ax-cpp-ai

Use when writing C++ code with `axllm` for named deployment profiles, generic provider clients, model selection, OpenAI-compatible calls, Responses, Gemini, Anthropic, routers, and balancers.

Quality

78%

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-ai/SKILL.md

Quality

Content

65%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 efficient, package-specific reference with concrete API surface and a solid core pattern, but it lacks explicit validation checkpoints in its workflows and references several bundle files that are not present in the skill.

Suggestions

Add the referenced bundle files (API.md, axir-api.json, axir-capabilities.json, examples/) or remove the references so navigation resolves.

Add explicit validation/verification steps (e.g., a check to run after constructing a client or selecting a profile) for destructive or batch operations to raise workflow clarity.

Convert a few more 'Use X for Y' rules into small inline code snippets so common cases are copy-paste ready without consulting examples.

Dimension	Reasoning	Score
Conciseness	The body is dense and largely assumes Claude's competence, with most lines carrying package-specific rules rather than general concept padding; a few slightly redundant defensive sentences keep it just below the lean/efficient anchor.	4 / 5
Actionability	Provides a concrete executable core pattern, exact factory functions, option names, and classes, plus pointers to runnable examples; minor gaps remain because most capabilities are described as rules with only one inline code block.	4 / 5
Workflow Clarity	A clear 'When To Use' list and sectioned rules give a usable sequence, but there are no explicit validation checkpoints the agent should run for risky operations, and 'fail before network I/O' is described as a behavior rather than a verification step.	3 / 5
Progressive Disclosure	Structure is good with clearly signaled one-level-deep references to API.md, axir-api.json, axir-capabilities.json, and examples/, but none of those bundle files actually exist in the skill, so the references do not resolve and navigation is incomplete.	3 / 5
	Total	14 / 20 Passed

Description

92%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 specific, well-triggered, complete, and distinct: it states what the skill does, when to use it, and lists concrete capabilities tied to the `axllm` package. The only minor gap is a few missing natural synonyms and file-extension trigger terms.

Dimension	Reasoning	Score
Specificity	Names the domain (C++ with `axllm`) and lists many specific concrete capabilities — named deployment profiles, generic provider clients, model selection, OpenAI-compatible calls, Responses, Gemini, Anthropic, routers, balancers — matching the comprehensive-coverage anchor.	5 / 5
Completeness	Explicitly answers both 'what' (writing C++ code with axllm for the listed capabilities) and 'when' via a concrete 'Use when...' trigger clause with specific triggers.	5 / 5
Trigger Term Quality	Good coverage of natural terms a user would say (writing C++ code, axllm, OpenAI-compatible calls, Responses, Gemini, Anthropic, routers, balancers), but a few synonyms and file/extension variants are missing, so it sits below the comprehensive-coverage anchor.	4 / 5
Distinctiveness Conflict Risk	Scoped to C++ with the specific `axllm` package and named features, giving it a clear niche with distinct triggers and minimal overlap with other skills.	5 / 5
	Total	19 / 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/cpp/skills/ax-cpp-ai/SKILL.md
Commit: 781623e

Reviewed: 4 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.