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

Securityby

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

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-organized skill body that leverages progressive disclosure effectively. The Core Pattern and API surface are concrete but incomplete as standalone executable guidance, and the evolution workflow lacks explicit validation checkpoints.

Suggestions

Make the Core Pattern self-contained: add the missing imports and define `llm`, `examples`, and `metric_fn` so the snippet is copy-paste executable, or explicitly label it as a call-shape sketch to justify the incompleteness.

Add an explicit validation/checkpoint step to the evolution workflow (e.g., verify mined weaknesses pass the metric before keeping them, with a rollback on failure) so the validate-fix-retry loop is visible.

Pair the Relevant API Surface names with at least one-line signatures or a pointer to the exact section of API.md, so the guidance is actionable without a separate lookup.

Dimension	Reasoning	Score
Conciseness	The body is lean and information-dense across terse sections (When To Use, Package Facts, Core Pattern, Guardrails) with no explanation of concepts Claude already knows, so every token earns its place; it does not drop to 2 because there is no unnecessary padding.	3 / 3
Actionability	The Core Pattern gives real Rust syntax and concrete function names, but it is not copy-paste ready — `llm`, `examples`, and `metric_fn` are undefined and imports are missing — matching the 'some concrete guidance but incomplete; missing key details' anchor; it does not reach 3 because the example is not fully executable standalone.	2 / 3
Workflow Clarity	The Core Pattern implies a loose sequence (program -> student -> playbook -> evolve), but there are no explicit validation or verification checkpoints for the evolution/rollback process, matching 'sequence present but checkpoints missing or implicit'; it does not reach 3 because no validate-fix-retry feedback loop is spelled out.	2 / 3
Progressive Disclosure	The SKILL.md is a lean overview that clearly signals one-level-deep references to detail material (Package API docs: `API.md` and `axir-api.json`, capability manifest `axir-capabilities.json`, runnable `examples/`), keeping detail out of the main file, matching the 'clear overview with well-signaled one-level-deep references' anchor.	3 / 3
	Total	10 / 12 Passed

Description

85%

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 specific, well-triggered, distinct description with an explicit 'Use when' clause. Its main weakness is heavy internal jargon in the capability list that users would not naturally voice, which limits trigger-term quality.

Dimension	Reasoning	Score
Specificity	The description enumerates multiple concrete actions — 'writing Rust code with `axllm`', 'agent-bound verified evolution', 'run-end learning', 'online updates', and 'rendering a playbook into a program' — rather than vague language, matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	It opens with an explicit 'Use when...' trigger clause and lists the concrete actions, clearly answering both what it does and when to use it, matching the 'explicit triggers' anchor; it does not fall to 2 because the trigger guidance is present rather than implied.	3 / 3
Trigger Term Quality	'writing Rust code with `axllm`' is a natural trigger for the niche, but the remaining terms ('playbook() context-engineering surface', 'agent-bound verified evolution', 'run-end learning') are internal jargon a user would not naturally say, so common natural variations are missing.	2 / 3
Distinctiveness Conflict Risk	The tightly scoped triggers ('Rust code with `axllm`', 'playbook()') define a clear niche unlikely to overlap with unrelated skills, matching the 'clear niche with distinct triggers' anchor.	3 / 3
	Total	11 / 12 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
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
Commit: fe8baf8

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.