CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

a

First 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/a/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

47%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 carries no actionable content — a single vacuous step that tells Claude nothing about what to actually do. It scores well only on token efficiency and adequate structure; actionability and workflow clarity are at the bottom of the scale.

Suggestions

Replace "Do the first thing." with concrete, executable guidance — specific commands, code, or a precisely defined instruction.

If the task has multiple steps, list the full sequence with explicit validation checkpoints where things can fail.

Keep the current brevity while ensuring each line conveys real, specific instructions rather than placeholders.

DimensionReasoningScore

Conciseness

The body is a single heading ("# Skill A") plus one step ("1. Do the first thing.") — nothing padded, no concepts explained, no wasted tokens. Every token present is as lean as the anchor-5 standard; the thinness is an actionability problem, not a verbosity one.

5 / 5

Actionability

"Do the first thing." is entirely vague and abstract — no code, no commands, no specifics about what 'the first thing' is. It matches anchor 1 ("only describes rather than instructs" with nothing concrete to execute).

1 / 5

Workflow Clarity

A numbered step exists, so a rudimentary sequence is present (keeping it above anchor 1's "steps missing"), but the single step is vacuous and poorly defined, matching anchor 2's "steps poorly defined". The simple-skill exception for a 5 does not apply because the action is ambiguous, and no validation is required since nothing risky is described.

2 / 5

Progressive Disclosure

The skill is under 50 lines with no bundle files (no references/, scripts/, or assets/ exist) and no external references are needed, so nothing is inlined that belongs elsewhere. Structure (heading + step) is appropriate for its scale, but the near-empty body keeps it below the anchor-5 bar of genuinely well-organized sections.

4 / 5

Total

12

/

20

Passed

Description

17%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 pure fixture metadata: it documents the skill's role in a test repo rather than any capability a user or Claude could act on. It contains no natural trigger terms, no "Use when..." guidance, and no concrete actions, scoring at or near the bottom on all four dimensions.

Suggestions

Replace the fixture/meta language with 2-3 concrete capability actions the skill actually performs (e.g., 'Extracts X from Y, then Z') in third person.

Add an explicit trigger clause, e.g., 'Use when the user mentions <natural phrases users would say>'.

Include natural keywords, synonyms, and relevant file extensions so the skill is discoverable and distinguishable from sibling skills.

DimensionReasoningScore

Specificity

The description states only meta-context — "First skill in the multi-skill fixture repo, used to test fan-out validation" — with no concrete user-facing capability actions at all. The language itself is concrete rather than pure abstraction (above anchor 1), but it names zero capability actions, so it cannot reach anchor 3's "1-2 concrete actions".

2 / 5

Completeness

A vague meta 'what' is present (being the first skill in a fixture repo) but it does not state what the skill actually does for a user, and there is no 'when' guidance at all — no "Use when..." clause or equivalent. This matches anchor 2 (vague what, no when) rather than anchor 1, since some explicit statement of purpose exists.

2 / 5

Trigger Term Quality

The only terms present are internal/technical jargon ("multi-skill fixture repo", "fan-out validation") that no user would naturally say when they need this skill. There are no natural keywords or synonyms whatsoever, matching the anchor-1 example style "Handles document object model manipulation".

1 / 5

Distinctiveness Conflict Risk

The description is nearly indistinguishable from sibling fixture skills (e.g., a hypothetical "Second skill in the multi-skill fixture repo, used to test X"), creating high overlap risk with any similar fixture entry. It is not entirely generic (above anchor 1) but offers no distinct user-facing triggers, so it cannot reach anchor 3.

2 / 5

Total

7

/

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/a/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.