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

70%

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%Weight 40%Scale 1-3

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

The body is a lean, well-sectioned quick reference with one concrete executable snippet and exact API symbol names, scoring well on conciseness. It loses points on actionability and workflow clarity because most guidance is bare symbol lists with no usage examples or validation steps, and on progressive disclosure because the large inline API surface duplicates the referenced API.md.

Suggestions

Add 2-3 short copy-paste-ready snippets beyond the Core Pattern (e.g. building an AxGen, running an AxFlow, invoking AxBootstrapFewShot) so guidance is actionable, not just a symbol list.

Move the dense "Relevant API Surface" dump into the referenced API.md (or a bundle reference file) and keep only the top entrypoints inline, with clear one-level-deep links.

Add a brief ordered workflow for a representative task (e.g. pick entrypoint -> wire provider -> validate against a no-key example -> run) with an explicit validation checkpoint.

Dimension	Reasoning	Score
Conciseness	The body is lean bullet points plus a minimal code snippet, with no padding explaining what C++ or a package is. Matches score-3 "Lean and efficient; assumes Claude's competence; every token earns its place." Not 2 because there is no unnecessary concept explanation; the only mild redundancy (the intro restating the description) is insufficient to drop it.	3 / 3
Actionability	Quotes: a concrete executable snippet (`#include "axllm/axllm.hpp"` / `axllm::ai("openai", ...)`) and exact symbol names, but only one tiny example is given and most of the "Relevant API Surface" is bare names with no usage; full examples live only in referenced `examples/`. Matches score-2 "Some concrete guidance but incomplete; missing key details." Not 3 because it is not copy-paste ready across the skill's tasks; not 1 because real executable code and specific symbols are present.	2 / 3
Workflow Clarity	Quotes: Guardrails give light ordering ("Start from package examples ... before inventing a new call shape") and the Core Pattern shows a starting action, but there is no multi-step sequence or validation/checkpoint for the broader agent/flow/optimizer tasks. Matches score-2 "Steps listed but validation gaps; sequence present but checkpoints missing or implicit." Not 3 because no explicit validation/feedback loops exist; not 1 because some structure and ordering cues are present.	2 / 3
Progressive Disclosure	Quotes: sections (When To Use, Package Facts, Core Pattern, Relevant API Surface, Guardrails) are well organized, and references like `API.md`, `axir-api.json`, and `examples/` are signaled, but the dense inline "Relevant API Surface" duplicates content that belongs in the referenced API.md and no bundle files exist to offload detail into. Matches score-2 "content that should be separate is inline." Not 3 because the API surface is not appropriately split out; not 1 because sections are clear with no deep nesting.	2 / 3
	Total	9 / 12 Passed

Description

75%Weight 40%Scale 1-3

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 clearly targets a specific niche (C++ code generation with the axllm package) and includes an explicit 'Use when' trigger, satisfying completeness and distinctiveness. It is slightly weakened on specificity and trigger-term quality because it lists resources/objects rather than concrete actions and mixes in some technical jargon.

Suggestions

Replace resource nouns ("factory functions, package docs, examples, API reference") with concrete verbs the skill performs, e.g. "Generate Ax programs in C++, wire up providers, build agents/flows, and run optimizers."

Add user-natural phrasings alongside the jargon, e.g. "Use when writing or debugging C++ with axllm, or when porting Ax programs to C++."

Dimension	Reasoning	Score
Specificity	Quotes: "writing C++ code with `axllm`" names the domain, and "factory functions, package docs, examples, and API reference" lists capabilities, but these are resources/objects rather than concrete performed actions, matching the score-2 anchor "Names domain and some actions, but not comprehensive." Not 3 because it lacks multiple concrete verbs (e.g. extract/fill/merge); not 1 because the domain and several capabilities are explicitly named.	2 / 3
Completeness	Quotes: "Use when writing C++ code with `axllm`" provides an explicit when-trigger, and "for using the generated Ax package, factory functions, package docs, examples, and API reference" states what it does. Matches score-3 "Clearly answers both what AND when with explicit triggers." Not 2 because the 'Use when' clause is explicit (the guideline that a missing 'Use when' caps at 2 does not apply).	3 / 3
Trigger Term Quality	Quotes: "writing C++ code" and "`axllm`" are natural terms a user might say, but "generated Ax package" and "factory functions" lean technical. Matches score-2 "Some relevant keywords but missing common variations." Not 3 because coverage of natural phrasings is incomplete; not 1 because genuine natural trigger terms are present.	2 / 3
Distinctiveness Conflict Risk	Quotes: "writing C++ code with `axllm`" and "the generated Ax package" define a narrow, package-specific niche unlikely to collide with unrelated skills. Matches score-3 "Clear niche with distinct triggers; unlikely to conflict." Not 2 because the C++ + axllm scope is specific, not a broad overlap zone.	3 / 3
	Total	10 / 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: 9 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.