CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

principle-type-system-discipline

Apply when designing types, reviewing a function signature, or writing code in any statically-typed language. Make illegal states unrepresentable, brand semantic primitives, parse external data at boundaries, exhaust variants, derive from authoritative schemas.

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

92%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.

An exemplary lean principle skill: dense, concrete, well-organized, and free of padding, with explicit when-to-apply conditions on each directive. The only minor gap is the absence of an inline code example of a branded type, which is acceptably delegated to a sibling skill.

DimensionReasoningScore

Conciseness

The body is dense and lean with zero padding — every sentence is either a directive ('Make the compiler reject impossible states, mismatched primitives, and unhandled variants') or a trigger condition ('If two arguments share a primitive type but mean different things, brand them'). It assumes Claude's competence and never explains basics Claude already knows.

5 / 5

Actionability

Guidance is concrete and specific — 'a branded intersection in TypeScript or a newtype elsewhere', 'Have a parse function at every boundary', 'derive from it instead of hand-rolling a parallel type' — with a concrete UserId/OrderId example and named schema sources (protocol buffer, OpenAPI spec, GraphQL schema). It stops short of showing an actual branded-type example, deferring syntax to the typescript-best-practices skill, which is a minor gap rather than fully executable instruction.

4 / 5

Workflow Clarity

This is a simple single-purpose principle skill where the rubric's simple-skill exception applies: each bullet is unambiguous and carries explicit when-to-apply conditions. No multi-step or destructive/batch operations are involved, so no validation checkpoints are required.

5 / 5

Progressive Disclosure

The skill is under 50 lines with no need for external references (the bundle contains none), and the body is well organized as a heading, a two-sentence framing, and three bold-labeled bullets. Cross-references to sibling skills (typescript-best-practices, boundary-discipline, encode-lessons-in-structure) are clearly signaled and one level deep.

5 / 5

Total

19

/

20

Passed

Description

85%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.

A strong description that is specific, complete, and well-structured with an explicit 'Apply when' trigger clause and a comprehensive list of concrete directives. Its main weaknesses are the overly broad 'any statically-typed language' trigger, which raises conflict risk with general coding skills, and missing natural trigger terms like specific language names.

Suggestions

Narrow the trigger clause — e.g. 'Apply when designing or reviewing type definitions, function signatures, or data validation at system boundaries' — so it does not fire on all statically-typed coding tasks.

Add natural trigger terms users would actually say, such as 'TypeScript', 'Rust', 'type safety', or 'type checking', to improve keyword coverage.

Consider dropping 'exhaust variants' or folding it into another directive, since it is jargon-heavy and less likely to be a phrase a user would naturally say.

DimensionReasoningScore

Specificity

The description lists five distinct concrete directives — 'Make illegal states unrepresentable, brand semantic primitives, parse external data at boundaries, exhaust variants, derive from authoritative schemas' — comprehensively covering the skill's scope with no gaps, matching the top anchor rather than the 'minor gaps' of level 4.

5 / 5

Completeness

It explicitly answers both questions: an 'Apply when designing types, reviewing a function signature, or writing code in any statically-typed language' clause for when, and the five-directive list for what. Both are explicit with concrete triggers, matching the top anchor.

5 / 5

Trigger Term Quality

Natural phrases like 'designing types', 'reviewing a function signature', and 'statically-typed language' give good keyword coverage, but common variations users would actually say are missing — language names (TypeScript, Rust), 'type safety', 'type checking'. This fits 'good keyword coverage; a few natural terms missing' rather than the comprehensive synonym coverage of level 5.

4 / 5

Distinctiveness Conflict Risk

The trigger 'writing code in any statically-typed language' is extremely broad and would match nearly all TypeScript/Rust/Java coding tasks, creating real overlap risk with language-specific skills (including the typescript-best-practices skill it references). The distinctive niche of the what-clause keeps it above the 'very broad' level-2 anchor, so it sits at 'somewhat specific but could still overlap with similar skills'.

3 / 5

Total

17

/

20

Passed

Validation

100%

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

geut/factory-skills

Path

.agents/skills/principle-type-system-discipline/SKILL.md

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.