Methodology

claude-api

Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.

02 WILD 5.0/5 C 5.0· A 0.0

prompt-engineering

Universal prompt engineering techniques for any LLM.

03 REPO TOOL 4.2/5 Adoption only

github-swyxio-ai-notes

notes for software engineers getting up to speed on new AI developments.

04 CURATED 4.4/5 C 4.4· A 0.0

hatch-pet

Create, repair, validate, preview, and package Codex-compatible animated pet spritesheets from character art, screenshots, generated images, or visual references.

05 CURATED 4.1/5 C 4.1· A 0.0

mcp-builder

Builds production MCP servers via 4-phase methodology: research, implement, test, evaluate. Triggers: build MCP, new MCP, MCP integration, MCP server scaffold.

06 WILD 4.7/5 C 4.7· A 0.0

prompt-optimizer

Analyze raw prompts, identify intent and gaps, match ECC components (skills/commands/agents/hooks), and output a ready-to-paste optimized prompt.

07 WILD 4.9/5 C 4.9· A 0.0

yes

Use when any task involves modifying files, configs, databases, or deployments.

08 CURATED 4.4/5 C 4.4· A 0.0

skill-review

Quality review and audit for Claude Code skills.

09 CURATED 4.4/5 C 4.4· A 0.0

one-three-one-rule

Structured decision-making framework for technical proposals and trade-off analysis.

10 CURATED 4.4/5 C 4.4· A 0.0

executing-nist-rmf-authorization-to-operate

Drive a federal system through the NIST Risk Management Framework (SP 800-37 Rev 2) to an Authorization to Operate (ATO): Prepare, Categorize (FIPS 199), Select a control baseline (FIPS 200 / SP…

11 CURATED 4.4/5 C 4.4· A 0.0

mcp-sentinel

Security monitoring agent for Claude Skills and MCP servers.

12 CURATED 4.4/5 C 4.4· A 0.0

skills-qa

Evaluate a skill against the Legal Skill Design Framework — thirteen design parameters (including trust-surface, freshness, schema validation, and conflict detection), three legal failure modes, and…

13 CURATED 4.4/5 C 4.4· A 0.0

mcp-client

Universal MCP client for connecting to any MCP server with progressive disclosure.

14 OFFICIAL 3.7/5 C 4.6· A 3.1

security-best-practices

Perform language and framework specific security best-practice reviews and suggest improvements.

15 WILD 4.8/5 C 4.8· A 0.0

pangle-ad-integration

Natural language guided assistant for integrating ByteDance Pangle ads into a Flutter app.

16 WILD 4.8/5 C 4.8· A 0.0

vendor-evaluation

Create a structured vendor evaluation framework for any procurement decision.

17 WILD 4.8/5 C 4.8· A 0.0

tech-radar

Build a technology radar for an engineering team, categorizing technologies into Adopt/Trial/Assess/Hold quadrants following the ThoughtWorks Tech Radar format.

18 WILD 4.8/5 C 4.8· A 0.0

social-media-strategy

Build a social media strategy for a brand, product, or creator.

19 WILD 4.8/5 C 4.8· A 0.0

social-ad-campaign

Plan and write a paid social advertising campaign.

20 WILD 4.8/5 C 4.8· A 0.0

grant-proposal

Write a structured grant proposal or funding application for any grant type.

21 WILD 4.8/5 C 4.8· A 0.0

compliance-checklist

Generate a prioritised compliance checklist for GDPR, SOC 2, ISO 27001, FCA, HIPAA, or other frameworks with a gap analysis.

22 WILD 4.8/5 C 4.8· A 0.0

claude-superpowers

Activate a 4-stage coding discipline framework that forces Claude to plan before coding, isolate changes on a branch, write tests first, and self-review output twice before presenting it.

23 WILD 4.8/5 C 4.8· A 0.0

agr

AGR: Artificial General Research — autonomous iterative optimization framework for Claude Code.

24 CURATED 4.3/5 C 4.3· A 0.0

hook-development

This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDEPLUGINROOT}", "set up…

25 CURATED 4.3/5 C 4.3· A 0.0

mcp-docs

Fetch live MCP specification and docs from modelcontextprotocol.io. Training data may be outdated — default to using this skill when the query touches MCP protocol in any way. Trigger for:…

26 CURATED 4.3/5 C 4.3· A 0.0

mcp-audit

Audit MCP servers for protocol compliance, metadata drift, and compatibility regressions.

27 WILD 4.2/5 C 4.2· A 0.0

prototype

Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.

28 CURATED 4.3/5 C 4.3· A 0.0

context7-mcp

Fetches current, version-specific library documentation and code examples through the Context7 MCP server.

29 CURATED 4.3/5 C 4.3· A 0.0

video-shortform

Short-form video generation skill — 3-10 second clips for product reveals, motion teasers, ambient loops.

30 CURATED 4.3/5 C 4.3· A 0.0

skill-security-auditor

Security audit and vulnerability scanner for AI agent skills before installation.

31 CURATED 4.2/5 C 4.2· A 0.0

recsys-pipeline-architect

Design composable recommendation, ranking, and feed pipelines using the six-stage Source→Hydrator→Filter→Scorer→Selector→SideEffect framework popularized by xAI's open-sourced For You algorithm.

