CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ax-rust-playbook

Use when writing Rust code with `axllm` for the playbook() context-engineering surface, agent-bound verified evolution, run-end learning, online updates, and rendering a playbook into a program.

Quality

78%

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

Quality

Content

80%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 an exemplary lean overview: token-efficient, well-sectioned, and clearly pointing to package docs and examples for depth. Its gaps are a code snippet with undefined bindings that keeps it from being copy-paste ready, and the absence of an explicit sequenced workflow with validation checkpoints for the evolve/refine cycle.

Suggestions

Make the Core Pattern snippet self-contained by showing how `llm`/`student`, `examples`, and `metric_fn` are constructed, or annotate that they come from the package examples.

Add a short ordered workflow for the evolve loop (build examples, run evolve, check verification result, roll back on failure) with an explicit validation checkpoint.

Include one-line call signatures or a pointer per optimizer in 'Relevant API Surface' so the names are actionable without opening API.md.

DimensionReasoningScore

Conciseness

The ~44-line body is lean and assumes Claude's competence: Package Facts, Core Pattern, API names, and Guardrails all carry non-obvious, package-specific information with zero padding or explanation of concepts Claude already knows. Every token earns its place.

5 / 5

Actionability

The Core Pattern is real Rust code showing the exact call shape, and the guardrail 'Start from package examples for exact native syntax' points to runnable examples. Not 5 because the snippet references undefined bindings (`llm`, `examples`, `metric_fn`) and the Relevant API Surface is a bare name list without signatures; not 3 because it is concrete, compilable-shape code rather than pseudocode.

4 / 5

Workflow Clarity

The 'When To Use' bullets imply a lifecycle order (grow, attach and learn, evolve, refine, render) but the body never presents an explicit sequence or any validation checkpoints for the evolve/refine operations. Steps are effectively listed with implicit ordering and missing checkpoints, matching the score-3 anchor.

3 / 5

Progressive Disclosure

The skill is under 50 lines with no bundle files, and the body is a well-organized overview (When To Use, Package Facts, Core Pattern, API Surface, Guardrails) that clearly signals one-level-deep detail in package materials ('API.md and axir-api.json', 'axir-capabilities.json', 'examples/'). Easy to navigate with no content that should be split out.

5 / 5

Total

17

/

20

Passed

Description

67%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.

The description is well-structured with an explicit 'Use when' trigger and a specific enumeration of capabilities, giving it good completeness and distinctiveness for a niche generated-package skill. Its main weakness is trigger term quality: much of the phrasing is internal package jargon ('context-engineering surface', 'agent-bound verified evolution') rather than language users would naturally type.

Suggestions

Rewrite capability phrases in plainer user-facing terms, e.g. 'grow or evolve a context playbook', 'learn avoidance rules from failed runs', instead of jargon like 'context-engineering surface' and 'agent-bound verified evolution'.

Add natural trigger synonyms users might say, such as 'playbook', 'evolve', 'context program', or 'learn from run failures', to improve trigger term coverage.

Narrow the 'when' clause to the specific tasks (e.g. 'Use when evolving, refining, or rendering an axllm playbook in Rust') to reduce overlap with other axllm skills.

DimensionReasoningScore

Specificity

Names the domain (Rust with `axllm`) and five specific capability areas ('playbook() context-engineering surface, agent-bound verified evolution, run-end learning, online updates, and rendering a playbook into a program'). Not 5 because the actions are expressed in package jargon rather than plain concrete operations; not 3 because it lists several specific actions beyond the 1-2 anchor.

4 / 5

Completeness

Both are present: an explicit 'Use when writing Rust code with `axllm`' trigger clause and an enumerated 'what' (the five capability areas). Not 5 because the 'when' is broad (any axllm Rust work) rather than task-specific triggers; not 3 because both what and when are explicitly stated.

4 / 5

Trigger Term Quality

Relevant keywords like 'writing Rust code', 'playbook', and 'axllm' are present, but terms like 'context-engineering surface' and 'agent-bound verified evolution' are technical jargon a user would not naturally say, and common variations or synonyms are missing. Fits the 'some relevant keywords but missing common variations' anchor.

3 / 5

Distinctiveness Conflict Risk

The description pins a clear niche (axllm's playbook surface) with distinct triggers, but 'Use when writing Rust code with `axllm`' could overlap with sibling skills covering other axllm surfaces. Mostly distinct with minor overlap risk against closely related package skills.

4 / 5

Total

15

/

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-playbook/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.