CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ax-rust-agent

Use when writing Rust code with `axllm` for agents, child delegation, tools, MCP, citations, persistent playbook learning, stage instructions, runtime state, final typed responses, and direct-respond executor skipping.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

50%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-sectioned, information-dense API reference with genuinely novel package-specific facts, but it reads as descriptive prose rather than executable guidance: only one small code snippet, no sequenced workflows with validation checkpoints, and bulk behavioral detail inlined where reference files would serve better. Tightening legacy/version asides and splitting the session/streaming semantics into referenced files would materially improve it.

Suggestions

Move the dense behavioral semantics (Astra session handling, cancellation propagation, streaming rules) into a reference file and keep a short summary with a clearly signaled link in SKILL.md.

Add a short sequenced workflow (e.g., create agent -> register child agents -> attach runtime -> attach MCP clients -> forward/stream) with validation checkpoints for common build tasks.

Replace some prose behavior descriptions with small executable Rust snippets in the style of the Core Pattern, and relocate version-history asides like 'as the ports did before 25.0.0' to a deprecated/old-patterns section.

DimensionReasoningScore

Conciseness

Mostly dense package-specific facts Claude would not know, but sections like 'Astra Session Work' are long prose walls, and legacy/version asides ('default since 25.0.0', 'as the ports did before 25.0.0') add tokens that could be trimmed or moved to a deprecated section.

3 / 5

Actionability

Provides one executable core-pattern snippet and many concrete API names ('with_runtime(Box::new(runtime))', 'agent.streaming_forward(&mut client, values, options, on_delta)', 'with_tool_module("crm", tools)'), but most sections describe runtime behavior in prose rather than executable patterns, deferring syntax to examples.

3 / 5

Workflow Clarity

The body is a topic-organized reference rather than a sequenced process; 'When To Use' and the 'Core Pattern' orient the reader, but multi-step tasks like building a child-agent flow with MCP have no step sequence or validation checkpoints.

3 / 5

Progressive Disclosure

Sections are clearly headed and package artifacts are named ('API.md', 'axir-api.json', 'examples/'), but heavy inline semantics (session handling, cancellation, streaming) that would belong in reference files dominate the body, and no in-skill reference navigation exists.

3 / 5

Total

12

/

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, highly distinctive description with explicit trigger guidance and broad, specific capability coverage. Its main weaknesses are that capabilities are listed as topic nouns rather than concrete actions, and the 'what' and 'when' are fused into a single 'Use when' clause instead of being stated separately.

DimensionReasoningScore

Specificity

Lists many concrete capability areas ('agents, child delegation, tools, MCP, citations, persistent playbook learning, stage instructions, runtime state, final typed responses, and direct-respond executor skipping'), though as topic nouns rather than concrete actions, leaving minor gaps in coverage.

4 / 5

Completeness

Explicit 'Use when...' trigger guidance is present and the capability list conveys the 'what', but what and when are merged into a single clause rather than clearly separated ('Use when writing Rust code with `axllm` for...').

4 / 5

Trigger Term Quality

Good coverage of natural terms users would say for this domain ('Rust', 'axllm', 'agents', 'tools', 'MCP'), but no synonyms or variations of these phrases are included.

4 / 5

Distinctiveness Conflict Risk

The description is anchored to a specific package ('axllm'), language ('Rust'), and niche capabilities (playbook learning, direct-respond executor skipping), giving it a clear niche with minimal conflict risk against generic agent or Rust 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-agent/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.