disabled-skill

A skill with model invocation disabled

Quality

16%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

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

The canonical home for this skill is disabled-skill in EveryInc/compound-engineering-plugin

Quality

Content

33%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 trivially concise but contains no actionable guidance, no workflow, and no structure — it is a placeholder rather than a functioning skill body. Its only virtue is that it wastes no tokens.

Suggestions

Add concrete, executable guidance (commands, code, or specific instructions) so the body instructs rather than merely describes — actionability is at floor.

If the skill has any real workflow, sequence it as numbered steps with validation checkpoints; even a single-step skill should state the one action unambiguously.

Organize content into headed sections (e.g., '## Quick start') and split any detail material into one-level-deep reference files instead of leaving a bare placeholder line.

Dimension	Reasoning	Score
Conciseness	The body ('Disabled skill body.') is three words with zero padding and no explanation of concepts Claude already knows — maximally lean, matching the 'every token earns its place' anchor. Nothing can be trimmed because nothing is over-explained.	5 / 5
Actionability	'Disabled skill body.' provides no code, no commands, and no concrete steps — it only describes a state rather than instructing, matching the 'entirely vague or abstract; only describes rather than instructs' anchor.	1 / 5
Workflow Clarity	There is no sequence of steps whatsoever, matching the 'steps missing or incoherent; no sequence' anchor. No destructive or batch operations are present, so the validation-cap rule is moot; the score is already at floor.	1 / 5
Progressive Disclosure	The body has no headers, no references, and no bundle files exist (references/, scripts/, assets/ are all absent), leaving minimal structure. It is not a monolithic wall of text or nested-reference chain (anchor 1), and the simple-skill exception does not apply because the content is not organized into sections at all.	2 / 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 configuration metadata, not a capability statement: it names no actions, no trigger terms, and no use conditions, scoring at floor on all four dimensions. It reads as a placeholder for a skill that has been intentionally disabled rather than described.

Suggestions

State what the skill actually does using concrete third-person verbs (e.g., 'Processes X by doing Y') instead of describing its configuration state.

Add an explicit 'Use when...' clause with natural trigger terms and file extensions users would actually say.

Anchor the description in a specific domain so it is distinguishable from other skills and unlikely to fire for the wrong one.

Dimension	Reasoning	Score
Specificity	'A skill with model invocation disabled' names no concrete actions — it describes the skill's configuration state, not a capability, matching 'entirely vague; no concrete actions; pure abstract language'. It does not reach anchor 2 because it doesn't even name a task domain the way 'Processes PDF files' does.	1 / 5
Completeness	Neither 'what does this skill do' nor 'when should Claude use it' is answered — the description carries no capability statement and no 'Use when...' clause, matching the 'missing both what and when' anchor.	1 / 5
Trigger Term Quality	There are no natural keywords a user would say when needing this skill; 'model invocation' is harness configuration jargon, not a user-facing trigger term, matching 'no natural keywords; only technical jargon or entirely generic language'.	1 / 5
Distinctiveness Conflict Risk	'A skill with model invocation disabled' is entirely generic meta-language indistinguishable from any other disabled or placeholder skill, so it 'would conflict with virtually any skill' per the anchor-1 example.	1 / 5
	Total	4 / 20 Passed

Validation

100%

Warnings & errors only

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: crdant/compound-engineering-plugin
Path: tests/fixtures/sample-plugin/skills/disabled-skill/SKILL.md
Commit: f794948

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.