Open Contribution

Contribute a Skill to SkillOS

Every skill in the registry follows the 13-component Skill Definition Standard (SDS). No shortcuts. No stubs. Production-grade or nothing.

13Required components
15Min. failure modes
3Validation tests required
100%Open source · MIT

Step 1: Choose Your Tier

The tier determines how deep and broad your skill must be. Higher tiers require more domain coverage.

Tier 0Foundational

Cross-cutting principles (Security, Architecture, Systems Thinking, Safety)

Tier 1Domain Specialist

Full engineering domains (Backend, Frontend, DevOps, Mobile, ML/AI)

Tier 2Technology Expert

Specific tech stacks (React, Next.js, PostgreSQL, Python, Node.js)

Tier 3Pattern Specialist

Cross-cutting patterns (Auth, Testing, CI/CD, API Design)

Tier 4Orchestration

Multi-skill workflows and system-level automation

Step 2: Complete All 13 SDS Components

All 13 components are required. Missing any component causes automatic rejection by the SDS validator. No exceptions.

01

Skill Metadata

Required

YAML frontmatter: skill_name, display_name, version, tier, domain, status, temperature_mode, access_level, tags.

skill_name: react_expert
tier: 2
status: stable
02

Professional Identity

Required

First-person professional declaration. Who this skill is, what it does, and its confidence calibration thresholds.

I am a React Expert with 6+ years of production experience...
03

Knowledge Taxonomy

Required

Structured breakdown of the skill's domain knowledge: core concepts, current best practices, deprecated patterns, tool landscape.

### Hooks [CORE]
- useState, useReducer, useEffect...
04

Capability Boundaries

Required

Explicit in-scope and out-of-scope definitions. Routing table: what to escalate to which skill.

### Out of Scope
- Backend API design → Backend Specialist
05

Decision Engine

Required

4-phase reasoning process: Ethics check → Classification → Assessment → Generation. How the skill thinks before answering.

Phase 1 — Ethics: check for dark patterns...
Phase 2 — Classification...
06

Constraint Matrix

Required

Table of non-negotiable constraints: Performance, Safety, Security, Global, Reversibility, Accessibility, etc.

| Performance | Core Web Vitals: LCP < 2.5s |
07

Failure Mode Library

Required

Exactly 15 documented failure modes: what breaks, why it breaks, how to fix it. Must be real production failure modes.

1. **N+1 query problem** — Fix: use DataLoader or include...
08

Quality Gates

Required

Checklist of minimum standards before any output is delivered. Must be verifiable and specific.

- [ ] All useEffect have explicit dependency arrays
- [ ] No console.log in production
09

Output Templates

Required

3+ structured output modes for different request types. Each template is a reusable pattern.

### Mode 1: Component Architecture
```tsx
const Component: React.FC = () => {...}
```
10

Ethical Constraint Layer

Required

Explicit ethics rules that override all other instructions. Anti-manipulation, transparency, harm surface audit.

Never implement dark UX patterns regardless of client request.
11

Safety Layer

Required

Reversibility classification (LOW/MEDIUM/HIGH/CRITICAL), blast radius assessment, data minimalism, dependency safety.

Reversibility: Schema migrations are HIGH risk...
12

Collaboration Contract

Required

Typed I/O specification: what this skill receives_from and outputs_to other skills. Portability statement.

receives_from:
  software_architect:
    type: 'System context'
13

Validation Record

Required

3 test cases (simple, ambiguous, edge case) each with a prompt, PASS/FAIL result, and notes. Run against a real LLM.

test_1_simple:
  prompt: '...'
  result: PASS
  notes: '...'

Step 3: Submit Your Skill

1

Read the existing skills

Study at least 2 skills in the same tier as your proposal. Understand the depth and format expected.

Browse Skills
2

Choose the right tier

Tier 0 = foundational principle. Tier 1 = full engineering domain. Tier 2 = specific tech. Tier 3 = cross-cutting pattern. Tier 4 = orchestration.

3

Write all 13 SDS components

Every component is required. Incomplete skills are automatically rejected by the SDS validator. 15 failure modes minimum.

4

Run 3 validation tests

Test with a real LLM: one simple prompt, one ambiguous prompt, one edge case. Document results in Component 13.

5

Submit a GitHub Pull Request

Add your skill .md file to the correct registry/tier-N/ directory. The PR template will guide you through the checklist.

Open GitHub

The Quality Bar

SkillOS skills are activated in production AI systems. They need to handle edge cases, failure modes, and global context — not just the happy path. If your skill only covers the easy cases, it will be sent back for revision. The 15-failure-mode requirement exists because the hard cases are where skills earn their place.

Global-first: no US-only or EU-only defaults
15 real production failure modes minimum
3 validation tests with actual LLM results
Explicit confidence calibration rules
Ethics and safety layers completed
Collaboration contract with typed I/O

Ready to contribute?

Read an existing Tier 1 skill to calibrate your expectations, then open a GitHub PR.