ax-cpp-flow

Use when writing C++ code with `axllm` for flows, nodes, program graphs, nested programs, dynamic options, caching, and optimizer components.

Quality

92%

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

Quality

Content

85%

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

A well-organized, code-forward skill that uses progressive disclosure effectively and stays concise. Its main weakness is actionability: several inline examples reference undefined nodes and an undefined provider `client`, so they are not fully copy-paste ready.

Suggestions

Define the provider `client` (or show where it comes from) so the 'Run a flow' `.forward(client, ...)` example is executable end-to-end.

In the parallel fan-out and draft/critique/revise examples, define the referenced ax nodes (`research`, `audience`, `join`, `critique`, `revise`) the way `classifier`/`responder` are defined, so each example is self-contained.

Mark which examples are illustrative snippets versus complete runnable programs, making it explicit when the agent should assemble the full program from `examples/`.

Dimension	Reasoning	Score
Conciseness	Lean and code-forward: each pattern is a one-line description followed by a code block, with no padding explaining concepts Claude already knows; every section earns its place.	3 / 3
Actionability	The core and branch-flow examples are complete C++, but 'Run a flow' relies on an undefined `client` and the parallel/refine examples reference ax nodes (`research`, `audience`, `join`, `critique`, `revise`) that are never defined — key details missing for copy-paste execution.	2 / 3
Workflow Clarity	Clear logical progression (When To Use → Package Facts → Core Pattern → More Patterns → Run → Guardrails) with decision guidance; this is a pattern catalog, not a destructive/batch operation, so the well-organized structure qualifies for 3 without explicit validation loops.	3 / 3
Progressive Disclosure	SKILL.md is a clean overview that defers detail to well-signaled one-level-deep references (`API.md`, `axir-api.json`, `axir-capabilities.json`, `examples/`, and the online gallery), keeping the body appropriately split.	3 / 3
	Total	11 / 12 Passed

Description

100%

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 strong, concise description with an explicit 'Use when' trigger and seven concrete capability areas. It is distinctive and free of fluff, closely matching the rubric's good examples.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — 'flows, nodes, program graphs, nested programs, dynamic options, caching, and optimizer components' — rather than vague language, matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	The 'Use when writing C++ code with `axllm` for ...' clause gives an explicit trigger (when) and names the coding activity plus its scope (what); it is not capped at 2 because an explicit 'Use when' trigger is present.	3 / 3
Trigger Term Quality	Pairs an explicit 'Use when' trigger with natural domain terms an axllm user would say ('C++ code', 'flows', 'nodes', 'caching'), giving good coverage rather than only internal jargon.	3 / 3
Distinctiveness Conflict Risk	Tightly scoped to 'C++ code with `axllm`' and specific flow components, creating a clear niche unlikely to trigger for unrelated skills.	3 / 3
	Total	12 / 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-flow/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.