Your AI agent is lazy. These 1432 skills fix that.
AI agents skip tests, ignore security, write placeholder code, and cut corners whenever they can. 1ai-skills forces them to follow real workflows with anti-rationalization tables, code examples, and verification checklists — across every domain.
Your AI agent says:
"I'll add tests later." "Security is a nice-to-have." "This placeholder works fine."
It doesn't. It won't. It never does.
Every skill in this library includes an Anti-Rationalization Table — a structured argument that prevents your agent from cutting corners:
| Rationalization | Reality |
|---|---|
| "Tests slow me down" | Bugs slow you down 10x more. Tests are speed, not overhead. |
| "I will refactor later" | Technical debt compounds. Refactor as you go. |
| "It works on my machine" | If it is not in CI, it does not work. Ship proof, not claims. |/plugin marketplace add oyi77/1ai-skills
/plugin install 1ai-skills@1ai-skillsgit clone https://github.com/oyi77/1ai-skills.git
cp -r 1ai-skills/cybersecurity/* .cursor/rules/gemini skills install https://github.com/oyi77/1ai-skills.git --path skillsgit clone https://github.com/oyi77/1ai-skills.git
# Point your agent to the skills/ directory| Category | Skills | What It Covers |
|---|---|---|
| Cybersecurity | 801 | Threat hunting, forensics, pen testing, SOC, incident response |
| Development | 106 | TDD, debugging, code review, PRD, engineering workflows |
| Content | 108 | Video, audio, design, writing, docs |
| Mindset | 55 | Negotiation, leadership, critical thinking |
| Marketing | 45 | SEO, viral content, email, ads, growth |
| Core | 53 | AI infrastructure, memory, self-improvement, model routing |
| Integrations | 29 | GitHub, Discord, Notion, Slack, Stripe, Firebase, Supabase |
| DevOps | 32 | Docker, Kubernetes, CI/CD, cloud ops, GitOps |
| Automation | 21 | Bots, workflows, scrapers, process automation |
| Research | 38 | Deep research, market analysis, competitive intelligence |
| Trading | 27 | Crypto, DeFi, Polymarket, trading strategies |
| Operations | 20 | Business ops, governance, HR, legal, project management |
| Agents | 16 | AI agent orchestration, coding, research, autonomous execution |
| MCP | 15 | Model Context Protocol servers and tool integrations |
| Meta | 14 | Self-evolving meta-skills, performance monitoring |
| Financial | 19 | Finance analysis, valuation, tax, portfolio management |
| Sales | 15 | Lead gen, CRM, outreach, sales automation |
| Data | 8 | Data pipelines, analysis, visualization, ETL |
| Productivity | 10 | Calendars, email, meetings, workspace management |
For AI agents to efficiently navigate 1432+ skills without loading everything into context, 1ai-skills follows a corporate organizational structure:
- Level 0 (The CEO): Root orchestrator. Takes high-level strategic goals, delegates to C-suite.
- Level 1 (C-Suite):
- CTO (Tech & R&D)
- CMO (Marketing & Acquisition)
- CCO (Content & Creative)
- CFO (Finance & Investment)
- COO (Operations & Process)
- Level 2 (Role Anchors): Department heads (17 job roles) representing employee responsibilities.
- Level 3 (Atomic Skills): The 1432 specialized playbooks used by the roles above.
| Other repos | 1ai-skills | |
|---|---|---|
| Skills | 24-100 curated | 1432 tested |
| Anti-rationalization | Some | Every skill |
| Code examples | Some | Every skill |
| Test suite | None | 8-dimension, 100% pass |
| Cybersecurity | None | 801 skills |
| Verification checklists | Some | Every skill |
| Dynamic website | Static | Auto-generated from data |
| Self-evolving | No | Meta-skills that improve |
- YAML frontmatter — Machine-readable metadata (name, description, domain, tags)
- Anti-Rationalization Table — Prevents agents from cutting corners
- Code Examples — Concrete, runnable code (Python, JS, Bash, SQL)
- Workflow — Step-by-step instructions with bold labels
- When to Use — 3+ trigger conditions
- When NOT to Use — 2+ contraindications
- Verification Checklist — Success criteria you can check
python3 scripts/test-skills.py # Full test
python3 scripts/test-skills.py --quick # Skip SDK checks
python3 scripts/test-skills.py --json # JSON output
python3 scripts/test-skills.py --skill NAME # Single skill8 test dimensions:
- Structure (YAML frontmatter, required fields)
- Content (sections, depth, no placeholders)
- Code syntax (Python
ast.parse, JS/TS, Bash) - Internal links (all
/skills/links resolve) - Description quality (50-200 chars, action-oriented)
- Quality markers (anti-rationalization, code, verification)
- SDK availability (referenced imports are installable)
- Workflow completeness (has workflow section)
Result: 1432/1432 PASS · 0 warnings · 0 failures
| Skill | Category | What It Does |
|---|---|---|
| docx-creator | content | Generate Word documents programmatically |
| pdf-creator | content | Create, edit, extract PDFs |
| pptx-creator | content | Build PowerPoint presentations |
| xlsx-creator | content | Create Excel spreadsheets with formulas |
| canvas-design | content | Generative art, SVG, data visualizations |
| frontend-ui-design | content | React/Vue UI components, design systems |
| theme-factory | content | Design tokens, color systems, typography |
| gemini-api-dev | core | Google Gemini API integration |
| replicate-runner | core | Run AI models on Replicate cloud |
| model-router | core | Multi-provider LLM routing |
| stripe-integration | integrations | Stripe payments and subscriptions |
| supabase-integration | integrations | Supabase auth, DB, real-time |
| firebase-integration | integrations | Firebase auth, Firestore, functions |
| bigquery-integration | integrations | BigQuery analytics and SQL |
| spec-driven-development | development | PRD-first workflow |
| context-engineering | development | Agent context window design |
| browser-testing-devtools | development | Playwright E2E testing |
| git-workflow-mastery | development | Advanced Git workflows |
1ai-skills includes 13 meta-skills that make the library improve itself:
- skill-tracker — Logs every skill invocation with metrics
- skill-evolver — Analyzes usage patterns and suggests improvements
- skill-feedback-capture — Captures user feedback on skill quality
- auto-learner — Learns from corrections and updates skills
- performance-monitor — Tracks skill success rates and response quality
- skill-banner — Shows activation banner with skill summary
| Command | What It Does |
|---|---|
/find |
Search and activate the right skill |
/audit |
Run comprehensive skill library audit |
/lint |
Lint and fix skill content quality |
/new-skill |
Create a new skill from template |
# Create a new skill
python3 scripts/generate-site.py # Regenerate website
bash scripts/audit-skills.sh --write # Update SKILLS.json
python3 scripts/validate-skills.py # Validate structure
python3 scripts/test-skills.py # Run all testsSee CONTRIBUTING.md for guidelines.
- Claude Code
- Cursor
- Gemini CLI / Antigravity
- Windsurf
- OpenCode
- GitHub Copilot
- Kiro
- Any agent that reads SKILL.md files
MIT — use freely, contribute back.
Star this repo if it saves your agent from being lazy.