ax-rust-flow

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

Quality

68%

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/rust/.well-known/agent-skills/ax-rust-flow/SKILL.md

Quality

Content

57%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 content is actionable with concrete, executable Rust examples and clear API guidance, but it inlines several near-duplicate code blocks and lacks explicit validation checkpoints for flow execution, which limits workflow clarity and progressive disclosure.

Suggestions

Add a validation/verification step after forward() runs (e.g., checking the output JSON or handling the returned error) so flow execution has an explicit feedback loop and workflow clarity can exceed 3.

Consolidate the repeated execute_with_options/returns boilerplate into one canonical example and offload the variant patterns to a referenced examples/ file to reduce token padding and improve progressive disclosure.

Replace prose pointers (examples/, the dev URL) with clearly signaled one-level-deep links and a brief 'what each file contains' map so navigation is unambiguous.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids explaining concepts Claude already knows, but the repeated near-identical execute_with_options/returns code blocks across five patterns add padding that could be tightened, matching the score-3 anchor of 'mostly efficient but includes some unnecessary explanation or could be tightened'.	3 / 5
Actionability	It provides concrete, executable Rust code for the core pattern and several variants with specific API calls and JSON shapes, with only minor gaps (e.g., no imports or client setup shown), fitting the score-4 anchor of 'mostly executable guidance; concrete code with minor gaps'.	4 / 5
Workflow Clarity	The body presents patterns as parallel examples rather than a sequenced workflow, and notably lacks validation/verification checkpoints despite forward() calls that can fail and a network-capable runtime; the rubric caps workflow clarity at 3 for batch/flow operations missing validation, matching the score-3 anchor.	3 / 5
Progressive Disclosure	It has reasonable section structure and points to examples/ and external docs, but several full code blocks that could live in referenced examples are inlined and references are prose rather than clearly signaled one-level-deep links, fitting the score-3 anchor of 'some structure but could be better organized'.	3 / 5
	Total	13 / 20 Passed

Description

78%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 is well-formed with an explicit 'Use when' trigger and a concrete, domain-specific capability list tied to the axllm Rust package. It is slightly feature-inventory-like rather than action-oriented, keeping specificity at the midpoint.

Dimension	Reasoning	Score
Specificity	The description names the domain (writing Rust code with axllm) and lists several concrete capabilities (flows, nodes, program graphs, nested programs, dynamic options, caching, optimizer components), but these are listed as nouns rather than explicit actions and coverage reads more like a feature inventory than discrete actions, matching the score-3 anchor of 'names domain and 1-2 concrete actions, but not comprehensive.'	3 / 5
Completeness	It explicitly answers both 'what' (writing Rust code with axllm for flows, nodes, program graphs, etc.) and 'when' (Use when writing Rust code with axllm for...) with concrete trigger phrases, matching the score-5 anchor.	5 / 5
Trigger Term Quality	It includes a natural 'Use when' clause and concrete trigger terms users would say ('writing Rust code', 'flows', 'nodes', 'caching'), giving good keyword coverage with only a few natural synonyms missing, aligning with the score-4 anchor.	4 / 5
Distinctiveness Conflict Risk	The 'axllm' package and Rust-specific flow vocabulary give it a clear, narrow niche with minimal conflict risk, but the general 'writing Rust code' framing could mildly overlap with generic Rust skills, fitting the score-4 anchor of 'mostly distinct; minor overlap risk'.	4 / 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/rust/.well-known/agent-skills/ax-rust-flow/SKILL.md
Commit: 1abea97

Reviewed: ~18 hours 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.