setup-python-tools
MUST be used when adding Pyodide or Python tool support to a Flows app. Do NOT manually configure usePyodideRuntime or wire pythonRuntime into useAtlasChat — this skill handles pyodide installation, hook setup, loading UI, and chat hook wiring. Prerequisite: integrate-atlas-chat (vendored src/atlas-agent + atlas chat wiring). Triggers: Pyodide, Python tools, pythonRuntime, usePyodideRuntime, runPythonCode, Python execution, client-side Python.
71
88%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Critical
Do not install without reviewing
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that clearly defines its scope, provides explicit trigger terms, states prerequisites, and even includes anti-patterns (what NOT to do). It effectively answers both what the skill does and when it should be used, with highly distinctive terminology that minimizes conflict risk.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'pyodide installation, hook setup, loading UI, and chat hook wiring.' Also specifies what NOT to do ('Do NOT manually configure usePyodideRuntime or wire pythonRuntime into useAtlasChat'), which adds clarity about the skill's scope. | 3 / 3 |
Completeness | Clearly answers both 'what' (handles pyodide installation, hook setup, loading UI, chat hook wiring) and 'when' ('MUST be used when adding Pyodide or Python tool support to a Flows app'). Also includes prerequisite information and explicit trigger terms. | 3 / 3 |
Trigger Term Quality | Explicitly lists natural trigger terms: 'Pyodide, Python tools, pythonRuntime, usePyodideRuntime, runPythonCode, Python execution, client-side Python.' These cover both user-facing language ('Python tools', 'Python execution', 'client-side Python') and technical identifiers ('usePyodideRuntime', 'runPythonCode'). | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: Pyodide/Python runtime integration specifically within a Flows app context. The prerequisite dependency ('integrate-atlas-chat') and specific technical terms like 'usePyodideRuntime' make it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable skill with clear step-by-step instructions and executable code examples. Its main weakness is moderate verbosity in the Background section explaining internal library mechanics that Claude doesn't need, and inline content (API reference, loading UI) that could benefit from being split into separate reference files. The workflow is well-sequenced with appropriate attention to error states and loading UX.
Suggestions
Trim or remove the 'Background' section — Claude doesn't need to understand the internal flow of how the library fetches Python tool code; just state that pythonRuntime handles execution automatically.
Consider moving the Hook API reference table and loading state UI snippets to a separate reference file to improve progressive disclosure and reduce the main skill's length.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill includes some unnecessary explanatory content (e.g., the 'Background' section explaining how atlas agents work internally, the flow description, and notes about what Python tools are). However, the core steps are reasonably lean with concrete code. The Hook API reference table is useful but the background section could be trimmed significantly. | 2 / 3 |
Actionability | Every step provides fully executable, copy-paste ready code with specific package versions, exact import paths, and concrete TSX snippets. The hook API reference table gives precise type information. The pyodide version is pinned with rationale. | 3 / 3 |
Workflow Clarity | The 5-step sequence is clearly ordered with explicit prerequisites (Step 1 reads files first), a logical progression from installation through wiring to UI concerns, and includes error handling UI (pythonError display) and loading state management. The prerequisite check and disabled-input step serve as validation checkpoints. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and headers, but it's somewhat monolithic — the Hook API reference, loading state UI snippets, and background explanation are all inline. The background section and API reference could be split out. References to the integrate-atlas-chat skill are present but the file paths for python modules could be clearer with a dedicated reference file. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
metadata_version | 'metadata.version' is missing | Warning |
Total | 9 / 11 Passed | |
- Repository
- cognitedata/builder-skills
- Commit
d6af887
- 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.