ax-python-flow

Use when writing Python code with `axllm` for flows, nodes, program graphs, nested programs, dynamic options, caching, and optimizer components.

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

86%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 well-structured, token-efficient skill body that leads with executable patterns and clear guardrails, deferring detail to package examples and manifests via well-signaled references. The main gap is that some example flow nodes are referenced before being defined, slightly reducing self-contained actionability.

Suggestions

Define or stub the helper nodes (research, audience, join, critique, revise) used in the parallel and refine examples, or explicitly note they are constructed with the same `ax(...)` contract shown earlier, so each example is fully self-contained.

Add a brief verification checkpoint after 'Run a flow' (e.g., checking returned keys against `.returns(...)`) so generated flow output can be validated before use.

Clarify that the `examples/` and external gallery links are where to find the complete runnable programs, making the handoff from the inline patterns to the bundle explicit.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: each pattern is a one-line rationale plus an executable block, with no padding or explanation of concepts Claude already knows.	5 / 5
Actionability	It provides concrete, copy-paste-ready code covering core cases (typed programs, branch, parallel, refine, run), but referenced nodes like `research`, `critique`, and `join` are used without being defined, leaving a minor gap in fully self-contained executability.	4 / 5
Workflow Clarity	Patterns are clearly sequenced and the 'Run a flow' section gives the execution step, but there is no explicit validation checkpoint for verifying generated flow output, so it stops just short of the highest anchor.	4 / 5
Progressive Disclosure	Content is organized into clear sections with one-level-deep, clearly signaled references to `examples/`, `API.md`, `axir-api.json`, and an external gallery, keeping the overview concise while routing detail to the right artifacts.	5 / 5
	Total	18 / 20 Passed

Description

92%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, specific description that names the package and enumerates concrete capabilities while providing an explicit 'Use when...' trigger. It is highly distinctive and complete, with only minor room for more natural synonym coverage in its trigger terms.

Dimension	Reasoning	Score
Specificity	The description names the package (`axllm`) and lists many concrete capabilities — 'flows, nodes, program graphs, nested programs, dynamic options, caching, and optimizer components' — giving comprehensive coverage of specific actions rather than vague language.	5 / 5
Completeness	It explicitly answers both 'what' (writing Python code with axllm for the listed components) and 'when' via the explicit 'Use when...' trigger clause.	5 / 5
Trigger Term Quality	Natural phrases like 'writing Python code', 'flows', 'nodes', and 'caching' are present, but the bulk of the terms are domain jargon with few common synonyms or variations a user would naturally say, so it sits just below the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	It is tightly scoped to the generated `axllm` Python package and its flow subsystem, forming a clear niche with distinct triggers and minimal overlap with unrelated skills.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: ax-llm/ax
Path: packages/python/skills/ax-python-flow/SKILL.md
Commit: 1abea97

Reviewed: ~17 hours 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.