CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

73

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

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 dense, command-driven operational skill: every step is executable, risky operations are guarded by dry-runs and post-change verification, and detail is correctly pushed to well-signaled, one-level-deep reference files. The only defects are cosmetic — a broken list numbering in Step 3 (item 11 is mis-indented under item 10) and mild repetition of troubleshooting pointers.

Suggestions

Fix the list numbering in Step 3: item 11 ('If the repository is in an organization that enforces apm-policy.yml...') is indented as a child of item 10 and numbered inconsistently; promote it to a top-level item.

DimensionReasoningScore

Conciseness

The body is a lean, imperative procedure list with almost no concept explanation ('Preview risky changes with `apm install --dry-run`'), assuming Claude's competence throughout. Minor redundancy — `references/troubleshooting.md` is re-signaled four times and the Error Handling section overlaps Steps 3–5 — keeps it just short of the 'every token earns its place' anchor.

4 / 5

Actionability

Nearly every step is a copy-paste-ready command with flags and arguments (`apm compile --validate`, `apm preview <script> -p key=value`, `apm mcp search <query>`), including a fully concrete install example (`apm install webmaxru/web-ai-agent-skills/skills/webmcp`). This matches the anchor of fully executable commands covering the common cases.

5 / 5

Workflow Clarity

Five explicitly sequenced steps with validation checkpoints exactly where risk lives: dry-runs before dependency changes, 'verify the lockfile `resolved_commit` actually changed' after updates, `apm deps list/tree` verification, and 'use `apm pack` only after a successful install'. The Error Handling section supplies feedback loops (auth failures → fix host authentication → retry; pack failure → rerun `apm install`), matching the top anchor for a batch/install-type skill.

5 / 5

Progressive Disclosure

The body is a well-organized overview that delegates detail to three real, one-level-deep reference files, each clearly signaled with its purpose and even the target section ('the "Self-referencing dependencies" section' in `references/troubleshooting.md`), plus an asset template (`assets/apm.yml.template`). Verified against the actual bundle: all referenced paths exist and contain no further nested references.

5 / 5

Total

19

/

20

Passed

Description

87%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 description in third-person voice with an explicit 'Use when' clause and an unusually valuable 'Don't use for' exclusion boundary. It is comprehensive and concrete on triggers; the only room for improvement is slightly more vivid leading verbs and a few more natural phrasings users might say.

DimensionReasoningScore

Specificity

Names the domain and many concrete objects and operations ('initializing apm.yml', 'validating manifests', 'managing lockfiles', 'browsing MCP servers', 'packaging resolved context for CI'), with only minor coverage gaps. The leading verbs ('Installs, configures, audits, and operates') are slightly more generic than the anchor-5 example's fully concrete action list, so it sits between anchors 4 and 5, clearly above the midpoint.

4 / 5

Completeness

Explicitly answers both questions: 'what' ('Installs, configures, audits, and operates Agent Package Manager (APM) in repositories') and 'when' ('Use when initializing apm.yml, installing or updating packages, ... for CI and team distribution') with concrete trigger phrases, plus an explicit negative-scope clause. This matches the top anchor exactly.

5 / 5

Trigger Term Quality

Good natural-term coverage users would actually say: 'apm.yml', 'installing or updating packages', 'lockfiles', 'MCP servers', 'runtimes', 'CI'. A few natural variations are missing (e.g. 'apm.lock.yaml', 'apm init', 'AGENTS.md/CLAUDE.md compilation), which fits the anchor 'good keyword coverage; a few natural terms missing' rather than the comprehensive synonym/extension coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

A clear niche (APM only) with distinct triggers, and the 'Don't use for ... generic package managers like npm or pip, or non-APM agent configuration systems' clause explicitly fences off the highest-conflict neighbors, giving minimal conflict risk as the anchor-5 example describes.

5 / 5

Total

18

/

20

Passed

Validation

100%

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/ai-native-dev
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.