writing-skills

Create and test agent skills using test-driven development with subagent pressure scenarios.

Updated Mar 26, 2026
One-click install
npx skills add https://github.com/LGJ-Jonathan/Jonathan_Global_Claude_Skills --skill writing-skills-lgj-jonathan
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: writing-skills
Source: https://github.com/LGJ-Jonathan/Jonathan_Global_Claude_Skills/tree/main/superpowers/skills/writing-skills
Command: npx skills add https://github.com/LGJ-Jonathan/Jonathan_Global_Claude_Skills --skill writing-skills-lgj-jonathan

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Writing documentation for AI agents often fails because untested instructions get rationalized away under pressure. This Skill applies test-driven development to skill authoring so you can 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 for Claude Search Optimization, including description writing rules, keyword coverage, naming conventions, and token efficiency targets. - Testing Methodology: Detailed reference for building multi-pressure scenarios, rationalization tables, red flag lists, and meta-testing techniques. - Use Case: When creating a new discipline-enforcing skill like TDD or verification-before-completion, run baseline scenarios without the skill, document verbatim rationalizations, then iterate until agents comply under maximum pressure. ## Quick Start Use the writing-skills skill to create a new skill for my agent following the test-driven development process.

Frequently Asked Questions about writing-skills

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

FAQPage Schema
How do I create a new skill for an AI agent?

Create a directory containing a SKILL.md file with YAML frontmatter defining name and description, followed by markdown instructions. Run baseline pressure scenarios with subagents first, then write the skill addressing the specific failures you observed.

How do I test that an agent skill actually works?

Test skills by running realistic pressure scenarios with subagents, combining three or more pressures like time constraints, sunk cost, and authority. Document exact rationalizations verbatim, then add explicit counters and re-test until agents comply.

What should go in a SKILL.md description field?

The description should start with "Use when..." and describe only triggering conditions, symptoms, and situations in third person. Never summarize the skill's workflow, because agents may follow the description instead of reading the full skill body.

When should I not create a skill?

Skip skill creation for one-off solutions, standard practices documented elsewhere, project-specific conventions that belong in CLAUDE.md, and mechanical constraints that can be enforced with validation or automation instead of documentation.

Why do agents ignore skill instructions under pressure?

Agents rationalize violations using excuses like sunk cost, time pressure, or spirit-versus-letter arguments. Counter this with explicit negations of each loophole, rationalization tables, red flag lists, and foundational principles stated early.