npm

npm registry ops: login, whoami, names, publish; 1Password tmux.

Quality

83%

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

100%

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

The body is lean, highly actionable, and well-structured, with concrete script invocations, explicit validation/retry checkpoints, and one-level-deep references to real bundle files. No meaningful weaknesses against the rubric.

Dimension	Reasoning	Score
Conciseness	Dense bullet lists with no padding and no explanation of concepts Claude already knows (what npm, 1Password, or tmux are); every line carries operational information, matching the 'lean and efficient' anchor.	3 / 3
Actionability	Provides concrete, copy-paste-ready invocations with absolute paths ('scripts/publish-package.sh', 'scripts/npm-service.sh -- <npm args...>'), exact 1Password item names, and specific flags ('--account my.1password.com'); fully executable, not pseudocode.	3 / 3
Workflow Clarity	Publish and reserve workflows enumerate ordered steps with explicit validation checkpoints ('verifies identity, refuses an existing package version', 'verifies registry visibility') plus error-recovery feedback ('retries one expired OTP', 'stop and ask if auth shape is ambiguous').	3 / 3
Progressive Disclosure	Organized into clear sections (Auth, Package Publishing, Package Reservation) that point to real one-level-deep bundle scripts — npm-auth.sh, npm-service.sh, publish-package.sh, reserve-packages.sh, npm-auth-login.mjs all verified present — with no deep reference nesting.	3 / 3
	Total	12 / 12 Passed

Description

67%

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 and distinctive, naming concrete npm registry operations, but it omits any 'when to use' trigger guidance and leans terse on natural user phrasing. Adding a 'Use when...' clause would lift the two capped dimensions.

Suggestions

Append an explicit trigger clause, e.g. 'Use when publishing packages, checking npm name availability, or debugging npm registry auth.'

Add common natural phrasings like 'package availability' or 'npm login' to broaden trigger-term coverage.

Consider expanding 'names' to 'package name availability/reservation' so the capability reads unambiguously.

Dimension	Reasoning	Score
Specificity	Quotes 'login, whoami, names, publish' — four concrete registry operations, matching the 'lists multiple specific concrete actions' anchor rather than the domain-only score 2 anchor.	3 / 3
Completeness	Clearly states what ('npm registry ops: login, whoami, names, publish') but has no 'Use when...' or equivalent trigger guidance, which per the guidelines caps completeness at 2; not score 3 because 'when' is entirely absent.	2 / 3
Trigger Term Quality	Has relevant keywords ('npm registry', 'publish', 'whoami') but is terse and omits common user variations such as 'package availability', 'unpublish', or 'npm login'; closest to 'some relevant keywords but missing common variations'.	2 / 3
Distinctiveness Conflict Risk	'npm registry ops' plus the unusual '1Password tmux' qualifier carves a clear niche unlikely to fire for unrelated skills; matches the distinct-triggers anchor.	3 / 3
	Total	10 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: steipete/agent-scripts
Path: skills/npm/SKILL.md
Commit: bb36883

Reviewed: about 13 hours 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.