env-management

Use when a notebook run fails on a missing package (ImportError, ModuleNotFoundError, "there is no package called"), when you need to inspect an installed package version, or when you need to install, add, or manage Python or R packages for the notebook runtime. Covers inspect_packages, routing Python vs R through manage_packages, why in-cell %pip/!pip/install.packages() and OS installers are forbidden, restarting the kernel after an install, and when to stop and ask the user.

Quality

95%

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

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.

An exceptionally actionable, well-organized policy document: every tool call is concrete with parameters and result-field semantics, and each workflow includes explicit checkpoints and error-recovery loops. The only weakness is minor word-level redundancy in the persistence paragraph.

Dimension	Reasoning	Score
Conciseness	Lean, policy-only prose that assumes Claude's competence (receipt fields, kernel library-state behavior) with no filler or explanation of known concepts. Minor trimmable redundancy: 'Every install persists — there is no "temporary" install to undo later. Install once; it stays available in later cells and sessions on that runtime.' states the same fact twice.	4 / 5
Actionability	Fully concrete, copy-ready guidance: 'manage_packages(language="python", packages=["numpy", "pandas"])', 'usePip=true', 'channels=["bioconda"]', 'manage_environments(action:"create", language, name)', plus exact result fields to check ('needsRestart', 'created.runnable', 'bindingChanged', 'selection:"unresolved"', 'DEFAULT_RUNTIME_NOT_READY').	5 / 5
Workflow Clarity	Each scenario has an explicit sequence with validation checkpoints and feedback loops: 'DEFAULT_RUNTIME_NOT_READY' → 'notebook_execute' → retry 'inspect_packages'; 'needsRestart' → 'notebook_restart' before importing; create → 'check created.runnable' → 'continue only when created.runnable is true' → bind/switch with the receipt's runtimeId.	5 / 5
Progressive Disclosure	Single-file skill under 50 lines with no bundle files and no need for external references; the well-organized scenario sections (missing package, version check, routing, restart, forbidden methods, when to stop) satisfy the rubric's simple-skill exception.	5 / 5
	Total	19 / 20 Passed

Description

95%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 dense, information-rich description with explicit 'Use when' triggers anchored to exact error messages, concrete capabilities, and a clear niche. The only deduction is the second-person 'when you need to...' phrasing, which violates the third-person voice guideline.

Suggestions

Convert second-person phrasing to third person, e.g. 'Use when a notebook run fails on a missing package... or when the session needs to inspect an installed package version or install, add, or manage Python or R packages for the notebook runtime.'

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities ('inspect an installed package version', 'install, add, or manage Python or R packages', 'routing Python vs R through manage_packages', 'restarting the kernel after an install'), but the second-person voice ('when you need to inspect', 'you need to install') triggers the rubric's explicit 1-point specificity penalty. Not 3, since coverage is comprehensive rather than 1-2 actions.	4 / 5
Completeness	Explicitly answers both: 'what' (inspect versions, install/add/manage Python or R packages, route by language, restart the kernel, stop and ask the user) and 'when' ('Use when a notebook run fails on a missing package (ImportError, ModuleNotFoundError...)').	5 / 5
Trigger Term Quality	Comprehensive natural trigger terms including exact error strings users would report: 'missing package', 'ImportError', 'ModuleNotFoundError', 'there is no package called', 'inspect an installed package version', 'install, add, or manage'.	5 / 5
Distinctiveness Conflict Risk	Clear niche — package management for the notebook runtime — with distinct, specific error-message triggers; minimal risk of firing for an unrelated skill.	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: aipoch/open-science
Path: resources/skills/env-management/SKILL.md
Commit: bf35648

Reviewed: 8 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.