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

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 ./website/static/cpp/.well-known/agent-skills/ax-cpp-llm/SKILL.md

Quality

Content

75%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 a disciplined quick reference: terse factual sections, one executable pattern, and guardrails that encode ordering, a local-verification path (no-key transport), and a doc-conflict feedback loop. Its main weaknesses are mild redundancy, reliance on external examples for concrete syntax, and an inline API inventory that overlaps the separate API reference.

Suggestions

Add one or two more complete executable snippets (e.g. building a signature with `axllm::s` and running `axllm::ax`) so common cases are copy-paste ready without opening examples/.

Trim the inline "Relevant API Surface" symbol list to the handful of entry points, deferring the full inventory to `API.md`/`axir-api.json` to reduce duplication.

Deduplicate the TypeScript-imports warning (stated in both the intro and When To Use) into a single guardrail.

Dimension	Reasoning	Score
Conciseness	The body is lean and fact-dense ("Real network support: yes.", "Runtime profiles: `javascript-quickjs`, `python-pyodide`.") with no explanations of concepts Claude already knows. Falls short of 5 due to redundancy: "do not import TypeScript-only APIs" in the intro repeats as "without TypeScript-only imports" under When To Use, and Package Facts restates the title's language and package name.	4 / 5
Actionability	Provides an executable core pattern ("#include "axllm/axllm.hpp"" and "axllm::ai("openai", { {"apiKey", std::getenv("OPENAI_API_KEY")} })") plus an exhaustive inventory of concrete symbols. Not a 5 because it shows only one call shape and defers most real syntax to external examples ("Start from package examples for exact native syntax before inventing a new call shape").	4 / 5
Workflow Clarity	Directional sequencing and checkpoints are present: consult examples before inventing call shapes, "Use `no-key` examples for deterministic local checks", and a conflict-resolution feedback loop ("if package docs disagree with source code, update the compiler and regenerate packages"). Not a 5 because there is no explicit validate-before-proceed step for the code the agent writes.	4 / 5
Progressive Disclosure	Sections are well organized and external materials are clearly signaled ("Package API docs: `API.md` and `axir-api.json`", "Runnable examples: `examples/`"). Not a 5 because the ~40-symbol "Relevant API Surface" list inlines content that duplicates the separate API reference, and the referenced paths are plain names rather than links; no bundle files exist alongside SKILL.md to verify them.	4 / 5
	Total	16 / 20 Passed

Description

73%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 has an explicit "Use when" trigger naming the C++/axllm niche, giving it strong distinctiveness and good trigger terms, but the capability half is a run-on resource list ("for using the generated Ax package, factory functions, package docs, examples, and API reference") rather than concrete actions. Rewriting it as verb-led actions would lift specificity and completeness.

Suggestions

Replace the resource-list clause with concrete verb-led actions, e.g. "Builds Ax programs in C++ with `axllm`: constructs signatures, generators, agents, flows, and optimizers using the package API, examples, and manifests."

Fix the grammatical tangle "with `axllm` for using the generated Ax package" so the what and when read as two clean sentences.

Add one or two natural synonyms (e.g. "Ax LLM", "axllm API") to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and one concrete action ("writing C++ code with `axllm`"), but "using the generated Ax package, factory functions, package docs, examples, and API reference" is a list of resources rather than specific actions, leaving coverage incomplete.	3 / 5
Completeness	Both parts are present: an explicit when ("Use when writing C++ code with `axllm`") and a what ("using the generated Ax package, factory functions, package docs, examples, and API reference"), though the what-clause is garbled ("with `axllm` for using...") and could be more precise.	4 / 5
Trigger Term Quality	"C++ code", "`axllm`", "Ax package", and "API reference" are natural terms a user needing this skill would say. Falls short of 5 because no synonyms or variations (e.g. "Ax in C++", "axcpp", "LLM API") are included.	4 / 5
Distinctiveness Conflict Risk	"C++ code with `axllm`" identifies a clear niche around a named generated package; triggers are distinct and conflict risk with other skills is minimal.	5 / 5
	Total	16 / 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: website/static/cpp/.well-known/agent-skills/ax-cpp-llm/SKILL.md
Commit: 3f630a0

Reviewed: 3 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.