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

88%

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

77%Weight 40%Scale 1-3

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

A highly actionable, well-sequenced conda-environment skill with concrete commands and clear error-recovery paths. Its main weaknesses are a dated version pin that hurts conciseness and a single-file structure with inline detail that leaves minor room for progressive disclosure.

Suggestions

Move the "As of 2026-02-13" version line into a clearly labeled 'Current versions' or 'Deprecated/old' section, or drop the date stamp, so time-sensitive info does not penalize conciseness.

Consider splitting the Git worktrees/remote-machines troubleshooting detail into a short reference file (e.g. WORKTREES.md) and linking to it one level deep, improving progressive disclosure.

Trim the explanatory prose in 'Reuse before creating' slightly; the numbered list is strong but steps 3-4 could be tightened to pure directives.

Dimension	Reasoning	Score
Conciseness	The body is largely lean and command-focused, but the dated line "As of 2026-02-13, current versions are conda 26.1.0, mamba/micromamba 2.5.0" is time-sensitive information not placed in an 'old patterns'/'deprecated' section, which the rubric penalizes.	2 / 3
Actionability	Fully executable, copy-paste-ready commands throughout (detection one-liner, `$CONDA_EXE env create -f environment.yml`, `$CONDA_EXE run -n CausalPy make setup`, troubleshooting `run -p` fallbacks).	3 / 3
Workflow Clarity	Clear sequenced decision flow (decide need → reuse → detect tool → create if needed → install → run → update) with explicit conditional checkpoints and a troubleshooting section providing error-recovery feedback loops.	3 / 3
Progressive Disclosure	Well-organized into clear sections with no nested references, but at ~100 lines with inline worktree/version troubleshooting detail and no progressive split or external references, some content that could be separated remains inline.	2 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 concise, well-constructed description that states concrete capabilities, an explicit "Use before" trigger, and natural example terms. It clearly answers both what the skill does and when to invoke it without padding.

Dimension	Reasoning	Score
Specificity	Lists concrete actions ("Detect, configure, and use a conda-compatible tool") alongside specific scenarios (importing project code, running tests, building docs, repo tooling), matching the multi-action anchor.	3 / 3
Completeness	Answers both what ("Detect, configure, and use a conda-compatible tool") and when via an explicit "Use before tasks that need the project environment, such as..." trigger clause.	3 / 3
Trigger Term Quality	Natural user-facing terms appear explicitly ("running tests", "building docs", "importing project code", "invoking repo tooling") beyond the technical "conda-compatible tool" phrasing.	3 / 3
Distinctiveness Conflict Risk	Scoped to a conda-compatible project-environment tool with concrete trigger scenarios, a clear niche unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 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: 7e23946

Reviewed: 13 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.