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

70%

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 ./website/static/rust/.well-known/agent-skills/ax-rust-playbook/SKILL.md

Quality

Content

68%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 efficient and actionable with a concrete code pattern and well-organized sections. It lacks a sequenced workflow with validation checkpoints and its file references are unlinked with some referenced bundles missing.

Suggestions

Convert the 'When To Use' menu into a short sequenced workflow for the primary evolve→learn→refine→render flow, with an explicit validation/check step after evolve.

Make the referenced files actual links (e.g., [API.md](API.md)) and ensure the referenced bundle files exist in the skill package.

Complete the Core Pattern snippet with minimal scaffolding (or a note) so the referenced variables (llm, examples, metric_fn) are defined or clearly marked as placeholders.

Dimension	Reasoning	Score
Conciseness	The body is lean with no over-explanation of Rust/library basics, though the intro and 'When To Use' bullets mildly restate the description's triggers and could be trimmed.	4 / 5
Actionability	Provides a concrete 'Core Pattern' Rust snippet, named optimizer/struct API surface, and package facts with file paths, but the snippet relies on undefined placeholders (llm, examples, metric_fn) so it is not fully copy-paste runnable.	4 / 5
Workflow Clarity	Capabilities are presented as an unordered bulleted menu rather than a sequenced process, with no validation checkpoints or feedback loop; a rough sense of the work exists but no real sequence.	3 / 5
Progressive Disclosure	Well-structured into clear sections with one-level-deep file references (API.md, axir-api.json, axir-capabilities.json, examples/), but references are unlinked bare names and several referenced bundle files are not present in the skill.	4 / 5
	Total	15 / 20 Passed

Description

71%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 specific and distinctive with an explicit 'Use when' trigger and concrete capability enumeration. Its main weakness is heavy reliance on internal jargon for trigger terms, which limits natural keyword coverage.

Suggestions

Add natural-language trigger synonyms a user might say (e.g., 'optimizing LLM programs', 'evolving prompts', 'context engineering') alongside the jargon.

Broaden the 'Use when' clause to mention common variations like refining prompts from feedback or learning from agent run failures.

Dimension	Reasoning	Score
Specificity	Names the domain (Rust + axllm) and lists several concrete actions ('verified evolution', 'run-end learning', 'online updates', 'rendering a playbook into a program'); not as comprehensively enumerated as the 5 anchor but clearly more than 1-2 actions.	4 / 5
Completeness	Provides both a clear 'what' (writing Rust code with axllm for the playbook surface and its feature set) and an explicit 'when' ('Use when writing Rust code with axllm'); the trigger is somewhat narrow rather than a broad concrete phrase set.	4 / 5
Trigger Term Quality	Opens with an explicit 'Use when' and natural phrases ('writing Rust code', 'axllm'), but the bulk of trigger content is dense jargon ('context-engineering surface', 'agent-bound verified evolution') users would not naturally say, missing common synonyms.	3 / 5
Distinctiveness Conflict Risk	Targets a highly specific niche (axllm playbook in Rust) with distinct triggers, making conflict with other skills minimal.	5 / 5
	Total	16 / 20 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: website/static/rust/.well-known/agent-skills/ax-rust-playbook/SKILL.md
Commit: 1abea97

Reviewed: ~19 hours 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.