apm-usage

Activate when the user asks about APM (Agent Package Manager): installing, configuring, authoring, or troubleshooting AI-agent packages, dependencies, compilation, MCP servers, policy, or any `apm` CLI command.

Quality

81%

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

Quality

Content

77%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is concise, well-organized, and gives a clear core sync workflow, but its actionability and progressive disclosure are undermined because every referenced detail file is a broken link. The overview promises detail that is not actually present in the bundle.

Suggestions

Add the eight referenced bundle files (installation.md, workflow.md, commands.md, dependencies.md, authentication.md, governance.md, package-authoring.md, troubleshooting.md) or remove the dead links, so progressive disclosure actually resolves.

Inline a minimal copy-paste-ready command example (e.g. a full clone-install-update sequence) so the skill is actionable even without the missing reference files.

Add a brief validation/verification note for policy-sensitive operations (e.g. how to confirm `apm audit` passed) to strengthen the workflow's error-recovery guidance.

Dimension	Reasoning	Score
Conciseness	The body is lean and efficient, using terse bullet lists and a single justifying intro sentence, with no padding of concepts Claude already knows; every token roughly earns its place.	3 / 3
Actionability	Concrete executable commands are present (apm install, apm install --update, pinning with #v1.0.0 tags), but the substantive operational detail is delegated to the referenced files, none of which exist, leaving the guidance incomplete and not copy-paste ready.	2 / 3
Workflow Clarity	For this simple orientation skill the core team-sync sequence (git clone then apm install to restore dependencies) is unambiguous and well sequenced, and the referenced operations are non-destructive so missing validation checkpoints are acceptable per the simple-skills scoring note.	3 / 3
Progressive Disclosure	The overview is well structured with clearly signaled one-level-deep references, but all eight referenced files (installation.md, workflow.md, commands.md, etc.) are missing, so the disclosure breaks at the first hop and navigation leads nowhere.	2 / 3
	Total	10 / 12 Passed

Description

85%Weight 40%Scale 1-3

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 specific, complete, and distinctive, with an explicit 'Activate when' trigger and a clear niche tied to the named APM tool. Its main weakness is trigger-term breadth: it relies on the product name rather than enumerating the natural variations users would actually say.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions (installing, configuring, authoring, troubleshooting) across dependencies, compilation, MCP servers, policy, and CLI commands, matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	It explicitly answers both what (installing/configuring/authoring/troubleshooting packages and MCP servers) and when ('Activate when the user asks about APM'), with an explicit trigger clause, so it is not capped at 2.	3 / 3
Trigger Term Quality	The natural trigger terms are essentially the product name repeated ('APM', 'Agent Package Manager', 'apm CLI command'); it gives the explicit trigger but lacks the breadth of common natural variations a user might say, fitting 'some relevant keywords but missing common variations' rather than full coverage.	2 / 3
Distinctiveness Conflict Risk	Scoped to a specific named tool (APM / Agent Package Manager) with distinct triggers tied to that proper name, giving it a clear niche unlikely to conflict with other skills.	3 / 3
	Total	11 / 12 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
relative_links	Relative link issues: 8 missing	Warning

	Total	15 / 16 Passed

Repository: microsoft/apm
Path: packages/apm-guide/.apm/skills/apm-usage/SKILL.md
Commit: 634f7b6

Reviewed: 8 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.