beta

Clean fixture tool skill with no forced reads and no mode table.

Quality

32%

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 ./test/fixtures/context-bill/tree-a/beta/SKILL.md

Quality

Content

43%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 extremely lean and well-structured for its tiny size, but it is content-free from an operational standpoint: it never states the command to run or the action to perform, leaving Claude with no executable guidance. Progressive disclosure is fine by virtue of the skill's simplicity, but actionability and workflow clarity are severely lacking.

Suggestions

State the actual one-command invocation and what it does, so the skill is executable rather than merely descriptive.

Add a concrete example of running the command against a fixture so the single action is unambiguous.

Replace the meta sentence ('Nothing eager beyond this file, nothing lazy') with the single concrete instruction the skill is meant to deliver.

Dimension	Reasoning	Score
Conciseness	The body is two tiny sentences with no over-explanation of concepts Claude already knows and nothing clearly trimmable, though 'Nothing eager beyond this file, nothing lazy' is borderline meta padding that does not fully earn its place, matching the anchor 'Efficient; minor instances of over-explanation that could be trimmed.'	4 / 5
Actionability	It provides no code, commands, or concrete guidance — 'One-command tool skill' only describes the skill rather than instructing how to run it, matching the anchor 'Entirely vague or abstract; no concrete code or commands; only describes rather than instructs.'	1 / 5
Workflow Clarity	Although it self-describes as a one-command skill, the actual command and action are never specified, so the single action is not unambiguous and the simple-skill exception cannot reach 5; this matches the anchor 'Rough sequence present but many gaps; steps poorly defined.'	2 / 5
Progressive Disclosure	The skill is under 50 lines, has no need for external references (none exist), and is organized into a single clear headed section, satisfying the simple-skill exception that lets progressive disclosure score 5 with just well-organized sections.	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 is a meta-commentary on the skill's design rather than a statement of what it does or when to use it: it names a niche vaguely, includes no concrete actions, no natural trigger terms, and no 'Use when' guidance. It is distinguishable only by the 'fixture tool' niche, not by clear triggers.

Suggestions

Rewrite the description to state concrete actions the skill performs (e.g., 'Cleans and resets test fixtures') instead of describing its own structure.

Add an explicit 'Use when ...' clause with natural trigger phrases a user would actually say.

Drop the meta jargon ('no forced reads', 'no mode table') which adds no capability or trigger information.

Dimension	Reasoning	Score
Specificity	The description names a domain ('fixture tool skill') but states zero concrete actions, instead listing meta-properties ('no forced reads', 'no mode table') that describe the skill's structure rather than its capabilities, matching the anchor 'Names the domain but actions are minimal or generic.'	2 / 5
Completeness	It offers only a vague 'what' (structural self-description, not function) and entirely omits any 'when'/'Use when' trigger guidance, matching the anchor 'Has a vague what and no when'; the missing trigger clause caps it at 3 but the what is too vague for that.	2 / 5
Trigger Term Quality	There are no natural user-facing keywords; 'forced reads' and 'mode table' are skill-design jargon a user would never say when they need this skill, matching the anchor 'No natural keywords; only technical jargon or entirely generic language.'	1 / 5
Distinctiveness Conflict Risk	'fixture tool' points at a somewhat specific niche, but the generic meta-phrasing ('Clean fixture tool skill') could still overlap with other tooling skills, matching the anchor 'Somewhat specific but could still overlap with similar skills.'	3 / 5
	Total	8 / 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: garrytan/gstack
Path: test/fixtures/context-bill/tree-a/beta/SKILL.md
Commit: 96764e8

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.