CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

my-skill

A test skill for fixture purposes

Quality

38%

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/claude-plugin/good/skills/my-skill/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 and appropriately self-contained (no external files needed or present), but it contains no actionable guidance and no workflow whatsoever — it is a content-free placeholder. It scores at the bottom on actionability and workflow clarity while earning full marks on conciseness and progressive disclosure simply because there is almost nothing to evaluate.

Suggestions

Add at least one concrete, executable instruction (specific command, code snippet, or step-by-step guidance) so the skill tells Claude what to actually do.

If the skill involves any multi-step or risky process, sequence the steps explicitly and include a validation/verification checkpoint.

Describe the skill's purpose and expected inputs/outputs in the body so the guidance is actionable rather than a bare label.

DimensionReasoningScore

Conciseness

The body is a single heading ("# My Skill") plus one sentence ("This is a test skill.") with zero padding, no concept explanations, and nothing that could be trimmed. It matches anchor 5 ("Lean and efficient; every token earns its place"); anchor 4 would require some over-explanation to cut, and there is none.

5 / 5

Actionability

The body provides no code, no commands, and no steps — it only describes ("This is a test skill.") rather than instructs. This matches anchor 1 ("Entirely vague or abstract; no concrete code or commands; only describes rather than instructs"); even anchor 2 expects at least high-level directional hints.

1 / 5

Workflow Clarity

There is no sequence, no steps, and no single unambiguous action to follow, so the simple-skill exception (score 5 for a clear single action) does not apply — there is no action at all. This matches anchor 1 ("Steps missing or incoherent; no sequence"); no destructive/batch operation exists, so the validation cap is not the binding constraint.

1 / 5

Progressive Disclosure

The body is under 50 lines, no bundle files exist (no references/, scripts/, or assets/ directories), and nothing needs to be split out, so per the rubric's guideline for short self-contained skills a well-organized body scores 5. The single heading and one line constitute adequate organization for content this size; there are no buried or nested references to penalize.

5 / 5

Total

12

/

20

Passed

Description

0%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 fails every dimension: it names no concrete capability, includes no natural trigger terms, answers neither 'what does this do' nor 'when should it be used', and is completely indistinguishable from other skills. It matches the rubric's bad_overall_examples class ("Helps with documents") or worse.

Suggestions

Replace the meta-statement with concrete third-person actions describing what the skill actually does (e.g., "Extracts X from Y, generates Z").

Add an explicit trigger clause such as "Use when the user mentions ..." naming the natural keywords, file types, or synonyms a user would actually say.

State the skill's niche scope so it is distinguishable from neighboring skills and unlikely to fire for unrelated requests.

DimensionReasoningScore

Specificity

The description is only "A test skill for fixture purposes" — pure meta-language with no concrete action and no working domain, matching anchor 1 ("Entirely vague; no concrete actions; pure abstract language"). Anchor 2 requires at least a named domain (e.g., "Processes PDF files"), which this lacks.

1 / 5

Completeness

The description states what the file IS ("A test skill for fixture purposes") but conveys no capability (no "what it does") and has no "Use when..." or equivalent trigger clause, so both halves are effectively missing. This matches anchor 1 ("Missing both what and when, or both are extremely vague") rather than anchor 2, whose example at least carries an explicit 'when'.

1 / 5

Trigger Term Quality

No natural user keywords appear anywhere; "test skill" and "fixture purposes" are meta/technical jargon no user would say when needing a capability. This fits anchor 1 ("No natural keywords; only technical jargon or entirely generic language"), not anchor 2, which expects at least one or two generic keywords.

1 / 5

Distinctiveness Conflict Risk

"A test skill for fixture purposes" contains no domain, capability, or trigger information, making it entirely generic and indistinguishable from any other placeholder skill. This is anchor 1 ("Entirely generic; would conflict with virtually any skill"); anchor 3+ requires at least some specific scope.

1 / 5

Total

4

/

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/claude-plugin/good/skills/my-skill/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.