environment-setup

Use when Python environment setup is needed for data visualization or conda installation is required

Quality

71%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/environment-setup/SKILL.md

Quality

Content

92%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.

The body is a lean, highly actionable runbook with concrete executable commands for macOS, Linux, and Windows, a clear sequenced workflow, an explicit self-check validation step, and a troubleshooting/feedback section. Its main weakness is structure: everything lives in one monolithic file with no progressive disclosure to separate reference files.

Suggestions

Split the platform-specific Miniconda install flows and the troubleshooting recipes into one-level-deep reference files (e.g. references/install-macos.md, references/install-windows.md, references/troubleshooting.md) and link to them from a concise overview to improve progressive disclosure.

Add an explicit validation gate before the HARD-GATE (e.g. abort and surface the self-check output if 'ENV CHECK: OK' is not printed) so the feedback loop is enforced rather than advisory.

Consider moving the optional/extra dependencies and the pip mirror config into a reference so the core path stays under ~50 lines.

Dimension	Reasoning	Score
Conciseness	The body is dominated by executable bash/powershell/python blocks and a tight checklist with almost no explanation of concepts Claude already knows; minimal prose ('本技能用于在终端完成 Python 画图环境的全流程配置') and every block earns its place, matching the 'lean and efficient; assumes Claude's competence' anchor.	3 / 3
Actionability	It provides copy-paste-ready, fully executable commands throughout — OS detection, silent Miniconda install for macOS/Linux and Windows, conda env creation, pip installs, an ipykernel registration, and a Python self-check — fitting 'fully executable code/commands; specific examples; copy-paste ready'.	3 / 3
Workflow Clarity	A numbered checklist plus sections 一–八 give a clear sequence (identify system → install → create env → install deps → self-check), with an explicit validation checkpoint (the self-check prints 'ENV CHECK: OK') and a troubleshooting/feedback section (常见问题与修复) for error recovery, matching the level-3 anchor with checklists and validation.	3 / 3
Progressive Disclosure	No bundle files exist and the skill is a single ~175-line monolithic file; sections are well-organized but platform-specific flows and the troubleshooting block are inline rather than split into one-level-deep references, fitting 'some structure but content that should be separate is inline' rather than the split-and-signaled level-3 pattern.	2 / 3
	Total	11 / 12 Passed

Description

50%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.

The description leads with an explicit 'Use when' trigger and targets a recognizable niche (conda/Python setup for data visualization), but it is terse and one-sided: it conveys 'when' more clearly than 'what', and lacks the breadth of natural trigger terms and concrete actions that would distinguish it from generic Python environment skills.

Suggestions

Lead with a concrete capability statement before the trigger, e.g. 'Installs Miniconda, creates a research conda environment, and installs data-visualization dependencies (numpy, pandas, matplotlib, seaborn).'

Expand trigger terms to natural user phrasings such as 'install miniconda', '用 Python 画图', 'create virtual environment', and 'matplotlib/conda not found' to improve trigger coverage and distinctiveness.

Tighten the niche by mentioning the self-check / progress.md write-back so it is clearly distinguishable from a generic Python setup skill.

Dimension	Reasoning	Score
Specificity	Phrases like 'Python environment setup' and 'conda installation' name the domain and one concrete action, but the description does not enumerate the specific operations the skill performs (create env, install deps, run self-check), matching the 'names domain and some actions, but not comprehensive' anchor rather than the multi-action level 3.	2 / 3
Completeness	It has an explicit 'Use when ... is needed ... or ... is required' trigger clause (the 'when'), but the 'what does this do' is only weakly implied as 'environment setup' — there is no clear statement of capability, so it does not reach the 'clearly answers both what AND when' bar of level 3.	2 / 3
Trigger Term Quality	'Python environment setup', 'data visualization', and 'conda installation' are relevant terms a user might say, but coverage is thin — common variations users actually say (e.g. '用 Python 画图', 'matplotlib', '虚拟环境', 'install miniconda') are absent, fitting 'some relevant keywords but missing common variations' better than the broad level-3 coverage.	2 / 3
Distinctiveness Conflict Risk	The 'conda installation' + 'data visualization' framing gives it a recognizable niche, but the broader 'Python environment setup' phrasing could overlap with a general Python/dev-environment skill, matching 'somewhat specific but could still overlap with similar skills' rather than a clearly non-conflicting level 3.	2 / 3
	Total	8 / 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: Norman-bury/research-writing-skill
Path: skills/environment-setup/SKILL.md
Commit: 6f79595

Reviewed: 10 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.