python-environment

Detect, configure, and use a conda-compatible tool. Use before tasks that need the project environment, such as importing project code, running tests, building docs, or invoking repo tooling.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

82%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 tight, highly actionable skill with executable bash and a clear sequenced workflow. Main improvements are moving the dated version note into a deprecated-style section and adding explicit validation around the destructive --prune update.

Suggestions

Move the 'As of 2026-02-13, current versions...' line into an 'Old/deprecated patterns' or version-reference section so the dated information does not penalize conciseness.

Add an explicit validation checkpoint after `env update --prune` (e.g., verify the env still imports the package) since --prune is destructive.

Consider extracting the troubleshooting and git-worktree guidance into a TROUBLESHOOTING.md reference to keep SKILL.md as a lean overview.

Dimension	Reasoning	Score
Conciseness	Largely lean with executable bash and no concept over-explanation, but the time-sensitive version line ('As of 2026-02-13, current versions are conda 26.1.0...') sits outside a deprecated/old-patterns section, which the rubric penalizes.	4 / 5
Actionability	Fully executable, copy-paste-ready commands throughout (CONDA_EXE detection loop, env create, run -n CausalPy make setup) with concrete examples like pytest and prek run covering common cases.	5 / 5
Workflow Clarity	Clear decide->reuse->detect->create->install->run sequence with an error-recovery fallback (run -n fails -> env list -> run -p), but the destructive `env update --prune` step lacks an explicit validation checkpoint.	4 / 5
Progressive Disclosure	Well-organized single-purpose sections with clear headers and no nested references, but at ~100 lines the inline troubleshooting and worktree guidance could be split into a reference file.	4 / 5
	Total	17 / 20 Passed

Description

88%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, concrete description that clearly states both capabilities and trigger conditions in third person. The only soft spot is mild overlap risk from generic task triggers alongside the more specific conda framing.

Dimension	Reasoning	Score
Specificity	Names the conda-tool domain and three concrete actions ('Detect, configure, and use') plus a use-case list, giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both 'what' (detect/configure/use a conda-compatible tool) and 'when' ('Use before tasks that need the project environment, such as...') with concrete triggers.	5 / 5
Trigger Term Quality	Includes natural phrases users say ('running tests', 'building docs', 'importing project code', 'repo tooling'), but leans on the technical 'conda-compatible tool' phrasing and misses a few synonyms.	4 / 5
Distinctiveness Conflict Risk	The conda-environment niche is clear and distinct, but the broad task triggers ('running tests', 'building docs') create minor overlap risk with related skills.	4 / 5
	Total	18 / 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: pymc-labs/CausalPy
Path: .agents/skills/python-environment/SKILL.md
Commit: f94d7af

Reviewed: 3 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.