CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

60

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./packages/apm-guide/.apm/skills/apm-usage/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

68%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.

A well-structured overview skill: concise, rule-dense, and easy to navigate, with concrete commands for the most common operations. Its weaknesses are a core workflow that is implied rather than sequenced, and a reference layer that is structurally excellent but points at files missing from the bundle.

Suggestions

Assemble the core lifecycle (git clone -> `apm install` -> edit apm.yml -> commit apm.yml + apm.lock.yaml + .apm/) into one ordered, numbered workflow with a verification step (e.g., check `apm install` output or run `apm audit`) before the Key rules section.

Ship the eight referenced files (installation.md, workflow.md, commands.md, dependencies.md, authentication.md, governance.md, package-authoring.md, troubleshooting.md) in the bundle — ideally under references/ — so the links resolve; currently none exist next to SKILL.md.

Trim the "When to activate" bullet list, which duplicates the frontmatter description's triggers, to reclaim tokens in the always-loaded body.

DimensionReasoningScore

Conciseness

The body is lean and rule-focused with a brief, informative intro; every section carries operational content. Not 5 because the "When to activate" section largely restates the frontmatter description's trigger list, which could be trimmed, and the intro slightly overlaps what the description already establishes.

4 / 5

Actionability

Concrete, executable directives throughout: "after `git clone`, run `apm install`", "`apm install --update` refreshes to latest refs", "use tags (`#v1.0.0`) in production", and an explicit commit/ignore file list. For an instruction-only skill this is actionable; not 5 because most operations (compile, audit, auth setup) are delegated to references without a single inline example.

4 / 5

Workflow Clarity

The pieces of the core workflow (clone -> `apm install` -> edit apm.yml -> commit apm.yml + apm.lock.yaml) are present but scattered across "Key rules" rather than assembled into an ordered sequence, and no validation checkpoints are given. Fits anchor 3 (steps present but sequence/checkpoints implicit); not 2 because the individual directives are concrete and correctly gated (e.g., "after `git clone`").

3 / 5

Progressive Disclosure

A clean overview with well-labeled, one-level-deep references, each with a short descriptor ("-- install and update APM", "-- full CLI command reference"). Not 5 because all eight linked files (installation.md, workflow.md, commands.md, dependencies.md, authentication.md, governance.md, package-authoring.md, troubleshooting.md) are absent from the bundle — no references/ directory exists — so the links cannot be verified as real targets.

4 / 5

Total

15

/

20

Passed

Description

75%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.

A strong trigger-oriented description with an explicit activation clause, a distinctive niche, and good natural keywords. Its main weakness is that it never explicitly states what the skill does — the 'what' is only implied by the enumerated topics — and it omits a few natural trigger variants like apm.yml or apm.lock.

Suggestions

Open with an explicit 'what' clause (e.g., "Guides usage of the `apm` CLI for installing, authoring, and governing AI-agent packages") before the activation clause.

Add natural trigger variants users would actually type, such as "apm.yml", "apm.lock", or "agent packages", to broaden keyword coverage.

Replace the vague term "policy" with concrete phrases like "policy enforcement" or "`apm audit`" to sharpen both specificity and triggers.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions ("installing, configuring, authoring, or troubleshooting" packages, dependencies, compilation, MCP servers, "any `apm` CLI command"), with minor gaps such as the vague "policy" term and no mention of sharing, governing, or auditing. Not 5 because coverage is not comprehensive; not 3 because it goes well beyond 1-2 actions.

4 / 5

Completeness

The 'when' is fully explicit ("Activate when the user asks about APM..." with an enumerated topic list), but the 'what' is never stated as the skill's purpose — only implied by the enumerated activities. Fits anchor 4 (both present, one could be more explicit) rather than 3, whose pattern is a clear 'what' with a weak 'when'.

4 / 5

Trigger Term Quality

Good natural keyword coverage ("APM", "Agent Package Manager", "`apm` CLI command", "dependencies", "MCP servers") that mirrors what users would say. Not 5 because natural variants like "apm.yml", "apm.lock", or "agent packages" are missing.

4 / 5

Distinctiveness Conflict Risk

"APM (Agent Package Manager)" and "any `apm` CLI command" establish a clear, distinctive niche with low conflict risk. Minor overlap remains via broad terms like "MCP servers" and "configuring", which could trigger for general MCP-setup questions; not 5 for that reason.

4 / 5

Total

16

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

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

Reviewed

Table of Contents

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.