Tessl • The management layer for AI agent skills

Blog Docs Log inGet started

SkillPublic

example-skill

An example skill from the mock plugin

Quality

34%

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/mock-plugin/.apm/skills/example-skill/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 well-organized and token-efficient for its size, but it contains no actionable guidance whatsoever — it describes what the skill demonstrates rather than instructing how to do anything, and defines no workflow steps. It reads as a structural placeholder rather than operational instructions.

Suggestions

Replace the descriptive bullets ("Demonstrates...", "Shows...", "Tests...") with concrete, executable guidance — specific commands, code, or step-by-step instructions for the task the skill performs.

Define an explicit workflow in "How to Use": a sequenced list of what to actually do when the skill is invoked, rather than a sentence about plugin installation and discovery.

Trim the explanation of the "normal skill discovery mechanism", which is knowledge Claude already has and earns no tokens.

Dimension	Reasoning	Score
Conciseness	The body is brief and free of padding, but "can be invoked through the normal skill discovery mechanism" explains a mechanism Claude already knows — a minor instance of over-explanation matching anchor 4 rather than the every-token-earns-its-place standard of anchor 5.	4 / 5
Actionability	The bullets ("Demonstrates skill integration in plugins", "Shows how skills are organized", "Tests the skill automation capabilities") only describe what the skill demonstrates — there is no code, command, or executable instruction, exactly matching the anchor for describing rather than instructing.	1 / 5
Workflow Clarity	No steps or sequence appear anywhere in the body; the single "How to Use" sentence is a vague statement about availability, not an unambiguous action, so the simple-skill exception for a clear single action cannot apply.	1 / 5
Progressive Disclosure	The skill is under 50 lines, needs no external references, and its sections ("What This Skill Does", "How to Use") are clearly organized with nothing buried or inlined that belongs elsewhere — meeting the rubric's explicit simple-skill standard for a top score.	5 / 5
	Total	11 / 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 fails on every dimension: it describes the skill's provenance ("from the mock plugin") rather than what it does or when to use it, contains no concrete actions, no natural trigger terms, and no distinguishing information. It functions as a placeholder label, not a capability description. Every dimension sits at the floor of the scale.

Suggestions

State concrete capabilities in third person (e.g., "Performs X, Y, and Z for plugin development") instead of describing the skill's origin.

Add an explicit "Use when..." clause with natural trigger phrases users would actually say, such as "Use when developing or testing plugin skill bundles".

Include distinguishing keywords (file extensions, tool names, or task-specific terms) so the skill cannot be confused with other plugin or testing skills.

Dimension	Reasoning	Score
Specificity	"An example skill from the mock plugin" names no concrete actions and no task domain — it describes provenance, not capability, making it even vaguer than the anchor-1 example "Helps with documents".	1 / 5
Completeness	Neither "what" (no capability is stated) nor "when" (no trigger guidance of any kind) is present; the description only identifies the skill's origin, matching the anchor for missing both what and when.	1 / 5
Trigger Term Quality	The description contains no natural keywords a user would say when needing this skill; "example skill" and "mock plugin" are meta-labels, not task language, so it fails to meet even the one-or-two generic keywords of anchor 2.	1 / 5
Distinctiveness Conflict Risk	The description is entirely generic with no distinguishing triggers or selection basis; it provides nothing that would differentiate it from any other skill, matching the anchor-1 example of generic conflict risk.	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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: microsoft/apm
Path: tests/fixtures/mock-plugin/.apm/skills/example-skill/SKILL.md
Revision: 2920043

Reviewed: 12 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.

example-skill

Table of Contents

Is this your skill?