rust-router
CRITICAL: Use for ALL Rust questions including errors, design, and coding. HIGHEST PRIORITY for: 比较, 对比, compare, vs, versus, 区别, difference, 最佳实践, best practice, tokio vs, async-std vs, 比较 tokio, 比较 async, Triggers on: Rust, cargo, rustc, crate, Cargo.toml, 意图分析, 问题分析, 语义分析, analyze intent, question analysis, compile error, borrow error, lifetime error, ownership error, type error, trait error, value moved, cannot borrow, does not live long enough, mismatched types, not satisfied, E0382, E0597, E0277, E0308, E0499, E0502, E0596, async, await, Send, Sync, tokio, concurrency, error handling, 编译错误, compile error, 所有权, ownership, 借用, borrow, 生命周期, lifetime, 类型错误, type error, 异步, async, 并发, concurrency, 错误处理, error handling, 问题, problem, question, 怎么用, how to use, 如何, how to, 为什么, why, 什么是, what is, 帮我写, help me write, 实现, implement, 解释, explain
57
66%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/rust-router/SKILL.mdQuality
Discovery
54%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is essentially a keyword dump with minimal explanation of what the skill actually does. While the trigger term coverage is impressively comprehensive (including bilingual terms and specific error codes), the description fails to articulate concrete capabilities or actions. It reads more like a search index than a skill description.
Suggestions
Replace the vague opening with specific capability statements, e.g., 'Diagnoses Rust compiler errors, explains ownership/borrowing/lifetime concepts, designs async architectures, and generates idiomatic Rust code.'
Restructure the description to separate the 'what it does' section from the 'when to use' section, with a clear 'Use when...' clause rather than mixing everything into trigger keyword lists.
Trim the trigger keyword list to the most essential terms and consolidate duplicates (e.g., 'compile error' appears twice, 'async' appears multiple times) to improve readability.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description says 'Use for ALL Rust questions including errors, design, and coding' which is extremely vague. It does not list concrete actions like 'diagnose borrow checker errors' or 'generate async Rust code'. The rest is just a list of trigger keywords, not capability descriptions. | 1 / 3 |
Completeness | The 'when' is partially addressed via 'CRITICAL: Use for ALL Rust questions' and 'Triggers on:' clauses, but the 'what' is extremely weak — it only says 'errors, design, and coding' without describing what the skill actually does. The trigger guidance exists but the capability description is nearly absent. | 2 / 3 |
Trigger Term Quality | The description includes extensive natural keywords users would say, covering both English and Chinese terms: error codes (E0382, E0597), natural phrases ('how to use', 'help me write', '怎么用'), tool names (tokio, cargo, rustc), and common error messages ('value moved', 'cannot borrow', 'does not live long enough'). | 3 / 3 |
Distinctiveness Conflict Risk | The Rust-specific focus and error codes provide some distinctiveness, but the description claims to handle 'ALL Rust questions' which is extremely broad. Terms like 'async', 'concurrency', 'error handling', 'implement', and 'explain' could easily overlap with general programming or other language-specific skills. | 2 / 3 |
Total | 8 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured routing/dispatch skill with highly actionable lookup tables mapping error codes, keywords, and domain signals to specific sub-skills. Its main weakness is moderate verbosity—the meta-cognition framework explanation and partially-inlined negotiation protocol add tokens that could be trimmed or fully deferred to sub-files. The workflow is clear for a routing skill, with explicit priority hierarchies and conflict resolution.
Suggestions
Move the negotiation protocol template entirely to patterns/negotiation.md instead of partially inlining it—just keep the trigger table and a one-line reference.
Trim the Meta-Cognition Framework section: the ASCII tree and explanatory text ('Don't answer directly...') could be condensed to just the routing table since Claude understands layered reasoning.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is a routing table, which is inherently reference-heavy, but there's notable redundancy: the dual-skill loading table partially duplicates the Layer 3 routing table, and the meta-cognition framework explanation is somewhat verbose for Claude. The negotiation protocol template adds bulk that could be in the referenced sub-file. | 2 / 3 |
Actionability | The routing tables are highly concrete with specific error codes, keywords, and exact skill file targets. The Cargo.toml defaults are copy-paste ready. The priority hierarchy and conflict resolution rules give unambiguous decision procedures for Claude to follow. | 3 / 3 |
Workflow Clarity | The priority order section provides a clear 5-step sequence. The routing-by-entry-point table clearly maps user signals to entry layers and directions. Keyword conflict resolution provides explicit disambiguation rules. For a routing/dispatch skill, this level of workflow clarity is appropriate and complete. | 3 / 3 |
Progressive Disclosure | The skill references sub-files (patterns/negotiation.md, examples/workflow.md, integrations/os-checker.md) which is good progressive disclosure structure. However, no bundle files are provided to verify these exist, and the negotiation protocol template is partially inlined despite claiming details are in a sub-file, creating redundancy. The inline negotiation markdown template could have been fully deferred. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- actionbook/rust-skills
- Commit
fa60f79
- 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.