CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./packages/rust/skills/ax-rust-flow/SKILL.md
SKILL.md
Quality
Evals
Security

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 body is a well-structured, code-rich pattern library for the flow API with actionable examples, but it is dragged down by a dense inlined Astra session specification and the absence of bundled reference files to offload detail. Workflow sequencing and validation guidance remain implicit.

Suggestions

Move the 'Astra Session Work' section into a separate reference file (e.g., references/astra-sessions.md) and keep a short summary with a clear link in SKILL.md.

Make the core examples self-contained by declaring the programs and client used in the fan-out and refine snippets, so they are copy-paste runnable.

Add a brief ordered workflow (pick pattern from examples/ -> declare reads/writes -> forward with no-key example to verify -> switch to provider client) with a verification checkpoint.

DimensionReasoningScore

Conciseness

The flow-patterns sections are lean and code-forward, but the ~30-line 'Astra Session Work' section is dense specification prose ("Queued and applied are different states", "Consuming buffered events does not reactivate a completed response") that repeats cross-language details and could be tightened or trimmed. Mostly efficient, with a substantial block that could be condensed.

3 / 5

Actionability

Concrete, realistic Rust snippets throughout (the Core Pattern, branch/parallel/refine flows, forward/streaming/caching calls) plus pointers to runnable examples. Not a 5 because several snippets reference undeclared variables (research, audience, join, critique, cache, client) so they are not fully copy-paste ready.

4 / 5

Workflow Clarity

Content is organized from core pattern to advanced patterns and the Guardrails section gives ordering advice ("Start from package examples for exact native syntax"), but there is no explicit multi-step sequence or validation checkpoint for building and verifying a flow. The pattern library is clear per-pattern, yet the overall process is implicit.

3 / 5

Progressive Disclosure

Sections are well-labeled and the body points to `API.md`, `axir-api.json`, `axir-capabilities.json`, `examples/`, and an external gallery, but no reference files ship in the skill bundle, and the long 'Astra Session Work' specification is inlined where a one-level-deep reference file would fit better.

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, trigger-first description that names a specific package and enumerates concrete feature areas, making it highly distinguishable. Its main weakness is that capabilities are expressed as topic nouns inside the 'Use when' clause rather than as distinct, explicit actions.

Suggestions

Split the description into an action statement plus trigger clause, e.g., 'Compose typed LLM workflow graphs in Rust with `axllm`: flows, nodes, nested programs, caching. Use when writing Rust code for axllm flows, program graphs, or optimizer components.'

Add natural synonyms users might say, such as 'AxFlow', 'workflow graph', or 'streaming', to broaden trigger coverage.

DimensionReasoningScore

Specificity

"writing Rust code with `axllm` for flows, nodes, program graphs, nested programs, dynamic options, caching, and optimizer components" names the domain and lists several specific capability areas. Not a 5 because these are topic nouns rather than concrete actions (e.g., 'Compose flows', 'Configure caching'), leaving minor gaps in coverage.

4 / 5

Completeness

Both 'what' (writing Rust code with `axllm`) and an explicit 'when' ("Use when writing Rust code with `axllm` for...") are present with concrete trigger phrases. Not a 5 because the 'what' is subsumed into the trigger clause rather than clearly enumerating the actions performed.

4 / 5

Trigger Term Quality

Terms like "Rust code", "flows", "nodes", "caching", and "nested programs" are natural phrases a user of this package would say. Not a 5 because synonyms and package-specific aliases (e.g., "AxFlow", "workflow", "streaming") are missing.

4 / 5

Distinctiveness Conflict Risk

The pairing of "Rust" with the package name "axllm" and its feature-specific terms (flows, program graphs, optimizer components) carves out a clear niche with minimal conflict risk against generic Rust or LLM skills.

5 / 5

Total

17

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

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

Reviewed

Table of Contents

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.