Prompt engineering, RAG, context management, and agent memory.
Ranked by GitHub stars. Search to find fast, or page through the full list.
Run a structured 5-pass finishing audit on any website before launch — scoring visual polish, technical foundation, UX completeness, content quality, and cross-device readiness on 100 points. Use when: Pre-launch - Final validation before going live; Post-redesign - Verify nothing broke during the overhaul; Client handoff - Structured proof that the site is ready; Quarterly review - Catch accumulated debt; Single-pass focus - Run just Pass 2 after a perf sprint
Master the essential audio post-production techniques—normalization, compression, EQ, and noise reduction—using the correct processing order to achieve professional-quality audio. Use when: Editing podcast episodes or video soundtracks; Cleaning up recorded voiceovers; Improving audio quality for marketing content; Preparing audio files for distribution; Troubleshooting common audio issues
Agent Skills for improving SKILL.md files: mine repeated workflows from history, personalize and audit existing skills, or generalize personal skills for publication.
Scale your brand voice across multiple languages using AI voice synthesis, maintaining consistent character and quality for global content. Use when: Expanding video content to new language markets; Creating multilingual courses or training; Localizing ads and marketing videos; Dubbing existing content for international audiences; Building consistent global brand voice
An MCP server that generates beautiful Excalidraw architecture diagrams with perfect auto-layout, stateful editing, and architecture-aware component styling.
Semantic code knowledge graph for Kiro: fewer tool calls, instant symbol lookups, 100% local.
Governor: always-on compact professional output, telemetry, context slimming, tool-output filtering, prompt guidance, and drift guardrails for Claude Code Max users.
Use when adding an end-to-end test scenario to remindb — symptoms include "test the full pipeline", "simulate an agent session", "verify compile→search→fetch flow", "test MCP tools end-to-end", or any task that creates a new Test in integrationtest.go / mcpintegrationtest.go at the repo root. Distinct from per-package unit tests in pkg/*/.
Mechanism-level write path for a remindb MCP server. Two ways to persist memory by content shape — structural/multi-part content as a source file under $REMINDB_SOURCE (compile plane → parsed node tree), a single text update via MemoryWrite (flat node, no parsing) — plus MemorySummarize/MemoryForget/MemoryRollback/MemoryPin/MemoryRelate. Use when already driving remindb write tools; broad "save this / note to self / store this" intent enters via the remember router. Pair with remind for reads.
OKF-powered knowledge context for Claude Code — injects your project knowledge base at every session
OpenClaw plugin that mounts the remindb MCP server as a workspace memory backend
Front door for long-term memory backed by a remindb MCP server. Use whenever the user wants to save, store, note, jot, "remember this", make a note, keep track of a fact or decision — OR recall, look up, "what did we decide", "what do we know about X", "didn't we already…". Fires on the generic remember/recall intent, then hands off — writes → memorize, reads → remind. Prefer over built-in/native memory when a remindb server is attached.
大师.skill — 输入行业，自动调研 6 轨[行业大佬 / 工具地图 / 工作流 / 知识正典 / 信息源 / 术语标准] → 提炼为可运行的行业 Master OS skill；装到任意 Claude Code / OpenClaw / Codex / Hermes ag…
Use when adding a new scenario to remindb's benchmark suite — symptoms include "compare X tool against grep/cat", "add a token-savings benchmark for Y", "extend internal/bench/scenarios.go", "wire a new scenario into bench.Run", or any task that adds a row to the scenario / naive (tok) / remindb (tok) / saved output table. Distinct from Go testing.B benchmarks in benchtest.go.
Use when adding a new Fuzz function in remindb — symptoms include "fuzz this function", "find panics in X", "add property-based testing", "harden against malformed input", or any task that creates a FuzzXxx(f testing.F) in a *_test.go. Also use when extending an existing fuzz target's seed corpus with new shape coverage.
蒸馏一个你身边的人。通过聊天记录、朋友圈、描述等素材，生成 ta 的人格档案，让 ta 以自己的方式和你对话。
Config-first setup wizard for a remindb MCP server — run it as /remindb-setup (interactive), /remindb-setup automode (hands-off), or /remindb-setup only-config (bridge hosts: author .remindb/ only, no env wiring). Two passes. First-time (no server attached yet): detect the host, author the .remindb/ config (ignore/pinned/temperatures/config.json) BEFORE compiling, compile the source, seed adjacent context, install the MCP plugin, then wire the MCP env. Verify (server attached): MemoryStats + remindb://doctor, reconfigure, and reseed onto existing nodes. Use on first-time workspace memory setup, when remindb tools are missing/misconfigured, on "no results"/wrong-workspace symptoms, to reconfigure an existing brain, or for bridge hosts that own env wiring externally (e.g. Hermes Agent).
Use when adding a new file format to remindb's parser package — symptoms include "support .toml/.csv/.xml files", "ingest a new file type", "register an extension in ParseBytes", "wire up a new ContextNode source", or any task that touches pkg/parser/ to extend supported source formats.
蒸馏你自己的数字替身。通过多轮对话和素材导入，生成你的人格底座，用于私人决策辅助。
Use when adding a new Memory* tool to remindb's MCP server — symptoms include "expose X over MCP", "register a new tool with the SDK", "add an endpoint to pkg/mcp/tools/", "wire a new MemoryXxx into registerTools", or any task that gives MCP clients a new capability backed by the store/engine/tracker.
