ax-cpp-audio

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

Quality

75%

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/cpp/skills/ax-cpp-audio/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 commendably concise and well-sectioned with a concrete entry-point snippet, but it reads as a reference card rather than an actionable workflow: the API surface is a symbol dump, there is no complete runnable example, and the referenced bundle files do not exist to back the progressive-disclosure pointers.

Suggestions

Add one complete, runnable C++ example (include + client creation + an actual audio call) so the Core Pattern graduates from a one-liner to copy-paste-ready guidance.

Convert the workflow into an explicit sequence (e.g., 1. Check `examples/` for the closest native syntax, 2. Respect guardrails on `provider-api` vs `no-key`, 3. Verify AxIR source-of-truth) so the single task is unambiguously ordered.

Either ship the referenced bundle files (`API.md`, `axir-api.json`, `axir-capabilities.json`, `examples/`) or move the inline API-surface symbol list into one of them, so progressive-disclosure pointers resolve to real artifacts.

Dimension	Reasoning	Score
Conciseness	The body is lean: short bullets, a single code snippet, and a dense symbol list, with no concept-explanation padding and no "what a library is" filler, matching the lean-and-every-token-earns-its-place anchor rather than the mostly-efficient-but-could-be-tightened anchor at 2.	3 / 3
Actionability	The Core Pattern provides an executable `axllm::ai(...)` snippet and Package Facts names concrete artifacts, but the Relevant API Surface is a symbol dump without call shapes and there is no end-to-end runnable example, fitting the some-concrete-guidance-but-incomplete anchor rather than fully-copy-paste-ready at 3.	2 / 3
Workflow Clarity	Guidance exists via When To Use, Core Pattern, and Guardrails, but it is presented as a reference sheet rather than a sequenced workflow with checkpoints, fitting the steps-present-but-no-explicit-sequence/checkpoints anchor; it is not 1 because the single task is reasonably clear, and not 3 because no explicit sequence is given.	2 / 3
Progressive Disclosure	Sections are clearly organized and references to `API.md`, `axir-api.json`, `axir-capabilities.json`, and `examples/` are one-level-deep and signaled, but no bundle directory exists so those references cannot be verified as real files, and the large inline API-surface symbol list is content that could live in a referenced file, fitting the some-structure-but-could-be-better-organized anchor rather than the clearly-split anchor at 3.	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 and distinctive, with an explicit trigger clause and four named capabilities. Its main weakness is trigger-term naturalness: several phrases are internal/technical jargon a user would be unlikely to say verbatim.

Suggestions

Add natural user-facing trigger terms (e.g., "audio streaming", "speech-to-text", "realtime voice", "play/record audio") alongside the technical ones so the skill fires on how users actually phrase requests.

Lead with a brief declarative capability statement ("Generates C++ audio I/O and realtime streaming code with `axllm`...") before the "Use when" clause so "what it does" is stated explicitly rather than only implied inside the trigger.

Dimension	Reasoning	Score
Specificity	Names the domain (C++ audio with `axllm`) and four concrete actions: "audio input/output, OpenAI Responses audio mapping, realtime event folding, and generated package audio examples," matching the multiple-specific-actions anchor rather than the domain-and-some-actions anchor at 2.	3 / 3
Completeness	Opens with an explicit "Use when..." clause (the when) and enumerates concrete actions (the what), satisfying the both-what-and-when-with-explicit-triggers anchor; it is not 2 because the trigger clause is present rather than missing or only implied.	3 / 3
Trigger Term Quality	Phrases like "writing C++ code" and "audio input/output" are natural, but "OpenAI Responses audio mapping" and "realtime event folding" lean technical and miss common user phrasings, fitting the some-relevant-keywords-but-missing-variations anchor rather than full natural coverage at 3.	2 / 3
Distinctiveness Conflict Risk	The C++ + `axllm` + audio/realtime niche with triggers like "realtime event folding" is a clear, distinct niche unlikely to fire for unrelated skills, matching the clear-niche anchor rather than the could-still-overlap anchor at 2.	3 / 3
	Total	11 / 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/cpp/skills/ax-cpp-audio/SKILL.md
Commit: 9087a01

Reviewed: 5 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.