ax-cpp-llm

Use when writing C++ code with `axllm` for using the generated Ax package, factory functions, package docs, examples, and API reference.

Quality

61%

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-llm/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 skill body is concise and well organized with a usable core snippet and a thorough API surface, but its single code example is incomplete and the cross-file references are neither bundled nor clearly signaled. Adding a complete runnable example and proper linked references would lift actionability and progressive disclosure.

Suggestions

Make the Core Pattern snippet complete and runnable: include `<cstdlib>` for `std::getenv` (or a fallback) and show a minimal end-to-end call so it is copy-paste ready.

Convert the inline file mentions into clear markdown links (e.g. [API.md](API.md), [examples/](examples/)) and ensure those bundle files actually ship alongside the skill, or move the API surface list into a referenced reference file.

Add a short ordered workflow (pick example -> adapt signature/provider -> run no-key check -> swap real credentials) with an explicit validation checkpoint to improve workflow clarity.

Dimension	Reasoning	Score
Conciseness	The body is lean and well sectioned, assumes Claude's competence, and never explains concepts Claude already knows; the API surface list earns its place as reference material.	3 / 3
Actionability	There is one concrete Core Pattern snippet, but it is incomplete (`std::getenv` is used without `<cstdlib>`) and the bulk of the guidance is a symbol list rather than executable, copy-paste-ready examples.	2 / 3
Workflow Clarity	Sections (When To Use, Core Pattern, Guardrails) provide clear guidance for a reference skill, but there is no sequenced multi-step workflow with validation checkpoints, so it sits at the level-2 anchor.	2 / 3
Progressive Disclosure	The body references `API.md`, `axir-api.json`, `axir-capabilities.json`, and `examples/`, but no bundle files are present and the references use backtick filenames rather than signaled markdown links; the long API surface is inline rather than split out.	2 / 3
	Total	9 / 12 Passed

Description

57%

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 has an explicit trigger and a clear, distinct niche, but its capability statement reads as a list of resources with redundant phrasing rather than concrete actions. Tightening the 'what' into specific actions would raise specificity and completeness.

Suggestions

Rewrite the capability clause as concrete actions, e.g. 'Write C++ code against the generated `axllm` package: call factory functions, read package docs and examples, and consult the API reference.'

Remove the redundant 'with `axllm` for using the generated Ax package' construction to avoid repeating the package name.

Add common user-facing trigger variations such as 'C++ Ax programs', 'axllm examples', or 'Ax C++ API' to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (C++ with `axllm`) and several areas (factory functions, package docs, examples, API reference), but these are resources rather than concrete actions and the phrasing 'with `axllm` for using the generated Ax package' is redundant.	2 / 3
Completeness	It answers both 'when' (Use when...) and 'what', but the what-clause is weak and repetitive ('for using the generated Ax package, factory functions, package docs, examples, and API reference'), so it falls short of the clearly-articulated-both anchor at level 3.	2 / 3
Trigger Term Quality	The explicit trigger 'Use when writing C++ code with `axllm`' is a natural phrase, but coverage is narrow and misses common variations a user might say.	2 / 3
Distinctiveness Conflict Risk	The scope is tightly bound to the C++ `axllm` generated package, giving it a clear niche unlikely to conflict with other skills.	3 / 3
	Total	9 / 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-llm/SKILL.md
Commit: 16c2119

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.