ax-python-audio

Use when writing Python code with `axllm` for audio input/output, OpenAI Responses audio mapping, realtime event folding, and generated package audio examples.

Quality

72%

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-audio/SKILL.md

Quality

Content

57%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 organized and concise with sensible guardrails and a runnable starting snippet, but it under-delivers on the skill's core audio/realtime tasks and inlines a lengthy API dump that belongs in the referenced API.md. No bundle files are present to validate the referenced paths against.

Suggestions

Add a copy-paste-ready example for the primary tasks (audio input/output and realtime event folding), not just client construction, so actionability reaches the common cases.

Move the flat Relevant API Surface name list into the referenced API.md and keep only the handful of entry points agents actually call, reducing inline duplication.

Add an explicit validate-then-proceed checkpoint (e.g., run a no-key example to confirm request mapping before using live provider credentials) to give the workflow a clear feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence (no explanation of what audio or Python is), with only minor trimmable items like "Language: Python" and the flat API-name dump that could be tightened.	4 / 5
Actionability	Provides one executable Core Pattern snippet and concrete guardrails, but the single example only shows client construction and omits the actual audio I/O, event folding, and provider-mapping code that the skill is for.	3 / 5
Workflow Clarity	Guardrails imply a loose sequence (start from examples, use no-key for checks, provider-api only with credentials) but there are no explicit validation checkpoints or feedback loops tying the steps together.	3 / 5
Progressive Disclosure	Sections are clearly headed and reference one-level-deep files (API.md, axir-api.json, examples/), but the long inline Relevant API Surface list duplicates material that the separately referenced API.md should hold.	3 / 5
	Total	13 / 20 Passed

Description

87%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 is well-constructed: it uses third-person/trigger voice, names concrete audio-specific capabilities, and provides an explicit "Use when" trigger with concrete phrases. Its only weakness is slightly limited keyword synonym coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — "audio input/output", "OpenAI Responses audio mapping", "realtime event folding", and "generated package audio examples" — but coverage is narrow to the audio niche, leaving minor gaps rather than full comprehensiveness.	4 / 5
Completeness	Explicitly answers both what (writing Python code with `axllm` for the listed audio tasks) and when via a clear "Use when writing Python code with `axllm` for..." trigger clause with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural, user-sayable terms like "Python code", "audio input/output", and "realtime events" with good coverage, though a few synonyms or common variations are absent.	4 / 5
Distinctiveness Conflict Risk	Targets a clearly defined niche (axllm audio I/O, OpenAI Responses audio mapping, realtime event folding) with distinct triggers and minimal overlap with other skills.	5 / 5
	Total	18 / 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-audio/SKILL.md
Commit: 781623e

Reviewed: ~11 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.