ax-rust-flow

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

Quality

85%

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

87%

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

A lean, highly actionable pattern catalog with executable Rust examples and well-signaled external references, weakened only by the absence of an explicit ordered workflow with checkpoints.

Suggestions

Add a short 'Build a flow' numbered procedure (define ax nodes -> compose flow with reads/writes -> returns -> forward -> check errors) so the end-to-end workflow is explicit rather than inferred from examples.

Trim one of the similar execute_with_options examples (e.g., the draft/critique/revise linear case) if the dependency-wiring pattern is already covered, to tighten token use.

Dimension	Reasoning	Score
Conciseness	The body is code-forward and lean: each section is a one-line description plus an executable snippet, with no padding explaining concepts Claude already knows.	3 / 3
Actionability	Multiple complete, executable Rust snippets ("axllm::ax(...)", "axllm::flow(...).execute_with_options(...).returns(...)", ".forward(&mut client, ...)") give copy-paste-ready guidance with concrete read/write contracts.	3 / 3
Workflow Clarity	Each example shows a consistent build sequence (define nodes -> compose flow with reads/writes -> returns -> forward), but there is no overarching ordered procedure or validation checkpoints for choosing and applying the patterns.	2 / 3
Progressive Disclosure	The SKILL.md is a concise overview that signals one-level-deep references ("examples/", "API.md", "axir-api.json", and the web gallery) rather than inlining them, with clear section organization.	3 / 3
	Total	11 / 12 Passed

Description

82%

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 specific, well-triggered description tied to a distinctive Rust package niche, but it folds the "what does this do" into the "when" clause rather than stating concrete actions separately.

Suggestions

Lead with a concrete action clause (e.g., 'Compose and run Rust flow graphs with the `axllm` package') before the 'Use when' trigger so the 'what' is stated explicitly.

Keep the feature list but anchor it to verbs users would say (e.g., 'compose flows, declare node inputs, wire dependencies, cache results').

Dimension	Reasoning	Score
Specificity	Lists multiple concrete, specific capabilities ("flows, nodes, program graphs, nested programs, dynamic options, caching, and optimizer components") rather than vague language, naming seven distinct feature areas.	3 / 3
Completeness	The "when" is explicit ("Use when writing Rust code with `axllm`..."), but the "what" is only merged into the trigger clause rather than stated as its own concrete action, so it does not clearly answer both.	2 / 3
Trigger Term Quality	Natural domain terms a user of the package would say ("writing Rust code", "axllm", "flows", "nodes", "caching") appear alongside the explicit "Use when" trigger, giving good keyword coverage.	3 / 3
Distinctiveness Conflict Risk	The package-scoped niche ("Rust code with `axllm`") is highly specific and unlikely to trigger for unrelated skills.	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/rust/skills/ax-rust-flow/SKILL.md
Commit: fe8baf8

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.