Tessl • The management layer for AI agent skills

Blog Docs Log inGet started

SkillPublic

skill

Overlay fixture

Quality

34%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./tests/fixtures/kits/overlay/extends-full/SKILL.md

Quality

Content

37%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 an empty shell: a lone heading with no instructions, examples, or workflow. While perfectly concise (nothing to trim), it is entirely non-actionable — Claude would have no idea what to do after loading this skill.

Suggestions

Add the actual task instructions under the heading — concrete commands or code showing how to perform the overlay operation.

If the skill involves multi-step or batch/destructive operations, sequence the steps explicitly with validation checkpoints.

If detailed material exists (API references, examples), move it to references/ files and link them one level deep from SKILL.md instead of leaving the body empty.

Dimension	Reasoning	Score
Conciseness	The body is a single heading ('# Overlay fixture') with zero padding, no over-explanation of concepts Claude already knows, and no wasted tokens — matching the anchor 'Lean and efficient; every token earns its place'. Nothing could be trimmed because essentially nothing is there.	5 / 5
Actionability	The body provides no concrete code, commands, or guidance of any kind — it does not even describe a task, matching the anchor 'Entirely vague or abstract; no concrete code or commands; only describes rather than instructs'. It cannot score 2 because there are not even high-level hints toward executing anything.	1 / 5
Workflow Clarity	No steps or sequence exist anywhere in the body — the content is just a title, matching the anchor 'Steps missing or incoherent; no sequence'. The simple-skill exception does not apply because it requires an unambiguous single action, and no action is stated at all.	1 / 5
Progressive Disclosure	The single heading provides nominal structure, but there is no organized content, overview, or navigation — the under-50-line exception requires 'well-organized sections' with clear content, which is absent. It does not score 2 because no content is improperly inlined and no references are buried; it does not score 4–5 because there is no overview or meaningful organization to navigate.	3 / 5
	Total	10 / 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 two-word placeholder label with no stated capabilities, trigger terms, or usage conditions. It fails all four dimensions at the lowest anchor because it conveys nothing about what the skill does or when it applies.

Suggestions

State concrete capabilities in third person (e.g., 'Applies overlay patches to configuration files and verifies results') instead of the bare label 'Overlay fixture'.

Add an explicit trigger clause such as 'Use when the user mentions overlays, fixtures, or patching configuration' so both 'what' and 'when' are answered.

Include natural keywords and synonyms users would actually say (e.g., file extensions or tool names related to the overlay task) to improve trigger-term quality and distinctiveness.

Dimension	Reasoning	Score
Specificity	The description 'Overlay fixture' names no concrete actions or capabilities — it is a pure abstract label, matching the anchor 'Entirely vague; no concrete actions; pure abstract language' ('Helps with documents'). It does not reach score 2 because even that anchor requires naming a domain with minimal actions (e.g., 'Processes PDF files').	1 / 5
Completeness	Neither 'what does this do' nor 'when should Claude use it' is stated — 'Overlay fixture' answers neither question, matching the anchor 'Missing both what and when'. There is also no 'Use when...' clause or equivalent trigger guidance.	1 / 5
Trigger Term Quality	No natural keywords a user would say when needing this skill are present; the phrase is generic label language with no user-facing trigger terms, matching anchor 1. It cannot score 2–3 since there are no relevant domain keywords at all, not even generic ones like 'Works with files'.	1 / 5
Distinctiveness Conflict Risk	The phrase is entirely generic and would conflict with virtually any other skill — it provides no distinguishing capability or trigger, matching anchor 1 ('Entirely generic; would conflict with virtually any skill').	1 / 5
	Total	4 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
description_field	'description' is very short (15 chars), consider making it more detailed	Warning

	Total	15 / 16 Passed

Repository: constructorfabric/studio
Path: tests/fixtures/kits/overlay/extends-full/SKILL.md
Revision: f6cba6a

Reviewed: 17 days ago

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.

skill

Table of Contents

Is this your skill?