ax-cpp-gen

Use when writing C++ code with `axllm` for AxGen programs, forward calls, streaming, tools, assertions, traces, usage, and output parsing.

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-gen/SKILL.md

Quality

Content

72%

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

The body is concise and well-organized for a simple code-generation skill, with a useful guardrails section. Its weaknesses are actionability (the Core Pattern snippet is not standalone-executable) and workflow clarity (no explicit validation/verification checkpoint before relying on generated output).

Suggestions

Make the Core Pattern example complete and copy-paste runnable: add the necessary includes and show how `llm` is obtained, or explicitly label it as a fragment that assumes a configured client.

Add an explicit verification step to the workflow, e.g. compile/run a no-key example to confirm the generated call shape works before extending it.

Clarify that referenced paths like `examples/` and `API.md` are inside the generated `axllm` package, so Claude knows where to look.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: short sections (Package Facts, Core Pattern, Relevant API Surface, Guardrails) with no concept explanations or padding. It is not 2 because nothing here is unnecessary or loosen-able, and time-sensitive version info lives in frontmatter rather than the body.	3 / 3
Actionability	The Core Pattern code references an undefined `llm` with no includes or setup, so it is not copy-paste executable, and 'Relevant API Surface' is a listing rather than runnable guidance. It is not 1 because concrete code and specific API symbols are present, and not 3 because the example is incomplete rather than fully executable/copy-paste ready.	2 / 3
Workflow Clarity	The Guardrails give ordered guidance ('Start from package examples... before inventing', 'Use provider-api only when...'), but there are no explicit validation checkpoints or feedback loops for the generated-package workflow. It is not 1 because steps are sequenced and unambiguous, and not 3 because no explicit validate/verify step is present for a code-generation task.	2 / 3
Progressive Disclosure	The skill is under 50 lines with no bundle directories and is organized into clear, well-labeled sections, so per the simple-skills note it qualifies for a top score on organization alone. It is not 2 because the structure is clean and the inline references (API.md, axir-api.json, examples/) point to package-internal docs rather than requiring multi-level navigation.	3 / 3
	Total	10 / 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, complete, and clearly scoped to a distinct C++/axllm niche with an explicit Use-when trigger. Its main weakness is trigger-term quality: several listed terms are internal jargon rather than phrases a user would naturally say.

Suggestions

Add user-natural phrasing alongside technical terms, e.g. 'Use when generating or calling LLM programs in C++, sending prompts, streaming responses, or attaching tools' so triggers match how users actually ask.

Consider pruning internal-sounding terms like 'assertions, traces, usage' from the description unless they map to things users request by name.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions ('forward calls, streaming, tools, assertions, traces, usage, and output parsing') tied to a named domain (C++ with axllm), matching the 'lists multiple specific concrete actions' anchor. It is not score 2 because the action enumeration is comprehensive rather than partial.	3 / 3
Completeness	An explicit 'Use when writing C++ code with `axllm` for AxGen programs...' clause answers when, and the enumerated capabilities answer what, matching the 'clearly answers both what AND when with explicit triggers' anchor. It is not 2 because the when-guidance is explicit, not merely implied.	3 / 3
Trigger Term Quality	'writing C++ code' is a natural user phrase, but several listed triggers ('assertions', 'traces', 'usage', 'forward calls') are internal/technical jargon rather than terms a user would naturally say, and common variations are missing. It is not 3 because natural-term coverage is incomplete, and not 1 because 'writing C++ code' and 'AxGen programs' are genuine relevant keywords.	2 / 3
Distinctiveness Conflict Risk	The niche is tightly scoped to C++ with the generated `axllm` package for AxGen programs, giving distinct triggers unlikely to fire for other skills. It is not 2 because the C++/axllm/AxGen scoping is far more specific than 'works with document files'-level overlap.	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-gen/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.