CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

69

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

72%

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

The content is highly actionable with executable code and a clear step sequence, but it is somewhat redundant in prose and omits validation/verification checkpoints for the fragile runtime setup. Tightening repetition and adding a verify step would lift the weaker dimensions.

Suggestions

Remove redundant restatements (the 'library fetches the code automatically' point and Pyodide load-size/timing facts each appear multiple times) to tighten conciseness.

Add an explicit verification checkpoint before the 'Done' section — e.g., a quick check that pythonRuntime is ready or that a sample Python tool executes — to strengthen workflow clarity.

Consolidate the loading-time/load-size notes into a single mention rather than repeating them in both the hook section and the loading-UI section.

DimensionReasoningScore

Conciseness

Mostly efficient and task-focused, but contains some unnecessary prose and redundancy (e.g. '~30MB, cached after first load' and 'First load is ~30-60s (downloads ~30MB)' repeat load-size facts; 'the library fetches the code automatically' is restated three times) that could be tightened.

2 / 3

Actionability

Provides complete, executable TSX code blocks for the runtime hook, useAtlasChat wiring, loading UI, and input disabling, plus exact install commands (pnpm add pyodide@0.29.3) and a hook API table — copy-paste ready.

3 / 3

Workflow Clarity

Steps are clearly sequenced (Prerequisite, Step 1–5, Done), but the fragile runtime-setup workflow lacks any explicit validation or verification checkpoint confirming Pyodide loaded or a Python tool actually executes before declaring completion.

2 / 3

Progressive Disclosure

Single self-contained SKILL.md, well-organized into prerequisite/background/steps/done sections with an API table and code blocks; no nested references (only a one-level pointer to the sibling integrate-atlas-chat skill), so structure is clear and navigable.

3 / 3

Total

10

/

12

Passed

Description

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.

The description is excellent: it names concrete actions, provides explicit trigger terms, answers both what and when, and explicitly distinguishes itself from a sibling skill. No significant gaps relative to the rubric anchors.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'pyodide installation, hook setup, loading UI, and chat hook wiring' — matching the anchor for specific concrete actions rather than vague domain+action phrasing.

3 / 3

Completeness

Clearly states what it does ('this skill handles...') and when to use it via an explicit 'MUST be used when...' plus 'Triggers:' clause, answering both what and when.

3 / 3

Trigger Term Quality

An explicit 'Triggers:' clause provides good coverage of natural terms (Pyodide, Python tools, pythonRuntime, usePyodideRuntime, runPythonCode, Python execution, client-side Python) a user would say.

3 / 3

Distinctiveness Conflict Risk

Niche is distinct and explicitly bounded from the sibling integrate-atlas-chat skill ('Do NOT manually configure...', 'Prerequisite: integrate-atlas-chat'), minimizing wrong-skill triggering.

3 / 3

Total

12

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

metadata_version

'metadata.version' is missing

Warning

Total

14

/

16

Passed

Repository
cognitedata/builder-skills
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.