writing-skills

Author and verify agent Skills using red-green-refactor pressure scenarios.

Updated Mar 16, 2026
One-click install
npx skills add https://github.com/chuangkevin/project-bridge --skill writing-skills-chuangkevin
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: writing-skills
Source: https://github.com/chuangkevin/project-bridge/tree/main/skill/superpowers/writing-skills
Command: npx skills add https://github.com/chuangkevin/project-bridge --skill writing-skills-chuangkevin

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Helps authors convert informal processes and tribal knowledge into concise, discoverable Skills that are verified under pressure so agents reliably follow discipline-enforcing patterns.

Core Features & Use Cases

  • Prescribes a RED-GREEN-REFACTOR workflow for skill authoring and verification using pressure scenarios and subagent tests.
  • Provides templates for pressure scenarios, rationalization tables, red-flag lists, and verification checklists to harden discipline-enforcing skills.
  • Includes guidance on discovery-optimized metadata (name/description conventions) and progressive disclosure so Skills load only when relevant.
  • Use case: creating a TDD-based documentation skill that forces agents to delete untested code and prove compliance under combined time, sunk-cost, and authority pressures.

Quick Start

Write a failing pressure scenario, run it without the skill to capture exact rationalizations, author a minimal SKILL.md addressing those failures, and re-run the scenario to verify compliance.

Frequently Asked Questions about writing-skills

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

FAQPage Schema
How do I test agent skills using test-driven documentation?

Test-driven documentation validates agent skills by writing a failing pressure scenario, capturing rationalizations, authoring a minimal SKILL.md, and re-running it to verify compliance. This enforces process discipline before deployment.

What are pressure scenarios in agent testing?

Pressure scenarios are test cases that verify discipline-enforcing skills under combined time, sunk-cost, and authority pressures. They force agents to prove compliance and prevent rationalization when following strict processes.

How do I convert tribal knowledge into reusable agent skills?

Convert tribal knowledge into reusable skills by applying red-green-refactor workflows to author minimal SKILL.md files. This transforms informal processes into tested, discoverable skills that agents reliably follow.

Can I use subagent tests to verify skill compliance?

Yes, subagent-based tests verify skill compliance by running pressure scenarios against authored SKILL.md files. This validates that agents enforce process discipline and delete untested code when required.

What is the best way to structure skill metadata for discovery?

Structure discovery-optimized metadata using specific name and description conventions with progressive disclosure. This ensures skills load only when relevant, maximizing discoverability while minimizing unnecessary context loading.

When do I need rationalization tables in skill authoring?

Rationalization tables document exact failure rationalizations captured during initial pressure scenario testing. They are needed when hardening discipline-enforcing skills to prevent agents from bypassing required processes under pressure.