ax-python-llm

Use when writing Python code with `axllm` for using the generated Ax package, factory functions, package docs, examples, and API reference.

Quality

70%

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

Fix and improve this skill with Tessl

tessl review fix ./packages/python/skills/ax-python-llm/SKILL.md

Quality

Content

65%

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 and well-organized with an executable core pattern, but actionability and workflow clarity are limited by a single init-only example and a symbol index with no usage or sequenced steps, while the referenced detail files are not provided.

Suggestions

Add at least one short executable example each for the main building blocks (signature/gen, agent, flow) so the API surface list is backed by runnable usage.

Reframe the referenced files as explicit navigation pointers (e.g., 'See API.md for full method signatures') and ensure those bundle files ship with the skill.

Add a brief ordered workflow (e.g., define signature → build gen → wrap in agent → compose flow → optimize) with a validation/check checkpoint for generated output.

Dimension	Reasoning	Score
Conciseness	The body is a lean quick reference that assumes Python competence — Package Facts, a single Core Pattern, a symbol index, and Guardrails — with every section earning its place and no padding about concepts Claude already knows.	3 / 3
Actionability	The Core Pattern is executable and copy-paste ready, but it only covers client initialization while the rest of the API surface (signatures, agents, flows, optimizers) is a list of names with no usage, and the referenced detail files (API.md, examples/) are not present in the bundle.	2 / 3
Workflow Clarity	The skill spans multiple operations (signatures, agents, flows, optimizers) but provides no sequenced workflow or validation checkpoints for them; only an implicit structure (When To Use → Core Pattern → API Surface → Guardrails) and a procedural hint in the Guardrails.	2 / 3
Progressive Disclosure	References to API.md, axir-api.json, axir-capabilities.json, and examples/ are present but listed as flat 'Package Facts' rather than clearly signaled navigation pointers, and none of these bundle files actually exist in the review directory to verify.	2 / 3
	Total	9 / 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 has an explicit 'Use when' trigger and a distinct, well-scoped niche, but its action specificity and trigger phrasing are weakened by generic verbs, a resource list, and an awkward grammatical construction.

Suggestions

Replace generic verbs ('writing', 'using') with concrete actions (e.g., 'build signatures, agents, flows, and optimizers with the `axllm` package').

Smooth the 'for using the generated Ax package, factory functions, package docs, examples, and API reference' clause into natural trigger phrasing users would actually say.

Lead with the concrete capability before listing the supporting resources (docs, examples, API reference).

Dimension	Reasoning	Score
Specificity	It names the domain ('writing Python code with `axllm`') and references resources ('factory functions, package docs, examples, and API reference'), but the verbs are generic ('writing', 'using') and the listed items are resources rather than concrete actions like 'extract' or 'fill'.	2 / 3
Completeness	It explicitly answers both what (writing Python code using the generated Ax package and its resources) and when, opening with an explicit 'Use when writing Python code with `axllm`' trigger.	3 / 3
Trigger Term Quality	Relevant keywords ('axllm', 'Ax package', 'Python code') appear, but they are padded with jargon ('factory functions', 'API reference') in an awkward 'for using...' construction and miss common natural variations a user might say.	2 / 3
Distinctiveness Conflict Risk	It is pinned to a clear niche — the specific `axllm` Python package — with distinct triggers, making it unlikely to fire for unrelated 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-llm/SKILL.md
Commit: fe8baf8

Reviewed: 4 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.