CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

b

Second skill in the multi-skill fixture repo, used to test fan-out validation.

Quality

46%

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 ./test/fixtures/agentskills-repo/skills/b/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

45%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 maximally lean but substantively empty: it names an undefined 'second thing' with no concrete guidance, executable steps, or validation. Structure is trivially fine for a skill this small, but the content gives Claude nothing to act on.

Suggestions

Replace 'Do the second thing' with the actual concrete task, including specific commands or executable guidance for it.

If the task involves multiple steps or any destructive/batch operation, list the sequence explicitly with validation checkpoints.

For a genuine single-step skill, state the one action unambiguously so workflow clarity qualifies for the simple-skill exception.

DimensionReasoningScore

Conciseness

The body is three lines with zero padding, zero explanation of concepts Claude already knows, and no wasted tokens — 'every token earns its place' in the lean-and-efficient anchor. Emptiness is penalized under actionability and workflow clarity, not here, since this dimension measures token efficiency of what is written.

5 / 5

Actionability

"Do the second thing" refers to an action that is never defined anywhere; there is no code, command, or specific guidance — vaguer even than the anchor-1 example 'Use a PDF library to extract the text content'. It only gestures at an instruction without instructing, so score 2's 'high-level hints' is still too generous.

1 / 5

Workflow Clarity

The single step is incoherent because 'the second thing' is undefined, and no validation or checkpoints exist. The simple-skill exception allows a 5 only when the single action is unambiguous; here the one step present fails to communicate any actionable sequence, matching 'steps missing or incoherent'.

1 / 5

Progressive Disclosure

The skill is under 50 lines, no bundle directories (references/, scripts/, assets/) exist, nothing that belongs in a separate file is inlined, and there are no nested references. Per the simple-skill guideline, a body this small with a clear header and organized line meets the structure bar with nothing to disclose progressively.

5 / 5

Total

12

/

20

Passed

Description

21%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 fixture's purpose in the test harness rather than any capability a user or Claude would invoke. It lacks both a concrete statement of what the skill does and any 'when to use' trigger guidance. As a deployable skill description it would essentially never be selected appropriately.

Suggestions

State concrete user-facing actions in third person (e.g., what task the skill performs) instead of describing the fixture's role in the test repo.

Add an explicit 'Use when...' clause with natural trigger phrases users would actually say when they need this skill.

Replace meta-language like 'Second skill in the multi-skill fixture repo' with capability keywords that distinguish this skill from its siblings.

DimensionReasoningScore

Specificity

"Used to test fan-out validation" names a domain (test infrastructure) but lists no user-facing actions or capabilities whatsoever, matching the anchor 'names the domain but actions are minimal or generic'. It is not pure abstract filler like 'Helps with documents' (score 1), but it never says what the skill actually does for a user.

2 / 5

Completeness

The description provides only a vague meta-level 'what' ("used to test fan-out validation" — what the fixture is for, not what the skill does) and contains no 'when to use' clause or trigger guidance at all, matching anchor 2 ('has a vague what and no when'). A clear user-facing 'what' is absent, so it cannot reach 3.

2 / 5

Trigger Term Quality

The only keywords are technical jargon ("multi-skill fixture repo", "fan-out validation") that no user would naturally say when they need this skill, matching the anchor 'no natural keywords; only technical jargon'. There are no capability terms, synonyms, or file extensions that would ever match a real request.

1 / 5

Distinctiveness Conflict Risk

"Fan-out validation" names a narrow niche with minimal trigger overlap, but "Second skill in the multi-skill fixture repo" is a positional label that would be near-indistinguishable from sibling fixture skills, so distinctiveness rests on context rather than capability — somewhat specific but still overlapping.

3 / 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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

saif-shines/doraval

Path

test/fixtures/agentskills-repo/skills/b/SKILL.md

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.