CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

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
SKILL.md
Quality
Evals
Security

Quality

Content

78%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.

The body is an exemplary router-style overview: a task-to-guide table with verified, one-level-deep references and tight conventions, with no wasted explanation. The only gaps are minor — a couple of trimmable filler lines and a version-check step without explicit instructions.

DimensionReasoningScore

Conciseness

The body is a lean, table-driven overview with no explanations of concepts Claude already knows; only minor filler could be trimmed ('Specialist skills remain optional when separate skill entries are useful' and the redundant opening sentence restating the description). It fits anchor 4 (efficient with minor instances that could be trimmed) rather than anchor 5's every-token-earns-its-place.

4 / 5

Actionability

Concrete per-task pointers ('Read [Quick reference](references/quickstart.md)') and specific artifacts ('API.md', 'axir-api.json', 'axir-capabilities.json') give mostly executable guidance. It falls short of anchor 5 because there is no code or command example and the version-check convention lacks a specific how.

4 / 5

Workflow Clarity

A clear sequence is present: pick a guide from the table, read it before writing code, check the installed version against the guide version, and consult the API manifests for exact signatures. This is a read-and-code router, not a destructive or batch operation, so no validation cap applies; it misses anchor 5 only because there is no explicit checkpoint or recovery guidance for a version mismatch.

4 / 5

Progressive Disclosure

The body is a concise overview with a task-to-guide table whose 16 referenced files all exist in references/ and are exactly one level deep (no reference file links further into the bundle). This matches anchor 5: clear overview, well-signaled one-level-deep references, and easy navigation.

5 / 5

Total

17

/

20

Passed

Description

53%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.

The description has an explicit trigger clause and a distinctive package name, but the capability statement is circular ('for using the generated Ax package') and trigger-term coverage lacks natural synonyms. It reads as a moderately effective trigger description with clear room to state concrete actions and richer keywords.

Suggestions

Replace the circular 'for using the generated Ax package' with concrete actions, e.g. 'Write Python code with the `axllm` package: factory functions, signatures, providers, agents, flows, and optimizers.'

Add natural trigger terms and synonyms users would actually say, such as 'Ax', 'LLM agents', 'prompt engineering', or 'model routing', so the skill fires on phrasing beyond the literal package name.

State what the skill provides (bundled guides, examples, and API reference for the generated package) as a distinct 'what' sentence before the 'Use when...' clause.

DimensionReasoningScore

Specificity

Names the domain ('writing Python code with `axllm`') and lists resources ('factory functions, package docs, examples, and API reference'), but these are objects rather than actions and 'for using the generated Ax package' is circular. It matches anchor 3 (domain plus limited concrete actions) rather than 4, which requires several specific actions.

3 / 5

Completeness

The 'when' is explicit ('Use when writing Python code with `axllm`') but the 'what' is vague and circular ('for using the generated Ax package'). It sits below anchor 4 because the 'what' does not clearly state what the skill provides, yet above anchor 2 because a clear 'when' clause exists.

3 / 5

Trigger Term Quality

Relevant keywords are present ('Python code', 'axllm', 'package docs', 'API reference') but common variations users would naturally say are missing (e.g. 'Ax', 'LLM', 'agents', 'signatures'). This fits anchor 3 — some relevant keywords but missing common variations — rather than anchor 4's good coverage with only a few gaps.

3 / 5

Distinctiveness Conflict Risk

The specific package name `axllm` establishes a clear niche with distinct triggers, giving minor overlap risk only with closely related Ax-family skills. It falls short of anchor 5 because generic phrases like 'package docs, examples, and API reference' could collide with sibling package-documentation skills.

4 / 5

Total

13

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

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

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.