CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ax-rust-gepa

Use when writing Rust code with `axllm` for GEPA, Pareto tradeoffs, reflection clients, metric budgets, optimizer state, and artifacts.

Quality

79%

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

Quality

Content

72%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 exceptionally lean and dense with non-obvious package-specific facts, and names concrete API symbols, but the code pattern is not runnable as-is and the workflow is never explicitly sequenced. Its biggest structural problem is that every referenced file (API.md, manifests, examples/) is missing from the bundle, leaving its pointers unresolvable.

Suggestions

Include the referenced files (API.md, axir-api.json, axir-capabilities.json, examples/) in the skill bundle, or state where they live relative to the skill so the pointers resolve.

Add an explicit ordered workflow (pick a no-key or provider example, adapt it, run optimize, then compare metadata.bestScore against baselineScore) so the multi-step process has a clear sequence.

Complete the Core Pattern snippet by showing how reflection_client, request, and evaluator are constructed, making it copy-paste runnable.

DimensionReasoningScore

Conciseness

The body is lean throughout: terse fact bullets ('Language: Rust. Package: `axllm`.'), a compact code pattern, and dense guardrails carrying non-obvious generated-package facts (budget accounting, demo freshness, baseline semantics) that Claude could not know. There is no padding or explanation of concepts Claude already knows.

5 / 5

Actionability

Concrete API symbols ('AxGEPA', 'optimize_with_client(&mut program, student.clone(), examples, options)' with 'Rc<RefCell<Client>>') and a code pattern give mostly executable guidance. The Core Pattern snippet has unresolved variables (reflection_client, request, evaluator) and the 'start from package examples' pointers target files absent from the bundle, which are more than the copy-paste-ready anchor 5 allows but only minor gaps.

4 / 5

Workflow Clarity

'When To Use', 'Core Pattern', and 'Guardrails' imply a flow (choose transport, run the optimizer, interpret baseline vs bestScore) but never explicitly sequence it, and there are no validation checkpoints on results. This is not a single-action simple skill, so it matches the 'sequence present but checkpoints missing or implicit' anchor rather than 4.

3 / 5

Progressive Disclosure

Sections are well-organized and the body is short, but it directs readers to 'API.md', 'axir-api.json', 'axir-capabilities.json', and 'examples/' — none of which exist in the skill bundle, so navigation dead-ends. The structure itself is good and references are one level deep and clearly signaled, keeping it above the 'minimal structure' anchor 2.

3 / 5

Total

15

/

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 with an explicit and specific 'Use when' trigger, natural domain keywords, and high distinctiveness. Its main limitation is that capabilities are expressed as a topic list rather than concrete actions, leaving the 'what' partially implicit.

DimensionReasoningScore

Specificity

Names the domain ('writing Rust code with `axllm`') and enumerates six concrete capability areas ('GEPA, Pareto tradeoffs, reflection clients, metric budgets, optimizer state, and artifacts'), matching the 'several specific actions; minor gaps' anchor. It falls short of 5 because these are topic noun phrases rather than stated actions.

4 / 5

Completeness

The 'when' is explicit and specific ('Use when writing Rust code with `axllm`'), and the 'what' is conveyed through the enumerated topics, matching 'both present; one could be more explicit'. Not 5 because the what is an implied topic list rather than a clear capability statement.

4 / 5

Trigger Term Quality

'Rust', 'axllm', 'GEPA', 'Pareto tradeoffs', 'reflection clients', and 'metric budgets' are terms a user of this package would naturally say, giving good keyword coverage. A few natural variations ('prompt optimization', 'playbook', 'bootstrap') are missing, keeping it below the comprehensive-synonym anchor 5.

4 / 5

Distinctiveness Conflict Risk

The combination of Rust, `axllm`, and GEPA forms a clear niche with distinct triggers and minimal conflict risk — the `axllm` qualifier prevents collision with generic Rust skills. No realistic overlap with other skills exists.

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-gepa/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.