CtrlK
BlogDocsLog inGet started
Tessl Logo

disabled-skill

A skill with model invocation disabled

24

Quality

15%

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 ./tests/fixtures/sample-plugin/skills/disabled-skill/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 content is a one-line placeholder with no actionable guidance, workflow, or real structure; it scores well only on conciseness by accident of being empty. As written it does not function as skill content.

Suggestions

Replace "Disabled skill body." with concrete, executable guidance (specific commands or code examples) for the skill's intended task, which is the lowest-scoring actionability dimension.

Define the actual workflow steps the skill should perform, with validation checkpoints if any operation is destructive or batch-oriented, to address the floor-level workflow_clarity score.

Either populate the body with real, well-organized content or remove the skill, since the current stub conveys no usable information to Claude.

DimensionReasoningScore

Conciseness

The body "Disabled skill body." is maximally terse with zero padding and nothing to trim, so it clears the efficiency bar of anchor 4; it does not reach anchor 5 only because the lone placeholder token carries no meaningful, earned weight.

4 / 5

Actionability

The body provides no concrete code, commands, or executable guidance — it is a placeholder that only describes itself, matching the anchor 1 case of entirely vague content with no instructive steps.

1 / 5

Workflow Clarity

No steps or sequence are present at all; the simple-skill exception requires an unambiguous single action, but here there is no described action, matching the anchor 1 case of steps missing.

1 / 5

Progressive Disclosure

The body has no organizing structure or sections, but as a one-line stub it contains no content that needs splitting into external files and nothing to navigate, so it neither fails (no monolithic wall or nested references) nor meets the well-organized-overview bar of anchor 5.

3 / 5

Total

9

/

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 meta-statement about the skill's configuration rather than a statement of what it does or when to use it, so it fails all four dimensions at the floor. It conveys no actionable capability, no user-facing triggers, and no distinct niche.

Suggestions

Rewrite the description to state concrete actions the skill performs (e.g., what it processes or produces) instead of the configuration property "model invocation disabled".

Add a "Use when..." clause with natural keywords users would actually say so Claude knows when to invoke it.

Name the skill's specific task domain so it is distinguishable from other skills and does not conflict on generic triggers.

DimensionReasoningScore

Specificity

The description "A skill with model invocation disabled" names no concrete actions — it describes a configuration property (disable-model-invocation) rather than any capability the skill performs, matching the anchor 1 example of pure abstract language.

1 / 5

Completeness

It answers neither "what does this do" (it states a config flag, not a function) nor "when should Claude use it", with no "Use when..." trigger clause, matching the anchor 1 case of both what and when missing/extremely vague.

1 / 5

Trigger Term Quality

"model invocation" is meta-configuration jargon about the skill's runtime, not a natural keyword a user would say when needing this skill; no natural trigger phrases are present, matching anchor 1.

1 / 5

Distinctiveness Conflict Risk

Naming no task domain, the description is entirely generic about capability and would be indistinguishable from any other skill, matching the anchor 1 example of something that conflicts with virtually any skill.

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
EveryInc/compound-engineering-plugin
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.