📝
WritingPython

Writing Skills

by GanyuanRan

Writing Skills is a Writing skill for Claude Code, published by GanyuanRan in Aegis.

1.1K stars50 forkson GanyuanRan/AegisAdded 2026/08/21+2% in starsRepository updated 2026/08/19
agent-skillsai-agentsai-codingarchitecture-driven-developmentawsome-coding-pluginbaseline-firstclaude-codecodexcoding-agentsdivedsh-pluginevidence-drivenfirst-principlesopencodesoftware-architecturespec-driven-developmentspec-kit
Install in seconds
Install Writing Skills
Copy Writing Skills into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/GanyuanRan/Aegis/tree/main/skills/writing-skills ~/.claude/skills/writing-skills

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/GanyuanRan/Aegis.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
skills/writing-skills/SKILL.md in GanyuanRan/Aegis
Installs to
~/.claude/skills/writing-skills
Collection
One of 22 skills cataloged from this repository
Category
Writing1012 skills

What Writing Skills does

Writing Skills uses pressure-scenario validation to check whether a skill changes agent behavior before deployment. Use it when creating, editing, or verifying skills and you need baseline-first validation.

Writing Skills is cataloged under Writing on DirSkills. Writing Skills comes from a repository tagged agent-skills, ai-agents, ai-coding, architecture-driven-development and awsome-coding-plugin.

Documentation

README

Writing Skills

Overview

Writing skills uses pressure-scenario validation, not a code TDD route.

Personal skills live in agent-specific directories (~/.claude/skills for Claude Code, ~/.agents/skills/ for Codex)

You write test cases (pressure scenarios with subagents), watch them fail (baseline behavior), write the skill (documentation), watch tests pass (agents comply), and refactor (close loopholes).

Core principle: If you didn't watch an agent fail without the skill, you don't know if the skill teaches the right thing.

Validation requirement: Skill changes need a baseline pressure scenario and post-change validation even when TDD mode is off; this does not require loading aegis:test-driven-development.

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Writing Skills

  • What else does GanyuanRan publish alongside Writing Skills?

    Writing Skills is one of 22 skills that DirSkills catalogs from GanyuanRan/Aegis, the repository it ships in. Its siblings there include Aegis Goal Framing, Anti-Entropy Governance and Brainstorming. Each one is a separate skill with its own page in this directory, installs the same way Writing Skills does, and is maintained by GanyuanRan in that same repository. The rest of the collection is listed on the GanyuanRan/Aegis page.

  • How does Writing Skills compare to other Writing skills?

    Writing Skills ranks #421 by stars among the 1012 Writing skills in this catalog. The most-starred ones next to it are Article Writing, Social Media Content Calendar and Knowledge Comic Creator. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Writing Skills against them. Open each page to compare what they document and how they install.

More from GanyuanRan/Aegis

Writing Skills is one of 22 skills cataloged on DirSkills from GanyuanRan/Aegis.

See all 22 skills
🎯
1w ago

Aegis Goal Framing

Aegis Goal Framing creates a thin goal frame before execution when a user sets an Aegis goal or asks for scope, success evidence, or stop conditions. It is used to define boundaries before routing into the next workflow.
AI Engineering
1.1K50
🧭
1w ago

Anti-Entropy Governance

Anti-Entropy Governance helps decide when to delete old code paths, collapse duplicate owners, or remove fallbacks safely. It also guards schema, persistence, and source-of-truth changes that need explicit confirmation.
AI Engineering
1.1K50
🧠
1w ago

Brainstorming

Brainstorming helps turn ambiguous or high-complexity ideas into clearer designs by asking focused questions, comparing approaches, and shaping a spec before implementation. Use it for new features, architecture, contracts, or plan pressure-tests.
AI Engineering
1.1K50
🔍
1w ago

Code Review Reception

Code Review Reception helps you evaluate code review feedback before making changes. Use it when comments are unclear, risky, disputed, or may conflict with the codebase or prior decisions.
Quality
1.1K50
✍️
1w ago

Communicating Concisely

Communicating Concisely shortens responses when the user asks for caveman mode, fewer tokens, or brief answers. It drops filler and keeps technical details exact until turned off.
Writing
1.1K50
🤖
1w ago

Dispatching Parallel Agents

Dispatching Parallel Agents delegates unrelated tasks to separate agents with isolated context. Use it when 2+ independent problems can be worked in parallel; otherwise handle them inline or with a planned subagent workflow.
AI Engineering
1.1K50