Create uncontested market space using value innovation instead of competing head-to-head. Use when the user mentions "blue ocean", "red ocean", "strategy canvas", "ERRC framework", "value innovation", or "non-customers". Covers the Four Actions Framework, buyer utility map, and value-cost trade-offs. For tech adoption strategy, see crossing-the-chasm. For product positioning, see obviously-awesome.
- Exploring the runpod-flash framework codebase
- 📁 examples/
- 📁 reference/
- 📄 SKILL.md
Develop and maintain the SimpleLLMFunc framework itself. Use when changing framework internals, tests, docs, specs, runtime primitives, decorator behavior, tool plumbing, event streams, PyRepl integration, or contributor-facing project structure and conventions.
- 📁 assets/
- 📁 references/
- 📁 scripts/
- 📄 SKILL.md
Analyzes and improves prompts using 27 research-backed frameworks across 7 intent categories. Use when a user wants to improve, rewrite, structure, or engineer a prompt — including requests like "help me write a better prompt", "improve this prompt", "what framework should I use", "make this prompt more effective", or any prompt engineering task. Recommends the right framework based on intent (create, transform, reason, critique, recover, clarify, agentic), asks targeted questions, and delivers a structured, high-quality result.
- 📁 .github/
- 📁 agents/
- 📁 commands/
- 📄 .gitignore
- 📄 CHANGELOG.md
- 📄 LICENSE
Multi-agent orchestration framework for Claude Code. Automatically delegates tasks to cheaper, faster sub-agents (Haiku 4.5, Sonnet 4.6) while maintaining Opus-level quality through verification. Use when working on any coding task — Hydra activates automatically to route file exploration, test running, documentation, code writing, debugging, security scanning, and git operations to the optimal agent. Saves ~50% on API costs. --- # 🐉 Hydra — Multi-Headed Speculative Execution > *"Cut off one head, two more shall take its place."* > Except here — every head is doing your work faster and cheaper. ## ⛔ MANDATORY PROTOCOLS — NEVER SKIP These protocols are NON-NEGOTIABLE. Skipping them is a framework violation. ### Protocol 1: Sentinel Scan After Code Changes When ANY agent returns output containing `⚠️ HYDRA_SENTINEL_REQUIRED`, you MUST — before doing ANYTHING else, before presenting results to the user, before running any other agents — dispatch hydra-sentinel-scan with the files and changes listed in the trigger block. **This is blocking.** The user does NOT see the code changes until sentinel completes. If you present code changes to the user without running sentinel first, you have violated the framework's core safety guarantee.
- 📁 references/
- 📄 SKILL.md
- 📄 SYNC.md
This skill teaches AI coding agents how to use the ACCESSIBILITY.md framework,
Step-by-step guide to add a new discord.py Cog to the framework
- 📄 7Dkb.md
- 📄 ide-rules-format.md
- 📄 levels-overview.md
**SevenD — 7D Framework Full Lifecycle Skill**: Scaffolds, customizes, deploys, and operates the 7D development framework for any project. Covers initial setup (assess → customize → deploy), ongoing operations (sprint management, feature workflow, agent debugging), and level upgrades. Make sure to use this skill whenever the user mentions 7D, SevenD, project setup for AI agents, framework levels, sprint reviews, feature workflows, or wants help structuring any project for AI-assisted development. - MANDATORY TRIGGERS: 7D, SevenD, seven D, framework setup, project setup, scaffold project, project structure, set up my project, start a new project, project template, configure framework, upgrade level, GitHub setup, sprint setup, IDE rules setup, sprint review, new feature workflow, agent not following rules, framework feels heavy, framework feels light - Also trigger when: user wants to organize a project for AI-assisted development, wants to set up Cursor/Windsurf/Claude Code/Copilot rules, wants to migrate between framework levels, wants help running a sprint review, wants to add a feature through the full 7D workflow, wants to debug why an AI agent isn't following framework rules, or asks how to structure any project so AI agents can work effectively — even non-software projects --- # SevenD — 7D Framework Skill
This skill should be used when the user asks to "analyze this framework's API", "outside-in outline for X", "API-first learning plan", "create a learning outline for X", "trace the public API", "analyze the API surface", "api-blueprint", or any request to map a Java framework's API surface for outside-in reimplementation. Analyzes a Java framework's source code and produces an API-first learning outline (api-outline.md) that maps the public API surface, traces each capability inward through implementation layers, generates ASCII call-chain diagrams, and creates a buildable project skeleton. --- # API Blueprint — API-First Learning Outline ## Philosophy: Outside-In, API-First The fastest way to learn a framework and confidently contribute to it is to start where the **user** starts — the public API. Instead of hunting for the framework's internal "heart" and building outward (v1 approach), this skill: 1. **Identifies the API surface** — the classes, interfaces, and methods that framework users actually import and call in their application code 2. **Organizes features as vertical slices** — each feature represents one API capability, traced from the public method all the way down through internal layers 3. **Orders by usage tier** — most commonly used APIs first, power-user/advanced APIs last
- 📁 blog/
- 📁 eden/
- 📁 essential/
- 📄 metadata.json
- 📄 README.md
- 📄 README.zh-CN.md
Create backend with ElysiaJS, a type-safe, high-performance framework.
Use this skill whenever working with the Tidos Rust component framework.
Independent Critic review — quality governance for framework changes
