writing-skills

Creates, edits, and verifies SKILL.md agent documentation with pressure testing and loophole hardening.

Updated May 28, 2026

Search Tags:#testing #tdd #documentation #skills #skill authoring #agent workflows

Ready to run

npx skills add https://github.com/haryelramalho/skills --skill writing-skills-haryelramalho

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: writing-skills
Source: https://github.com/haryelramalho/skills/tree/main/skills/community/writing-skills
Command: npx skills add https://github.com/haryelramalho/skills --skill writing-skills-haryelramalho

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you create, edit, and verify agent skills so they are discoverable, concise, and reliable under pressure instead of being ignored or followed inconsistently.

Core Features & Use Cases

Skill authoring guidance: Structure SKILL.md with effective metadata, clear triggers, and compact instructions.
Testing before deployment: Use baseline scenarios, pressure tests, and refactoring cycles to expose failure modes before shipping a skill.
Loophole hardening: Add explicit counters, red flags, and rationalization handling for discipline-enforcing skills.
Reference organization: Split heavy material into supporting files and keep the main skill focused and token-efficient.
Use Case: A team writing a new workflow skill can validate that agents comply under time pressure, sunk cost, and authority pressure before making it available.

Quick Start

Use this skill to draft or review a SKILL.md file, then test it against realistic pressure scenarios before deployment.

Frequently Asked Questions about writing-skills

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

FAQPage Schema

How do I write agent skills that are actually followed and not ignored?▼

Agent skill authoring requires concise metadata, strong trigger wording, and iterative testing to close rationalization loopholes. Structuring SKILL.md with compact instructions and explicit counters ensures agents comply reliably under pressure instead of ignoring or inconsistently following instructions.

How do I test agent skills before deployment to ensure reliable behavior?▼

Testing agent skills before deployment involves running baseline scenarios and pressure tests to expose failure modes. Refactoring cycles validate behavior under time pressure, sunk cost, and authority pressure, ensuring the skill documentation holds up reliably before making it available.

Why does my agent ignore skill documentation or apply it inconsistently?▼

Agents ignore skill documentation when metadata lacks clear triggers or concise instructions. Rationalization loopholes allow agents to bypass rules under pressure; adding explicit counters, red flags, and discipline-enforcing wording hardens the skill and forces consistent compliance.

How do I harden discipline-enforcing skills against agent rationalization?▼

Hardening discipline-enforcing skills requires adding explicit counters, red flags, and rationalization handling directly within the SKILL.md. By anticipating pressure scenarios like sunk cost or authority pressure, you close loopholes that allow agents to bypass the intended rules.

What is the best way to organize heavy reference material in agent skills?▼

Organizing heavy reference material in agent skills requires splitting complex content into supporting files. Keeping the main skill focused and token-efficient ensures agents process the core instructions without being overwhelmed by excessive context.