32 OFFICIAL 3.6/5 C 4.6· A 3.0

speech

Use when the user asks for text-to-speech narration or voiceover, accessibility reads, audio prompts, or batch speech generation via the OpenAI Audio API; run the bundled CLI…

needs key

33 WILD 4.4/5 C 4.4· A 0.0

council-multi-model

Add one optional external Codex critique after the existing council has produced a decision draft.

34 WILD 4.3/5 C 4.3· A 0.0

golang-testing

Go testing patterns including table-driven tests, subtests, benchmarks, fuzzing, and test coverage.

35 CURATED 4.2/5 C 4.2· A 0.0

skill-developer

Create and manage Claude Code skills following Anthropic best practices.

36 CURATED 4.1/5 C 4.1· A 0.0

interview-me

Extracts what the user actually wants instead of what they think they should want.

37 WILD 4.6/5 C 4.6· A 0.0

thumbnail-creator

Generate article or newsletter thumbnail candidates using the Gemini API from inside Claude Code.

38 WILD 4.5/5 C 4.5· A 0.0

ai-product-canvas

Structure AI and ML product decisions with the rigour of any product decision.

39 WILD 4.2/5 C 4.2· A 0.0

rust-testing

Rust testing patterns including unit tests, integration tests, async testing, property-based testing, mocking, and coverage.

40 CURATED 4.1/5 C 4.1· A 0.0

skill-prompt-convert

在 Skill（SKILL.md）与 Prompt（聊天框指令）两种格式之间相互转换。支持 Skill→Prompt 与 Prompt→Skill 双向转换，保持核心信息零丢失。当用户提到 Skill 转 Prompt、Prompt 转 Skill、格式互转、SKILL.md 转换时使用。

41 CURATED 4.1/5 C 4.1· A 0.0

mcp-scaffold

Scaffold production-ready Python MCP servers using FastMCP.

42 CURATED 4.1/5 C 4.1· A 0.0

mcp

Build or consume Model Context Protocol (MCP) servers and clients in .NET using the official MCP C# SDK, including stdio, Streamable HTTP, tools, prompts, resources, and capability negotiation. USE…

43 CURATED 4.0/5 C 4.0· A 0.0

competitive-report-structure

Use after benchmark-methodology has produced scored competitor profile cards.

44 CURATED 4.0/5 C 4.0· A 0.0

mcp-app-scaffolding

Scaffolds MCP App project structure with correct directory layout, dependencies, entry points, and framework-specific templates.

45 CURATED 4.0/5 C 4.0· A 0.0

idea-refine

Refines raw ideas into sharp, actionable concepts through structured divergent and convergent thinking.

46 WILD 4.5/5 C 4.5· A 0.0

pm

When you want to manage projects across your businesses using a kanban + Eisenhower methodology.

47 WILD 4.5/5 C 4.5· A 0.0

lumi-diary

Your local-first memory guardian and cyber bestie.

48 WILD 4.2/5 C 4.2· A 0.0

eval-harness

Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles. Use when a Claude Code workflow needs a formal eval before it is trusted or changed.

49 WILD 4.4/5 C 4.4· A 0.0

financial-due-diligence

Generate a financial due diligence checklist and analysis framework for any investment, acquisition, or partnership.

50 WILD 4.4/5 C 4.4· A 0.0

ux-research-plan

Create a structured UX research plan for any product question or feature.

51 WILD 4.4/5 C 4.4· A 0.0

prisma-patterns

Prisma ORM patterns for TypeScript backends — schema design, query optimization, transactions, pagination, and critical traps like updateMany returning count not records, $transaction timeouts,…

52 WILD 4.4/5 C 4.4· A 0.0

morning-intelligence

Interviews you across 15 questions to capture your role, topics, sources, exclusions, and format preferences, then writes a master prompt you can paste into a scheduled task or Claude Code Routine.

53 WILD 4.1/5 C 4.1· A 0.0

llm-trading-agent-security

Security patterns for autonomous trading agents with wallet or transaction authority.

54 WILD 4.3/5 C 4.3· A 0.0

serving-llms-vllm

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching.

55 WILD 4.3/5 C 4.3· A 0.0

research-protocol

Write a structured research protocol or study design document.

56 WILD 4.3/5 C 4.3· A 0.0

santa-method

Multi-agent adversarial verification with convergence loop.

57 WILD 4.3/5 C 4.3· A 0.0

custom-icons-skill

Professional workflow for creating bespoke vector and complex raster icons.

58 WILD 4.2/5 C 4.2· A 0.0

pixi-vn-ui

Use when building game UI (menus, HUD, dialogue box, settings/save screens) on top of Pixi'VN with an external JS framework (React, Vue) or with plain PixiJS components — mounting HTML or PixiJS UI…

59 WILD 4.2/5 C 4.2· A 0.0

nx

Build and manage monorepos with Nx. Use when a user asks to set up a monorepo, manage multiple packages/apps, cache builds, run affected tests, or migrate from Lerna.

60 WILD 4.1/5 C 4.1· A 0.0

ph

Fill a placeholder — infer the best content from surrounding context.

61 WILD 4.1/5 C 4.1· A 0.0

p9

P9 Tech Lead mode — write Task Prompts, manage P8 agent teams, never write code yourself.

62 WILD 4.1/5 C 4.1· A 0.0

web3-audit-plugin-core-skill

Root skill definition for the Web3 Audit Plugin providing AI-powered smart contract security auditing across EVM, Solana, Move, Cairo, CosmWasm, and TON platforms.

63 CURATED 3.4/5 C 4.3· A 2.8