Writing Skills
If you've ever watched an AI agent completely ignore your carefully written instructions or fail to surface the skill you need, this is the fix. It's a meta-skill that teaches you how to write agent skills that actually work: decision trees for picking the right architecture tier, CSO techniques so LLMs can find your skill, anti-rationalization patterns so agents follow your rules instead of talking their way around them, and templates for technique, reference, discipline, and pattern skills. The quick decision tree alone is worth it. Think of it as the missing manual for skill authors who are tired of agents doing their own thing.
- skills.sh installs
- 674
- GitHub stars
- 43.1K
- last updated
- Jul 14, 2026
Install
$ npx -y skills add sickn33/antigravity-awesome-skills --skill writing-skills --agent claude-codeInstalls into .claude/skills of the current project.
Files
Writing Skills (Excellence)
Compatibility: these templates are conventions, not a universal loader schema. Use the target host's documented skill directory and current schema; custom metadata.triggers is optional and does not itself guarantee discovery. Bundled upstream guidance is a historical snapshot. Rendering requires Node.js and a locally installed Graphviz dot; inspect trusted DOT only, and open generated SVG cautiously. --combine shares node IDs across graphs and is a visual convenience, not a semantics-preserving merge. Outputs are exclusive: remove or choose another output directory deliberately before rerunning.
Scope: examples are authoring/test fixtures, not live instructions. Follow the user, host, and repository instruction hierarchy. Run pressure tests only with authorized isolated fixtures; never delete user work or weaken safety/approval boundaries to enforce a skill. Preserve existing work and adapt the validation plan when a baseline already passes. Sample compliance does not prove universal reliability.
Dispatcher for skill creation excellence. Use the decision tree below to find the right template and standards.
⚡ Quick Decision Tree
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/sickn33/antigravity-awesome-skills
- Categories
- Documentation, Skill Development
- First seen
- May 16, 2026
More from sickn33/antigravity-awesome-skills
All 708- Instagram Automation672
- Marketing Ideas672
- Skill Developer670
- Postgresql664
- Viral Generator Builder662
- Test Fixing661
- Behavioral Modes659
- Loki Mode658
- Observability Engineer656
- Tiktok Automation648
- Aws Skills645
- Environment Setup Guide645
- Remotion Best Practices644
- Paid Ads642
- Pentest Checklist634
- Code Refactoring Tech Debt630
- Crewai630
- Api Documenter628
- Langfuse628
- Avalonia Layout Zafiro625
- Pricing Strategy621
- Email Systems616
- Backend Development Feature Development615
- Social Content615
Recommended
More Documentation
wikiyeachan-heo/oh-my-claudecodeLLM Wiki — persistent markdown knowledge base that compounds across sessions (Karpathy model)663skills.sh installs
hook-writingmotion-team/creative-strategy-skillsWrites high-converting, psychologically-driven hooks for paid ads, TikTok, Instagram Reels, and organic content. Use this whenever a user wants to write hooks, 653skills.sh installs
writing-linkedin-postsjamesgray007/hoai-courseCreate engaging, authentic LinkedIn posts like a Top Voice. Use this skill when asked to write LinkedIn content, social media posts for LinkedIn, professional t649skills.sh installs
writing-humanizer-zhhairyf/skills去除文本中的 AI 生成痕迹。适用于编辑或审阅文本，使其听起来更自然、更像人类书写。 基于维基百科的"AI 写作特征"综合指南。检测并修复以下模式：夸大的象征意义、 宣传性语言、以 -ing 结尾的肤浅分析、模糊的归因、破折号过度使用、三段式法则、 AI 词汇、否定式排比、过多的连接性短语。630skills.sh installs
docker-security-guidejosiahsiegel/claude-plugin-marketplaceComprehensive Docker security guidelines and threat mitigation. PROACTIVELY activate for: (1) container security review, (2) running as non-root user, (3) read-619skills.sh installs
paper-writingwanshuiyin/auto-claude-code-research-in-sleepWorkflow 3: Full paper writing pipeline that goes from a narrative report to a polished, submission-ready PDF. Use when user says "写论文全流程", "write paper pipelin595skills.sh installs