ax-cpp-ai

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

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-ai/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.

A concise, well-organized skill body with an executable core pattern and clear decision guidance. Its main weaknesses are that advanced routing/balancing flows are described rather than shown, and the referenced bundle files (API.md, axir-api.json, examples/) are not actually present.

Suggestions

Ship the referenced bundle files (API.md, axir-api.json, axir-capabilities.json, examples/ including adaptive_balancer_no_key) so the one-level-deep references resolve, or remove the references if the artifacts are not bundled.

Add a small runnable snippet for the adaptive-balancer or multi-service-router case so the core advanced flow is copy-paste ready rather than only described.

Add an explicit verification step (e.g. run a no-key example to confirm routing before committing changes) to turn the implicit sequence into a checkpointed workflow.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — it never explains what C++, a router, or a balancer is, and every section earns its place without padding; the long Relevant API Surface line is reference material, not explanatory verbosity.	3 / 3
Actionability	The Core Pattern is fully executable copy-paste C++ and the API surface lists concrete symbols, but the routing/balancing guidance describes behavior ("Use the multi-service router when...") and defers to examples/ rather than showing runnable code, leaving key flows incomplete.	2 / 3
Workflow Clarity	When-to-use decision guidance and ordering cues ("Start from package examples...", "Start with examples/adaptive_balancer_no_key... then...") give a light sequence, but there are no explicit validation/verification checkpoints or error-recovery feedback loops.	2 / 3
Progressive Disclosure	Content is cleanly sectioned and signals one-level-deep references (API.md, axir-api.json, axir-capabilities.json, examples/), but none of those bundle files actually exist in the skill directory, so the referenced navigation does not resolve.	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.

A specific, well-scoped description with an explicit use-when trigger and comprehensive capability list. Its main weakness is trigger-term naturalness, leaning on SDK jargon (routers, balancers, Responses) rather than phrasing users would naturally invoke.

Suggestions

Reframe some jargon as user-facing verbs in the description (e.g. "route between providers" and "fail over on errors" alongside "routers and balancers") so the trigger matches how users actually ask.

Add a couple of natural variations users might say (e.g. "OpenAI/Gemini/Anthropic client", "multi-provider failover") to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the language (C++), package (axllm), and lists multiple concrete capabilities — "provider clients, model selection, OpenAI-compatible calls, Responses, Gemini, Anthropic, routers, and balancers" — matching the multiple-specific-actions anchor.	3 / 3
Completeness	It explicitly answers what (the listed capabilities) and when (the explicit "Use when writing C++ code with axllm..." clause), matching the both-what-and-when-with-explicit-triggers anchor.	3 / 3
Trigger Term Quality	"Use when writing C++ code with axllm" and the named providers give relevant natural keywords, but several terms ("routers and balancers", "Responses") are SDK jargon more than what a user would naturally say, leaving common variations partly uncovered.	2 / 3
Distinctiveness Conflict Risk	Narrowly scoped to C++ plus the axllm package with named providers and routing concepts, forming a clear niche unlikely to trigger for unrelated skills.	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-ai/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.