful overlap.

1 / 5

Total

5

/

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.