skills.rest
kangjuhyup
kangjuhyupCOMMUNITY
Explore all skills by this author →
GitHub

writing-skills

Create and test agent skills using TDD-style pressure scenarios with subagents.

Updated Sep 6, 2026
Search Tags:#documentation#prompt engineering#test-driven development#skill authoring#rationalization#skill discovery#subagent testing
One-click install
npx skills add https://github.com/kangjuhyup/study --skill writing-skills-kangjuhyup
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: writing-skills
Source: https://github.com/kangjuhyup/study/tree/main/scoped-superpowers-ab/workflow-code-benchmark/fixture/workflows/full/skills/writing-skills
Command: npx skills add https://github.com/kangjuhyup/study --skill writing-skills-kangjuhyup

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Writing documentation-style skills for AI agents often fails because untested instructions get rationalized away under pressure; this Skill applies Test-Driven Development to skill authoring so you verify agents actually comply before deployment. ## Core Features & Use Cases - TDD-based skill authoring: Run baseline pressure scenarios with subagents (RED), write the skill addressing observed failures (GREEN), then close rationalization loopholes (REFACTOR). - Discovery optimization guidance: Rules for writing name and description frontmatter, keyword coverage, token efficiency, and cross-referencing so agents can find the skill. - Testing methodology references: Includes guides for pressure-scenario testing, persuasion principles for discipline-enforcing skills, Anthropic's official best practices, and a graphviz diagram renderer. - Use Case: Before publishing a new TDD-enforcement skill, run a scenario where an agent has sunk cost and time pressure, document its verbatim rationalizations, then bulletproof the skill against each excuse. ## Quick Start Ask the agent to create a new skill following the writing-skills TDD process, starting with a baseline pressure scenario before writing any SKILL.md content.

Frequently Asked Questions about writing-skills

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

FAQPage Schema
How do I test a new agent skill before deploying it?▼

Run pressure scenarios with subagents without the skill first to capture baseline failures verbatim, then write the skill addressing those failures and re-test until agents comply. Combine three or more pressures like time, sunk cost, and authority for realistic results.

What should go in a SKILL.md description field?▼

Write a third-person description starting with "Use when..." that lists only triggering conditions and symptoms, never a summary of the skill's workflow. Keep it under 500 characters and include searchable keywords like error messages and tool names.

Why do agents ignore skills under time pressure?▼

Agents rationalize skipping rules when facing sunk cost, deadlines, or authority pressure. The fix is explicit loophole closing: rationalization tables, red-flag lists, and foundational principles like "violating the letter is violating the spirit."

When should I not create a new skill?▼

Skip skill creation for one-off solutions, project-specific conventions, well-documented standard practices, or mechanical constraints that can be enforced with validation or regex instead of documentation.

How do I render flowcharts from a SKILL.md file?▼

Run the included render-graphs.js script with the skill directory path to extract dot blocks and render them to SVG via graphviz. Use the --combine flag to merge all diagrams into a single SVG file.

Related Skills

Explore More Software Engineering Skills→
HalseyYangHalseyYang
1

writing-skills

Create and test agent skills using test-driven development methodology.

Community
Advanced
AndrejKiriAndrejKiri

design-system-apply-feedback

Apply feedback documents to design system skills with version bumps.

Community
Intermediate
lgerard314lgerard314

coverage-gap-detection

Identify untested paths and missing coverage in a codebase.

Official
Advanced
nimadorostkarnimadorostkar
25

hooks

Implement deterministic lifecycle hooks to enforce operational rules during agent execution.

Community
Advanced