> Agent Skills Architecture
Foundational "High-Density" standard for token-optimized agent instructions and CLI-based automated activation.
curl "https://skillshub.wtf/HoangNguyen0403/agent-skills-standard/agent-skills-architecture?format=md"Agent Skills Architecture Standard
Priority: P0 (CRITICAL)
The primary goal is Maximum Information Density and Automated Precision.
🏗️ Core Architectural Pillars
1. Separation by Package (Granularity)
- Rule: Separate skills based on specific library/framework dependencies.
- Goal: Avoid context pollution. Don't load "Riverpod" instructions into a "BLoC" project.
- Example:
flutter/bloc-state-managementvsflutter/riverpod-state-management.
2. Presence = Active (Simplified Configuration)
- Logic: If a skill is listed in
.skillsrc, it is considered active. - Standard: Remove legacy
enabledflags. Control activation via inclusion/exclusion lists.
3. CLI Detection & Dynamic Exclusion
- Mechanism: The CLI (
ags) mapspackage.json/pubspec.yamldependencies to skill IDs. - Exclusion: Irrelevant sub-skills are automatically added to the
excludelist during initialization if their corresponding packages are missing.
4. Progressive Disclosure (Three-Level Loading)
- Level 1 (Metadata): Triggers activation via high-precision keywords/files.
- Level 2 (SKILL.md Body): Core imperative logic (<100 lines). No conversational fluff.
- Level 3 (References): Detailed examples, complex patterns, scripts. Lazy-loaded on-demand.
📦 ID & Naming Standards
- Category: Lowercase letters (e.g.,
flutter,nestjs). - Skill ID: Kebab-case, must match the directory name.
- Registry ID: Must match the Skill ID for automated CLI detection/exclusion.
📋 High-Density Writing Style
- Imperative Mood: Use "Use X", "Avoid Y". No "Please" or "You should".
- Token Compression: Skip articles ("the", "a") where possible. Use bullet points > paragraphs.
- Anti-Patterns: Avoid conversational intros ("In this skill, we see...").
🔗 Internal References
- Skill Creator Standard - Detailed authoring rules.
- Resource Organization - Folder structure best practices.
> related_skills --same-repo
> typescript-tooling
Development tools, linting, and build config for TypeScript. Use when configuring ESLint, Prettier, Jest, Vitest, tsconfig, or any TS build tooling. (triggers: tsconfig.json, .eslintrc.*, jest.config.*, package.json, eslint, prettier, jest, vitest, build, compile, lint)
> typescript-security
Secure coding practices for TypeScript. Use when validating input, handling auth tokens, sanitizing data, or managing secrets and sensitive configuration. (triggers: **/*.ts, **/*.tsx, validate, sanitize, xss, injection, auth, password, secret, token)
> typescript-language
Modern TypeScript standards for type safety and maintainability. Use when working with types, interfaces, generics, enums, unions, or tsconfig settings. (triggers: **/*.ts, **/*.tsx, tsconfig.json, type, interface, generic, enum, union, intersection, readonly, const, namespace)
> typescript-best-practices
Idiomatic TypeScript patterns for clean, maintainable code. Use when writing or refactoring TypeScript classes, functions, modules, or async logic. (triggers: **/*.ts, **/*.tsx, class, function, module, import, export, async, promise)