CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

62

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-agent/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%

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

A concise, well-structured orientation skill that points appropriately to package docs, with a real but minimal Core Pattern example. Its main gap is actionability/workflow: the inline code is incomplete and no multi-step workflow with validation checkpoints is shown.

Suggestions

Make the Core Pattern self-contained — add the import and show how 'llm'/'inputs' are constructed, or label it explicitly as a shape to copy from 'examples/'.

For the more involved flows (e.g., harvesting run-end failures into the playbook, save/restore runtime state), add a short numbered sequence with a verification checkpoint.

DimensionReasoningScore

Conciseness

The body is lean and sectioned into terse bullets with no padding or explanation of concepts Claude already knows (no 'what is Rust' or 'how libraries work'); every line (Package Facts, Core Pattern, Guardrails) earns its place.

3 / 3

Actionability

It provides a concrete Core Pattern snippet and specific API symbols/files, but the inline example is incomplete (no imports, undefined 'llm' and 'inputs') and leans on external 'examples/' and 'API.md' for the missing key details, fitting the 'some concrete guidance but incomplete' anchor.

2 / 3

Workflow Clarity

Content is well organized into clear sections, but this is reference/orientation material with no explicit multi-step sequence or validation checkpoints, so it sits at 'sequence/checkpoints missing or implicit' rather than a fully sequenced workflow.

2 / 3

Progressive Disclosure

At 49 lines with clear, well-organized sections and no skill bundle files needed, it appropriately keeps an overview in SKILL.md while signaling package docs ('API.md', 'axir-api.json', 'examples/') one level deep — matching the under-50-lines well-organized anchor.

3 / 3

Total

10

/

12

Passed

Description

75%

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, distinctive description with an explicit 'Use when' trigger and a clear niche, weakened only by capability-noun framing and a jargon-heavy tail of trigger terms. It clearly answers both what and when.

Suggestions

Reframe some capability nouns as concrete verb actions (e.g., 'create agents with tools', 'attach citations') to lift specificity.

Trim or soften the most internal jargon ('direct-respond executor skipping', 'persistent playbook learning') so trigger terms read like what a user would actually say.

DimensionReasoningScore

Specificity

The description enumerates many concrete capabilities ('agents, child delegation, tools, MCP, citations, persistent playbook learning'), but they are framed as capability nouns under 'writing Rust code with axllm for X' rather than specific verb-driven actions, so it names the domain and items comprehensively without listing discrete actions.

2 / 3

Completeness

It explicitly answers both what (writing Rust code with axllm for the enumerated capabilities) and when, via an explicit 'Use when...' trigger clause, matching the 'clearly answers both what AND when' anchor.

3 / 3

Trigger Term Quality

It opens with a natural trigger ('writing Rust code with axllm') plus some relevant keywords ('agents', 'tools', 'MCP'), but much of the tail is technical jargon a user would not naturally say ('persistent playbook learning', 'direct-respond executor skipping', 'stage-owned actor instructions'), missing common variations.

2 / 3

Distinctiveness Conflict Risk

The niche is highly specific (Rust code with the generated 'axllm' package and RLM agents) with distinct triggers, making it very unlikely to fire for an unrelated skill.

3 / 3

Total

10

/

12

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.

Validation15 / 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
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.