ax-rust-flow

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

Quality

73%

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 flow-graph half of this skill is excellent: tight, concrete, executable Rust patterns with dependency semantics explained through code. The 'Astra Session Work' section is the weak spot — a wall of dense, partly off-topic prose inlined where a one-level-deep reference file should be, which hurts token efficiency and navigation more than it helps.

Suggestions

Move the 'Astra Session Work' section (sessions, steering, cancellation, MCP host policy, WebSocket adapters, parallel workers) into a separate reference file (e.g., SESSIONS.md) and keep a 3-5 line summary with a clear link in SKILL.md.

Add a short ordered 'how to build and run a flow' sequence (draft programs -> declare reads/writes -> returns -> forward -> verify against examples) so the implicit workflow becomes an explicit checklist.

Make the core snippet closer to copy-paste ready by including the use statements and the minimal client construction, or point explicitly to the example file that contains them.

Dimension	Reasoning	Score
Conciseness	The flow-pattern sections are lean and code-first ('execute_with_options', 'returns', 'forward'), but the multi-paragraph 'Astra Session Work' section is dense prose covering cross-language behavior (Python, Go, Java, C++ client options, WebSocket adapters, MCP policy) that a Rust flow skill does not need inline, matching anchor 3 ('mostly efficient but could be tightened'). It is not 2 because the material is package-specific knowledge Claude does not already have, not generic concept explanation.	3 / 5
Actionability	Concrete Rust snippets cover the common cases: building flows with 'execute_with_options' plus reads/writes JSON plans, 'returns', 'forward', 'streaming_forward', and 'forward_with_caching_function', with guardrails directing the agent to runnable examples. It matches anchor 4 rather than 5 because snippets omit imports and client construction, so they are not copy-paste complete.	4 / 5
Workflow Clarity	A progression (compose nodes with reads/writes -> run via forward -> cache) is implicit in the pattern catalog, but the body presents parallel patterns rather than an explicit step sequence, and validation/checkpoint guidance is limited to guardrail hints like 'Start from package examples... before inventing a new call shape'. This matches anchor 3 ('sequence present but checkpoints missing or implicit').	3 / 5
Progressive Disclosure	References are clearly signaled in 'Package Facts' ('API.md and axir-api.json', 'examples/', the external gallery URL), but the large inline 'Astra Session Work' section (~9 dense paragraphs on sessions, steering, cancellation, MCP policy, and parallel workers) is content that clearly belongs in a separate reference file, matching anchor 3 ('content that should be separate is inline').	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.

A strong description: explicit trigger guidance, a named package and language, and an enumerated capability list make it specific and highly distinguishable. Its main weakness is that the capability list is a string of topic nouns rather than concrete actions, which slightly blurs the 'what does this do' answer.

Suggestions

Lead with one or two concrete action verbs (e.g., 'Build and run typed LLM workflow graphs in Rust with `axllm`: flows, nodes, nested programs, caching, optimizer components') so the 'what' reads as actions rather than a topic list.

Add one or two natural synonyms users might say (e.g., 'workflow', 'AxFlow', 'streaming') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ("writing Rust code with `axllm`") and enumerates several concrete capability areas ("flows, nodes, program graphs, nested programs, dynamic options, caching, and optimizer components"), matching anchor 4. It falls short of 5 because these are topic nouns carried by a single verb ('writing') rather than multiple distinct concrete actions.	4 / 5
Completeness	An explicit "Use when writing Rust code with `axllm` for..." clause answers 'when' with concrete triggers, and the enumerated topics convey the 'what'. It matches anchor 4 rather than 5 because what and when are merged into a single clause, with the skill's actions implied rather than distinctly stated.	4 / 5
Trigger Term Quality	Terms like "Rust", "axllm", "flows", "nested programs", and "caching" are phrases a user of this package would naturally say, giving good keyword coverage per anchor 4. It is not 5 because natural synonyms and variations (workflow, AxFlow, streaming) are missing and "program graphs" / "optimizer components" lean toward internal jargon.	4 / 5
Distinctiveness Conflict Risk	The pairing of "Rust" with the specific package name "`axllm`" carves out a clear niche with distinct triggers and minimal risk of firing for unrelated skills, matching anchor 5.	5 / 5
	Total	17 / 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: 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.