ax-python-flow

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

Quality

87%

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

100%

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

The body is concise, highly actionable with complete executable examples, and well-organized with appropriate pointers to deeper package resources. It is a strong reference skill with no notable weaknesses against the rubric.

Dimension	Reasoning	Score
Conciseness	The body is lean and code-forward, assumes Claude's competence, and avoids explaining what flows or libraries are; the one-line prose intros under each pattern are brief orienting glue rather than padding.	3 / 3
Actionability	It provides multiple complete, copy-paste-ready Python blocks (flow().execute().returns() chains, typed ax() contracts, parallel fan-out, and a concrete forward() run call) plus a pointer to runnable examples.	3 / 3
Workflow Clarity	Patterns escalate cleanly from a core flow to variants to execution, and the forward() call serves as the run/verify step; no destructive or batch operations are involved so the missing-explicit-validation cap does not apply.	3 / 3
Progressive Disclosure	The skill is a self-contained, well-sectioned overview that signals one-level-deep offloading to the package's own materials ('API.md', 'axir-capabilities.json', 'examples/', and the dev gallery URL) rather than nesting references or inlining a wall of reference text.	3 / 3
	Total	12 / 12 Passed

Description

75%

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 distinctive and has an explicit 'Use when' trigger with clear package scoping, but its action vocabulary is thin and some trigger terms lean technical. Strengthening the verbs and trimming jargon would raise specificity and trigger-term quality.

Suggestions

Lead with concrete verbs over the components, e.g. 'Compose flows, nodes, and program graphs; build nested programs; configure dynamic options, caching, and optimizer components in Python with `axllm`.'

Replace jargon-heavy trigger terms ('program graphs', 'optimizer components') with phrasings a user would naturally say, or pair each with a plain-language equivalent.

Keep the explicit 'Use when' clause but tie the trigger to concrete user situations (e.g. building an LLM workflow graph, wiring typed flow nodes).

Dimension	Reasoning	Score
Specificity	The description names the domain (axllm) and enumerates many subsystem nouns ('flows, nodes, program graphs, nested programs, dynamic options, caching, and optimizer components') but relies on a single thin verb ('writing Python code ... for'), so it lists components rather than concrete actions like the score-3 anchor's 'extract, fill, merge'.	2 / 3
Completeness	It opens with an explicit 'Use when writing Python code with `axllm` for ...' clause that states both what the skill does and when to invoke it, satisfying the explicit-trigger requirement that prevents a cap at 2.	3 / 3
Trigger Term Quality	'Use when writing Python code' is natural but generic, and the trigger list mixes accessible terms ('flows', 'caching', 'nested programs') with technical jargon ('program graphs', 'dynamic options', 'optimizer components'), fitting 'some relevant keywords but missing common variations'.	2 / 3
Distinctiveness Conflict Risk	Scoping to a named package ('axllm') plus specific subsystems (flows, program graphs, optimizer components) carves a clear niche unlikely to trigger for unrelated Python skills.	3 / 3
	Total	10 / 12 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: fe8baf8

Reviewed: 5 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.