skills.rest
teslasoft-de
teslasoft-deCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

skill-design

Designs production-grade applet skills using the 10-step Skill Design Loop.

1|1|Updated Jan 25, 2026
Search Tags:#design#evaluation#progressive-disclosure#agent-skills#sdl#security-hardening
One-click install
npx skills add https://github.com/teslasoft-de/claude-skills-marketplace --skill skill-design-teslasoft-de
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-design
Source: https://github.com/teslasoft-de/claude-skills-marketplace/tree/main/plugins/skill-design/skills/skill-design
Command: npx skills add https://github.com/teslasoft-de/claude-skills-marketplace --skill skill-design-teslasoft-de

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) and assets (resource) components.

What problem does it solve?

SDL provides a rigorous, repeatable process to design production-grade agent skills that are maintainable, composable, and auditable.

Core Features & Use Cases

  • The 10-Step Skill Design Loop (SDL) guides from Uncertainty Ledger to Scope, Contract, Progressive Disclosure, Matching Signals, and Lifecycle metadata.
  • Progressive disclosure decouples core instructions from deep references, enabling safe activation with on-demand detail.
  • Security hardening and structured evaluation guardrails ensure predictable behavior and reliable outcomes across projects.

Quick Start

Follow the SDL 10-step process to design a reusable, secure skill from requirement capture to packaging and evaluation.

Frequently Asked Questions about skill-design

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
What is the best way to design production-grade agent skills?▼

Production-grade agent skills are designed using a repeatable 10-step Skill Design Loop, which enforces a contract-first approach with progressive disclosure, security hardening, and structured evaluation guardrails for maintainability.

How do I package reusable agent workflows for safe on-demand activation?▼

Package reusable workflows by applying progressive disclosure, which decouples core instructions from deep references within a prefabricated structure, ensuring safe activation and on-demand detail retrieval.

How does progressive disclosure work in agent skill design?▼

Progressive disclosure decouples core instructions from deep references, allowing agent skills to activate safely with deterministic matching signals and on-demand detail retrieval.

Can I enforce security and evaluation guardrails when building agent skills?▼

Yes, you enforce security hardening and structured evaluation guardrails by following a rigorous design loop that scopes contracts, defines matching signals, and applies lifecycle metadata for predictable behavior.

What structure do I need to create maintainable and auditable agent skills?▼

You need a prefabricated contract-first structure containing SKILL.md, references, and scripts assets to enable deterministic evaluation, robust matching signals, and lifecycle metadata for auditable agent skills.

When should I not use a contract-first approach for agent skill design?▼

A contract-first approach with structured evaluation guardrails may be unnecessary for disposable prototypes where strict lifecycle metadata, security hardening, and deterministic evaluation are not required.

Related Skills

Explore More Design & Creative Skills→
yu13130122297yu13130122297

scout

Identify uncertainties in research framing, datasets, metrics, and baselines.

Community
Intermediate
p-iknowp-iknow
1

meta-skill

Create, validate, and package AI agent skills with SKILL.md metadata.

Community
Intermediate
TrevokeTrevoke
483

test-driven-development

Automate RED-GREEN-REFACTOR cycles with BD-managed TDD workflows.

Community
Advanced
carl10086carl10086
7

writing-great-skills

Design, review, and refactor AI skills for deterministic execution.

Community
Advanced