CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

48%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-organized but largely abstract runbook: sequencing and fail-fast validation are explicit, yet it contains zero concrete pnpm commands or selector examples, making it difficult to execute directly. Its progressive-disclosure pointer targets a nonexistent path instead of the real bundle files.

Suggestions

Add concrete, executable pnpm examples — e.g. `pnpm --filter "...@origin/main" run test` and `pnpm install --frozen-lockfile` — under Workflow or a Quick start section so the guidance is copy-paste ready.

Replace abstract Inputs/Outputs entries ("command intent", "risk posture") with concrete artifacts like the actual filter-selector syntax and validation commands to expect.

Fix the Progressive Disclosure path to point at the real bundle files (references/contract.yaml, references/evals.yaml, references/task-profile.json) and drop the duplicated content between the body and contract.yaml.

DimensionReasoningScore

Conciseness

The body never explains concepts Claude already knows, which is good, but sections like "Philosophy" ("Prefer the smallest reversible step that proves or disproves the current assumption") and abstract Inputs/Outputs entries ("risk posture", "command intent") are generic process padding that could be tightened. It sits between the 'mostly efficient' (3) and 'efficient' (4) anchors; the abstract filler is more than minor.

3 / 5

Actionability

There is not a single concrete pnpm command, filter-selector example, or executable step anywhere in the body — "Take the smallest action that advances the confirmed goal" and "Run the narrowest real validator or command path available" are high-level hints without the specific steps to execute. This matches the 2 anchor (minimal concrete guidance); it is above 1 because a coherent process shape (classify, inspect, stop at gates) is still described.

2 / 5

Workflow Clarity

The Workflow section gives a clear 5-step sequence with explicit validation checkpoints and a feedback loop: "Stop at the first failed gate or blocker", "Rerun the relevant validation after fixes", and "Fail fast: stop at the first failed gate; do not proceed until it is fixed and rerun". This satisfies the batch-operation validation requirement and matches the 4 anchor; it misses 5 because checkpoints are conceptual — no actual validation command is ever named.

4 / 5

Progressive Disclosure

The body is well-sectioned and has a dedicated Progressive Disclosure section, but it points to "Infrastructure/references/deferred-skill-context/agent-ops-pnpm-manager/", a path that does not exist in the bundle, while the actual files present (references/contract.yaml, evals.yaml, task-profile.json) are never referenced — and contract.yaml largely duplicates the body. This fits the 3 anchor: structure present but references not clearly/signaled correctly.

3 / 5

Total

12

/

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, concise, with an explicit 'Use when' clause and concrete pnpm-specific trigger phrases. Its only weakness is generic leading verbs and missing file-extension/synonym triggers, which keep specificity and trigger coverage at 4 rather than 5.

DimensionReasoningScore

Specificity

Quotes: "Run, plan, and validate pnpm workspace operations" plus "monorepo installs, tests, builds, filters, changed-package selection, or publish routing" — several concrete capabilities are listed with good domain coverage. It falls short of the 5 anchor because the leading verbs (run/plan/validate) are generic compared to fully concrete action phrasing, and a few plausible capabilities (lockfile handling, dependency updates) are absent.

4 / 5

Completeness

Explicitly answers both: what ("Run, plan, and validate pnpm workspace operations") and when ("Use when a user needs pnpm monorepo installs, tests, builds, filters, changed-package selection, or publish routing") with concrete trigger phrases — a clear match to the 5 anchor, matching the good_overall_examples pattern.

5 / 5

Trigger Term Quality

Quotes: "pnpm", "monorepo", "installs, tests, builds, filters, changed-package selection, publish routing" — natural phrases a user with this need would say. Not 5 because it lacks synonyms and file-extension triggers (e.g., pnpm-workspace.yaml, pnpm-lock.yaml, 'affected packages').

4 / 5

Distinctiveness Conflict Risk

Quotes: "pnpm workspace operations", "pnpm monorepo installs" — a clear niche named after a specific tool, with trigger phrasing that other skills (npm/yarn, generic build) would not claim. Minimal conflict risk.

5 / 5

Total

18

/

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

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

jscraik/Agent-Skills

Path

Skills/agent-ops/pnpm-manager/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.