agent-package-manager

Installs, configures, audits, and operates Agent Package Manager (APM) in repositories. Use when initializing apm.yml, installing or updating packages, validating manifests, managing lockfiles, compiling agent context, browsing MCP servers, setting up runtimes, or packaging resolved context for CI and team distribution. Don't use for writing a single skill by hand, generic package managers like npm or pip, or non-APM agent configuration systems.

Quality

92%

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

Quality

Content

92%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 operational skill body: actionable commands, clear sequenced workflows with validation and error-recovery loops, and clean progressive disclosure into real reference files. Minor conciseness headroom only.

Dimension	Reasoning	Score
Conciseness	Lean procedural steps with concrete commands and no over-explanation of concepts Claude already knows; a few explanatory clauses (e.g. the apm compile vs install distinction) could be trimmed further.	4 / 5
Actionability	Concrete executable commands throughout (apm install, apm deps list, apm compile --dry-run) with copy-paste-ready examples like 'apm install webmaxru/agent-skills/skills/webmcp' covering common cases.	5 / 5
Workflow Clarity	Five sequenced steps plus an Error Handling section with explicit validation checkpoints (dry-run previews, verify resolved_commit changed, stale-cache feedback loop) appropriate for batch/destructive dependency operations.	5 / 5
Progressive Disclosure	Overview body with well-signaled one-level-deep references (manifest-and-lockfile.md, command-workflows.md, troubleshooting.md) and an asset template, all verified to exist; content is appropriately split for navigation.	5 / 5
	Total	19 / 20 Passed

Description

92%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 high-quality description that names concrete capabilities, gives explicit 'Use when' triggers, and disambiguates against generic package managers. Slight headroom only in trigger-term synonym/extension coverage.

Dimension	Reasoning	Score
Specificity	Lists many specific concrete actions (installs, configures, audits, operates, initializing apm.yml, validating manifests, managing lockfiles, compiling agent context, browsing MCP servers, setting up runtimes, packaging) with comprehensive coverage.	5 / 5
Completeness	Explicitly answers both what ('Installs, configures, audits, and operates Agent Package Manager (APM) in repositories') and when ('Use when initializing apm.yml...'), with concrete trigger phrases and negative boundary guidance.	5 / 5
Trigger Term Quality	Strong natural trigger phrases ('installing or updating packages', 'validating manifests', 'MCP servers', 'setting up runtimes') plus the APM acronym, but a few common synonyms and file extensions (e.g. apm.lock.yaml, .yml) are absent from the description.	4 / 5
Distinctiveness Conflict Risk	Clear APM niche with distinct triggers and an explicit 'Don't use for...npm or pip, or non-APM agent configuration systems' clause that minimizes conflict with adjacent skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: webmaxru/web-ai-agent-skills
Path: .github/skills/agent-package-manager/SKILL.md
Commit: adc6b11

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.