CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

69%

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-audio/SKILL.md
SKILL.md
Quality
Evals
Security

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 a dense, fact-rich reference with an executable core pattern and specific API details, and it avoids padding or explaining known concepts. Weaknesses are the inlined ~40-symbol API list, absent end-to-end code examples for speak/realtime, and references to files outside the skill bundle without clear navigation structure.

Suggestions

Move the 'Relevant API Surface' symbol list into a reference file (e.g., references/api-surface.md) and keep only the few symbols needed for audio work inline.

Add a complete, copy-paste-ready speak() or realtime event-folding example to close the actionability gap beyond the initialization snippet.

Convert package-path mentions ('API.md', 'axir-api.json', 'examples/') into clearly signaled references with context on where they live, or ship them as bundle reference files so navigation is unambiguous.

DimensionReasoningScore

Conciseness

The body is mostly dense, non-padded fact statements, but the 'Relevant API Surface' section inlines a ~40-symbol list ('AxBalancer', 'AxMeter', 'ProviderRouter', etc.) that could be tightened or moved to the already-referenced API docs. This matches anchor 3 ('mostly efficient but... could be tightened') rather than 4, which would require only minor trims.

3 / 5

Actionability

The 'Core Pattern' gives an executable code snippet ('llm = ai("openai", api_key=...)') and the audio-fields section gives exact key names, defaults ('gpt-4o-mini-tts', 'alloy'), and error behavior — concrete, executable guidance. It is not 5 because there is no complete end-to-end speak() or realtime code example, leaving a minor gap.

4 / 5

Workflow Clarity

There is no explicit multi-step sequence; the intended flow (start from examples, use the core pattern, apply field rules) is implicit in section ordering, and 'When To Use' bullets are not ordered steps. No destructive or batch operations are involved so no hard cap applies, but the implicit sequencing fits anchor 3 rather than 4.

3 / 5

Progressive Disclosure

The single file is well-sectioned and under 50 lines, but it points to package paths ('API.md', 'axir-api.json', 'examples/') that are not bundle files and not clearly signaled navigation, while inlining a large API-surface list that belongs in a separate reference. This matches anchor 3 ('some structure... references present but not clearly signaled; content that should be separate is inline').

3 / 5

Total

13

/

20

Passed

Description

67%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 solid description with an explicit 'Use when' trigger, a named package, and several concrete capability areas. Its main weakness is trigger-term coverage: natural user synonyms like speech, TTS, transcription, and voice are missing, which limits both completeness and distinctiveness.

Suggestions

Add natural trigger synonyms such as 'speech', 'text-to-speech (TTS)', 'transcription', and 'voice' so users' phrasing matches the description.

Enumerate the concrete actions more comprehensively (e.g., 'generate speech, transcribe audio input, map realtime events') instead of relying on umbrella phrases like 'audio input/output'.

Make the when-clause more specific about context, e.g., 'Use when writing Python code against the generated axllm package for speech, audio input, or realtime voice features.'

DimensionReasoningScore

Specificity

The description lists several concrete actions — "audio input/output", "OpenAI Responses audio mapping", "realtime event folding", and "generated package audio examples" — rather than vague language, though coverage of the audio workflow (e.g., speech generation, transcription) is implied rather than enumerated. It matches anchor 4 ('several specific actions; minor gaps') better than 5 because it is not comprehensive and better than 3 because it goes beyond 1-2 actions.

4 / 5

Completeness

It explicitly opens with "Use when writing Python code with `axllm` for...", answering both when and what (the enumerated audio tasks). It is not a 5 because the trigger guidance could name concrete user-facing phrases (speech, transcription, realtime events are only partially covered), matching anchor 4 ('both what and when; when could be more explicit or specific').

4 / 5

Trigger Term Quality

Relevant keywords like "audio", "realtime", and "Python" appear, but common natural variations users would say — "speech", "TTS", "transcription", "voice" — are absent. This fits anchor 3 ('some relevant keywords but missing common variations or synonyms'); it is above 2 because multiple domain keywords are present, and below 4 because key synonyms are missing.

3 / 5

Distinctiveness Conflict Risk

The named package `axllm` plus the specific audio/realtime niche makes it mostly distinct with only minor overlap risk against other Python LLM or audio skills. It falls short of anchor 5's 'clear niche with distinct triggers' because the audio terms alone could overlap generic audio/TTS skills.

4 / 5

Total

15

/

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-audio/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.