rust-skill-creator
Use when creating skills for Rust crates or std library documentation. Keywords: create rust skill, create crate skill, create std skill, 创建 rust skill, 创建 crate skill, 创建 std skill, 动态 rust skill, 动态 crate skill, skill for tokio, skill for serde, skill for axum, generate rust skill, rust 技能, crate 技能, 从文档创建skill, from docs create skill
Install with Tessl CLI
npx tessl i github:actionbook/rust-skills --skill rust-skill-creator76
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
72%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 excels at trigger term coverage with bilingual keywords and specific crate examples, making it highly discoverable. However, it lacks specificity about what concrete actions the skill performs beyond 'creating skills' - it reads more like a keyword list than a capability description. The 'Use when' clause exists but is essentially just restating the trigger terms rather than explaining the skill's actual functionality.
Suggestions
Add specific concrete actions the skill performs, e.g., 'Generates skill files by parsing Rust documentation, extracting API signatures, and creating usage examples'
Expand the 'Use when' clause to describe scenarios beyond keywords, e.g., 'Use when the user wants to create a reusable skill from crate docs or needs to document Rust library usage patterns'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Rust crates/std library documentation) and the action (creating skills), but doesn't list specific concrete actions like 'parse documentation', 'generate API references', or 'extract code examples'. | 2 / 3 |
Completeness | Has a 'Use when' clause that addresses when to use it, but the 'what' is weak - it only says 'creating skills' without explaining what that process involves or what the skill actually does beyond triggering on keywords. | 2 / 3 |
Trigger Term Quality | Excellent coverage of natural keywords including English and Chinese variations ('create rust skill', '创建 rust skill'), specific crate examples (tokio, serde, axum), and multiple phrasings users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | Very specific niche targeting Rust crate/std documentation skill creation with distinct triggers including specific crate names and bilingual keywords, unlikely to conflict with general coding or documentation skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides solid actionable guidance with clear command examples and well-organized dual-mode workflows. The main weaknesses are content duplication (URL tables repeated) and insufficient validation steps - the verification only checks file existence rather than validating the generated skill actually works or follows proper format.
Suggestions
Remove the duplicate URL Construction Helper table since it's already in Step 1 of Inline Mode
Add validation step to verify generated SKILL.md has valid YAML frontmatter and required sections before considering the skill complete
Add a feedback loop: 'If skill fails to load, check frontmatter syntax and file permissions, then regenerate'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill has some redundancy - the URL construction table appears twice (Steps 1 and URL Construction Helper section), and the example interactions section largely repeats the workflow steps already documented. However, it avoids explaining basic Rust concepts Claude would know. | 2 / 3 |
Actionability | Provides fully executable commands with concrete examples (agent-browser CLI, specific URLs, directory creation commands). The command syntax is copy-paste ready and includes specific file paths and templates. | 3 / 3 |
Workflow Clarity | Steps are clearly numbered and sequenced for both Agent and Inline modes. However, validation is weak - Step 6 only checks if files exist rather than validating the skill content works correctly. No feedback loop for error recovery during skill creation. | 2 / 3 |
Progressive Disclosure | Well-organized with clear sections separating Agent Mode vs Inline Mode workflows. Tables provide quick reference, and the structure allows scanning for the relevant execution path. Content is appropriately contained in a single file given its scope. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 13 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata' field is not a dictionary | Warning |
license_field | 'license' field is missing | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 13 / 16 Passed | |
- 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.