rust-pro

Master modern Rust (2024 edition) with async patterns, advanced type system features, and production-ready systems programming. Expert in the current Rust ecosystem including Tokio, axum, and modern crates. Use PROACTIVELY for Rust development, performance optimization, or systems programming.

Quality

44%

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 ./.agents/skills/rust-pro/SKILL.md

Quality

Content

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

The body is essentially a topical outline of Rust features Claude already knows — verbose, non-actionable, and self-redundant — with no code examples, no validation steps, and no progressive disclosure through bundle files. It reads as a capability advertisement rather than operational guidance.

Suggestions

Cut the concept catalog (Capabilities, Knowledge Base, Behavioral Traits, Purpose) down to only non-obvious guidance, and replace generic bullet lists with a few executable snippets (e.g. a Tokio select example, an anyhow/thiserror error type, a criterion bench).

Add explicit validation checkpoints to the workflow for risky operations — e.g. 'after writing unsafe: run cargo miri and clippy::unsafe; only proceed if both pass'.

Move deep reference material (crate-by-crate patterns, FFI safety checklists) into references/*.md files and link to them one level deep so SKILL.md stays a lean overview.

Dimension	Reasoning	Score
Conciseness	The body is a ~170-line catalog of concepts Claude already knows (ownership rules, smart pointers, Result/Option combinators, what Tokio is) presented as bullet lists, padded with redundant 'Knowledge Base', 'Behavioral Traits', and 'Purpose' sections that restate the same facts.	1 / 3
Actionability	Despite claiming expertise across many concrete tools (criterion, sqlx, bindgen, perf, cargo-flamegraph), the body gives zero executable code or commands — it only lists categories like 'Profiling with perf, valgrind, and cargo-flamegraph' with no usage guidance.	1 / 3
Workflow Clarity	A sequence exists ('Instructions' 1-4 and 'Response Approach' 1-8), but the steps are abstract ('Choose async/runtime and crate ecosystem approach', 'Profile and optimize hotspots') with no validation checkpoints or feedback loops, even though the skill explicitly covers destructive/risky areas like unsafe code and FFI.	2 / 3
Progressive Disclosure	The skill is a monolithic wall of text with no references, scripts, or assets to offload detail; all capability lists sit inline in SKILL.md with no navigation to deeper material.	1 / 3
	Total	5 / 12 Passed

Description

82%

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-formed: it states both what the skill does and when to use it with explicit, natural trigger terms tied to a distinctive Rust niche. Its main weakness is specificity, where it leans on broad capability categories rather than enumerating concrete actions.

Suggestions

Replace abstract capability phrases ('advanced type system features', 'production-ready systems programming') with a few concrete actions users would request, e.g. 'optimize async hotpaths, design safe FFI wrappers, fix lifetime/borrow errors'.

Trim the redundancy between the first and second sentences ('Master modern Rust...' vs 'Expert in the current Rust ecosystem...') to keep the description tight.

Dimension	Reasoning	Score
Specificity	It names a concrete domain (Rust, async patterns, type system, systems programming) and tools (Tokio, axum), but the actions are high-level categories rather than the multiple specific concrete actions (e.g. 'extract text', 'fill forms') that the score-3 anchor requires.	2 / 3
Completeness	It explicitly answers 'what' (master modern Rust, async/type-system/production systems programming) and 'when' via the explicit 'Use PROACTIVELY for Rust development, performance optimization, or systems programming' trigger, satisfying both halves.	3 / 3
Trigger Term Quality	It includes natural terms users would actually say — 'Rust development', 'performance optimization', 'systems programming', 'Tokio', 'axum', 'Cargo.toml', '.rs files' (in when_to_use) — giving good coverage of common phrasings.	3 / 3
Distinctiveness Conflict Risk	The Rust-specific niche with named crates (Tokio, axum) gives clear, distinct triggers unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: vudovn/ag-kit
Path: .agents/skills/rust-pro/SKILL.md
Commit: 04514f0

Reviewed: about 11 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.