skill-one

Sample skill

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/skill-one/SKILL.md

The canonical home for this skill is skill-one 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 a placeholder ("Skill body.") containing no instructional content of any kind: no actions, no workflow, no examples, and no structure. It scores at the floor for actionability and workflow clarity; its conciseness reflects absence of content rather than disciplined editing. The body needs to be written from scratch with concrete, executable guidance.

Suggestions

Replace the placeholder with concrete, executable guidance — actual code blocks, commands, or specific step-by-step instructions for the skill's task (actionability).

If the task involves multiple steps or any destructive/batch operation, lay out a numbered sequence with explicit validation checkpoints and a fix-and-retry loop (workflow_clarity).

Organize the body into clearly headed sections (e.g. "## Quick start", "## Advanced") and move bulk reference material into separate files in references/ linked one level deep (progressive_disclosure).

Dimension	Reasoning	Score
Conciseness	The body is a single line ("Skill body.") with zero padding, no over-explanation of concepts Claude already knows, and nothing that could be trimmed — the leanest possible on this dimension. The emptiness is penalized under the other dimensions, not here, since conciseness measures token waste.	5 / 5
Actionability	"Skill body." provides no code, commands, or steps — it neither instructs nor describes anything concrete, matching the anchor "Entirely vague or abstract; only describes rather than instructs". It falls short of level 2, which at least gives high-level hints.	1 / 5
Workflow Clarity	There is no sequence of steps whatsoever — no multi-step process is laid out and no validation checkpoints exist, matching the anchor "Steps missing or incoherent; no sequence". This is below the rough-sequence example "1. Open the document; 2. Make changes".	1 / 5
Progressive Disclosure	The body has no sections, headers, or organization at all, so the simple-skill exemption (score 5 for a short, well-organized skill) does not apply. It is not a monolithic wall of text or nested-reference chain (level 1), so it best fits the "minimal structure" anchor at level 2.	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 a placeholder with no informative content: it names no capabilities, no domain, no triggers, and no use cases. It matches the lowest anchor on every dimension and resembles the bad example "Does stuff with files". It needs a full rewrite stating what the skill does and when to use it.

Suggestions

State the skill's concrete capabilities in third person, e.g. "Extract text and tables from PDF files, fill forms, merge documents" — currently no action or domain is named (specificity).

Add an explicit trigger clause: "Use when working with <file types / tasks>, or when the user mentions <keywords>" — the absence of any "when" guidance leaves completeness at the floor.

Include natural keywords, synonyms, and file extensions users would actually say (e.g. "PDF files, PDFs, forms, .pdf") so the skill is discoverable and distinguishable from other skills.

Dimension	Reasoning	Score
Specificity	The description is just "Sample skill" — no domain is named and no concrete actions are listed, matching the anchor for entirely vague, pure abstract language ("Helps with documents"). It does not reach level 2, which requires at least naming a domain ("Processes PDF files").	1 / 5
Completeness	Neither a "what" nor a "when" is present, and there is no "Use when..." clause or equivalent trigger guidance (which would cap this dimension at 3 regardless). This matches the anchor "Missing both what and when".	1 / 5
Trigger Term Quality	"Sample skill" contains no natural keywords, synonyms, or file extensions a user would say — matching the lowest anchor ("only technical jargon or entirely generic language") and falling below even "Works with files".	1 / 5
Distinctiveness Conflict Risk	"Sample skill" is entirely generic with no niche, so it would conflict with virtually any other skill — exactly the level-1 anchor; it lacks even the partial specificity of "Works with document files" (level 3).	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 (12 chars), consider making it more detailed	Warning

	Total	15 / 16 Passed

Repository: crdant/compound-engineering-plugin
Path: tests/fixtures/sample-plugin/skills/skill-one/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.