pnpm-manager

Run, plan, and validate pnpm workspace operations. Use when a user needs pnpm monorepo installs, tests, builds, filters, changed-package selection, or publish routing.

Quality

73%

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

Fix and improve this skill with Tessl

tessl review fix ./Skills/agent-ops/pnpm-manager/SKILL.md

Quality

Content

60%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.

The body is a well-structured, concise runbook with a clear sequenced workflow and explicit fail-fast validation feedback loops. Its main weakness is actionability: it gives abstract philosophy and direction instead of concrete pnpm commands or selector examples, and its progressive-disclosure pointer targets an archived path rather than the real local bundle files.

Suggestions

Add 1-2 concrete pnpm command/selector examples (e.g. `pnpm --filter '...[origin/main]' test` for changed-package tests, or a scoped install/build invocation) so the guidance is executable rather than philosophical.

Replace the duplicated opening description line with a brief one-sentence purpose to remove the verbatim frontmatter redundancy, or drop it entirely since the frontmatter already carries it.

Point the Progressive Disclosure section at the actual local bundle files (contract.yaml, evals.yaml, task-profile.json) or confirm the archived path exists, so deferred references resolve to real, loadable files.

Dimension	Reasoning	Score
Conciseness	The body is lean with short bullets and avoids explaining concepts Claude already knows, but it repeats the frontmatter description verbatim as the opening line ('Run, plan, and validate pnpm workspace operations. Use when...'), a minor token redundancy that keeps it at 4 rather than 5.	4 / 5
Actionability	Guidance is largely philosophical direction — 'Take the smallest action that advances the confirmed goal', 'Run the narrowest real validator or command path available' — with no concrete pnpm commands or selector syntax (e.g. `pnpm --filter '...changed since main' test`), fitting the 2 anchor of high-level hints missing the specific steps to execute; it does not reach 3 because there is no executable or pseudocode detail.	2 / 5
Workflow Clarity	A clear 5-step sequence exists with an explicit checkpoint ('Stop at the first failed gate or blocker and report exact evidence') and a fix-then-rerun feedback loop ('Rerun the relevant validation after fixes before claiming completion'), but validation is described abstractly rather than with concrete commands, so it is 4 rather than 5.	4 / 5
Progressive Disclosure	Sections are well-organized and a dedicated 'Progressive Disclosure' section signals one-level-deep deferred loading, but it points to an archived path ('Infrastructure/references/deferred-skill-context/agent-ops-pnpm-manager/') that is not present in the local bundle and does not name the actual bundle files (references/contract.yaml, evals.yaml, task-profile.json), a minor organization gap that fits 4 rather than 5.	4 / 5
	Total	14 / 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.

The description is strong: third-person voice, explicit what-and-when structure, concrete trigger phrases, and a clearly scoped pnpm-workspace niche with minimal conflict risk. The only minor gap is that trigger phrasings lean slightly technical rather than mirroring exact user utterances.

Dimension	Reasoning	Score
Specificity	Quotes 'Run, plan, and validate pnpm workspace operations' name the domain plus three action verbs, and the use-when clause enumerates installs, tests, builds, filters, changed-package selection, and publish routing — several specific actions with only minor coverage gaps, fitting the 4 anchor better than the more comprehensive 5.	4 / 5
Completeness	It explicitly states the 'what' ('Run, plan, and validate pnpm workspace operations') and the 'when' ('Use when a user needs pnpm monorepo installs, tests, builds, filters, changed-package selection, or publish routing') with concrete trigger phrases, matching the 5 anchor exactly.	5 / 5
Trigger Term Quality	Natural terms like 'pnpm', 'monorepo', 'workspace', 'installs', 'tests', 'builds', 'filters', and 'publish' are what a user would actually say; coverage is good with synonyms (monorepo/workspace), but a few natural phrasings (e.g. 'pnpm install', 'run tests for changed packages') are not present, so it sits at 4 rather than 5.	4 / 5
Distinctiveness Conflict Risk	The pnpm-workspace/monorepo niche with operation-specific triggers is clearly distinct from generic package-manager or unrelated skills and unlikely to fire for the wrong skill, matching the 5 anchor.	5 / 5
	Total	18 / 20 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: jscraik/Agent-Skills
Path: Skills/agent-ops/pnpm-manager/SKILL.md
Commit: f1f2f21

Reviewed: 2 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.