CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

62

Quality

73%

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

62%

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

The body is well-organized and appropriately assumes Claude's competence, and its single-task routing is clear. It is held back by a single client-construction code sample that never demonstrates the advertised audio/realtime capabilities, an inlined API symbol dump that belongs in the referenced API docs, and referenced bundle files that are not actually present.

Suggestions

Add at least one executable example showing the promised capability — e.g. an audio input/output call and a realtime event-folding snippet using no-key examples — so the Core Pattern covers more than client construction.

Move the inline "Relevant API Surface" symbol list into the referenced API docs (`API.md` / `axir-api.json`) and keep only the few entry-point symbols (e.g. `ai`, `OpenAIResponsesClient`) in SKILL.md to reduce token redundancy.

Ship the referenced bundle files (`API.md`, `axir-api.json`, `axir-capabilities.json`, `examples/`) alongside SKILL.md, or remove the dangling references, so the one-level-deep navigation actually resolves.

DimensionReasoningScore

Conciseness

The body is mostly lean and assumes competence, but the inline "Relevant API Surface" dump of ~30 symbol names duplicates what the referenced `API.md`/`axir-api.json` already provide, so it 'could be tightened' rather than earning the every-token-earns-its-place anchor.

2 / 3

Actionability

The only executable snippet (Core Pattern) merely constructs a client (`ai("openai", api_key=…)`); the actual audio I/O, realtime event folding, and OpenAI Responses mapping the skill promises have no concrete example, fitting 'some concrete guidance but incomplete; missing key details'.

2 / 3

Workflow Clarity

This is a simple, single-purpose skill under 50 lines with clear, well-organized sections and an unambiguous routing rule (no-key for local checks, provider-api for live calls), so the simple-skills carve-out lets it score 3 despite having no explicit multi-step sequence.

3 / 3

Progressive Disclosure

References are signaled one-level-deep ("Package API docs: `API.md` and `axir-api.json`", "Runnable examples: `examples/`"), but none of those files actually exist in the bundle and the API symbol list is inlined rather than split out, matching 'content that should be separate is inline' rather than the well-split score-3 anchor.

2 / 3

Total

9

/

12

Passed

Description

85%

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 specific, distinctive, and explicitly pairs a 'Use when…' trigger with a list of concrete audio capabilities. Its main weakness is terminology: the headline trigger leans on internal API jargon (e.g. 'realtime event folding') rather than the words a user would naturally say.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "audio input/output, OpenAI Responses audio mapping, realtime event folding, and generated package audio examples" — which matches the 'lists multiple specific concrete actions' anchor rather than the score-2 'some actions but not comprehensive'.

3 / 3

Completeness

Explicitly answers both: an explicit "Use when writing Python code with `axllm` for…" trigger (when) plus the enumerated audio capabilities (what), matching the 'clearly answers both what AND when with explicit triggers' anchor and clearing the 'Use when…' clause requirement.

3 / 3

Trigger Term Quality

Includes the natural term "audio input/output" but leans on technical jargon ("realtime event folding", "OpenAI Responses audio mapping") and omits common user-facing variations, fitting 'some relevant keywords but missing common variations' rather than full natural-term coverage.

2 / 3

Distinctiveness Conflict Risk

The conjunction of Python + `axllm` + audio + realtime event folding forms a clear niche unlikely to fire for unrelated skills, matching 'clear niche with distinct triggers; unlikely to conflict'.

3 / 3

Total

11

/

12

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.

Validation15 / 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
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.