m05-type-driven

CRITICAL: Use for type-driven design. Triggers: type state, PhantomData, newtype, marker trait, builder pattern, make invalid states unrepresentable, compile-time validation, sealed trait, ZST, 类型状态, 新类型模式, 类型驱动设计

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 ./skills/m05-type-driven/SKILL.md

Quality

Content

85%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 a lean, well-structured reference for type-driven design with concrete Rust examples and a clear decision workflow, losing only minor points on actionability due to abbreviated code bodies.

Dimension	Reasoning	Score
Conciseness	The body is lean and reference-style: tables, short code snippets, and terse prompts that assume Claude's knowledge of Rust type mechanics, with no padding or explanation of basic concepts.	5 / 5
Actionability	It provides concrete, mostly-executable Rust snippets (Newtype with validation, type-state Connection transitions) and clear pattern-to-implementation mappings, though several examples are abbreviated with '...' bodies that are not fully copy-paste ready.	4 / 5
Workflow Clarity	The 'Thinking Prompt' and 'Trace Up/Trace Down' sections give a clear sequenced decision process with trace-to checkpoints, but there are no explicit validate/verify feedback loops; since this is a design-decision skill rather than a destructive/batch operation, the missing-validation cap does not apply.	4 / 5
Progressive Disclosure	For a sub-50-line skill with no bundle files, the body is well-organized into clearly signaled sections (Core Question, Thinking Prompt, Trace Up/Down, Quick Reference, Anti-Patterns), satisfying the simple-skill exception for progressive disclosure.	5 / 5
	Total	18 / 20 Passed

Description

61%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 well-populated with natural type-system trigger terms, giving it a clear niche, but it lacks an explicit 'Use when...' clause, which caps its completeness.

Suggestions

Add an explicit 'Use when...' clause (e.g., 'Use when designing types to make invalid states unrepresentable or encoding invariants at compile time') to raise completeness.

Tighten the 'Triggers:' list into a few concrete user-facing phrases and a couple of natural synonyms to lift trigger term quality.

Clarify the distinct action (e.g., 'Encode invariants and state transitions in the type system') so the 'what' reads as an action rather than only a topic list.

Dimension	Reasoning	Score
Specificity	The description lists several concrete type-driven design mechanisms (type state, PhantomData, newtype, marker trait, builder pattern, sealed trait, ZST), which are specific actions/patterns, though it is a list of techniques rather than actions performed on artifacts, leaving minor coverage gaps.	4 / 5
Completeness	The 'what' is reasonably clear (type-driven design), but there is no explicit 'Use when...' clause despite a 'Triggers:' prefix; the judging guidelines cap completeness at 3 when explicit trigger guidance of the 'Use when...' form is missing.	3 / 5
Trigger Term Quality	It includes strong natural developer terms like 'type state', 'newtype', 'builder pattern', and 'make invalid states unrepresentable' plus bilingual synonyms, but a few common phrasings users might say are absent.	4 / 5
Distinctiveness Conflict Risk	The trigger set is narrowly focused on type-driven Rust idioms with distinct markers, giving it a clear niche with only minor overlap risk against closely related design skills like m09-domain.	4 / 5
	Total	15 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: actionbook/rust-skills
Path: skills/m05-type-driven/SKILL.md
Commit: 5c40d3a

Reviewed: 14 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.