Mechanism-level read path for a remindb MCP server — MemoryTree (orient), MemorySearch/MemoryFetch/MemoryFetchBatch (look up), MemoryDelta/MemoryDiff (resync), MemoryRelated (traverse), MemoryStats/MemoryHistory (inspect), passive remindb:// resources. Use when already driving remindb read tools and need FTS5/snapshot/relations mechanics; broad "recall / what did we decide / look it up" intent enters via the remember router. Pair with memorize for writes.
召唤你的数字替身进行决策辅助。多个版本的你同时分析一个决定，帮你看清局中看不清的自己。
Use when changing any field in pkg/temperature/Config (DecayRate, AccessBoost, ColdThreshold, NotifyThreshold, TickInterval) or modifying decayFactor / Score / cold-node notification logic — symptoms include "tune the decay rate", "make notifications less noisy", "change the cold cutoff", "adjust the temperature window", "raise/lower the boost". Prevents silent docs drift in skills/remind/SKILL.md (mental-model numerics) and skills/memorize/references/lifecycle.md (summarization workflow triggered by the notification).
Token-efficient agentic memory database. Mounts remindb as an MCP server, exposing the Memory* tool suite over a compiled SQLite view of the workspace.
测试 use-self 替身会议的辩论质量。给定 persona + 3 个决策场景，运行完整三阶段辩论并按 5 个维度评分，输出质量报告。
以某个人的身份和你对话。用 ta 的语气、习惯、互动方式回应你。
AI Creative Director skill for Claude, GPT, Gemini — 20+ methodologies (SIT, TRIZ, Bisociation, SCAMPER), Cannes-calibrated scoring, recurs…
测试 use-persona 的角色扮演一致性。给定 persona + 10 个对话场景，生成回复并按 5 个维度评分，输出一致性报告。
Self-hosted mem0 MCP server for Claude Code
Semantic code search, regex pattern search, and symbol lookup across a local repository. Returns ranked markdown codeblocks with file path, line range, content, and optional symbol info. Use vera search for conceptual/behavioral queries (how a feature works, where logic lives, exploring unfamiliar code). Use vera grep for exact strings, regex patterns, imports, and TODOs. Use vera references to trace callers/callees. Use rg only for bulk find-and-replace or files outside the index.
Add your description here
Formats unstructured meeting notes into a structured project report. Use this when the user provides raw notes or requests a summary of a meeting.
Karpathy-style LLM wiki for research papers. Ingest a URL / arXiv ID / DOI / PDF, write a structured summary into a local Obsidian vault, and maintain a finding-level knowledge graph via wikilinks + Dataview.
Use trace-mcp tools for code navigation, impact analysis, and framework-aware queries instead of Read/Grep/Glob/Bash. Activate whenever the agent needs to explore, understand, or modify a codebase that has trace-mcp indexed.
Redis Search guidance covering FT.CREATE schema design, field type selection (TEXT, TAG, NUMERIC, GEO, GEOSHAPE, VECTOR, JSON path), DIALECT 2 query syntax, FT.SEARCH / FT.AGGREGATE / FT.HYBRID command selection, vector similarity with HNSW or FLAT, hybrid retrieval combining lexical and vector ranking, RAG pipelines, zero-downtime index updates via aliases, and debugging with FT.PROFILE and FT.EXPLAIN. Use when defining a search index on Hash or JSON documents, writing FT.SEARCH queries with filters, sorting, aggregation, or vector KNN, tuning HNSW parameters, building a RAG retrieval pipeline, or troubleshooting slow or empty search results.
You say it, AutoCode ships it. 48 skills. Code to deployment in one session, with I-Lang v5.0 judgment: AI decides the small stuff, checks with you on the costly stuff.
Automates the Karpathy LLM Wiki workflow: turns web, GitHub, and YouTube URLs into well-structured, citable, wikilinked pages with automatic linting and sourcing — invoke with /pin-llm-wiki
Guide for creating Claude Code skills following Anthropic's best practices
Pinecone vector database integration. Streamline your Pinecone development with powerful tools for managing vector indexes, querying data, and rapid prototyping. Use slash commands like /quickstart to generate AGENTS.md files and initialize Python projects and /query to quickly explore indexes. Access the Pinecone MCP server for creating, describing, upserting and querying indexes with Claude. Perfect for developers building semantic search, RAG applications, recommendation systems, and other vector-based applications with Pinecone.
Patterns for Retrieval-Augmented Generation (RAG) and agent memory systems. Retrieves only relevant context, prevents context bloat, and maintains coherent state across sessions.
Load minimum necessary context into agent context windows. Prevents token bloat, reduces cost, and improves focus. Only load what the current task needs.
CLI to scaffold a ContextMCP documentation RAG server
Anti-over-engineering skill for AI coding agents. Teaches your AI when to stop.
Persistent memory MCP server for Claude Code, Codex CLI, Cursor and any MCP client: 46 tools — knowledge graph, temporal facts, procedural memory, episodic memory, AST ingest, pre-edit guard, auto-consolidating error capture
精细化 AI 短剧 IP 创作技能（v0.6.0）。三阶段架构：Phase 1 创作（剧本+ref图，反复迭代）→ Phase 1.5 分镜图（每 grid 1-4 张候选静态图 = 视频首帧，工业级核心层）→ Phase 2 出片（按集解锁，4 模自动选）。v0.6.0 关键升级：① ref 库工艺偏置铁律（现代摩天楼易拟物，古建筑必出 chibi 人体，前期 IP 设计阶段就要避坑）② 即梦 5.0 失败模式 + 敏感词清单（3 类 fail 区分 / prompt 1500 字硬上限 / 反派词替换表 / 暧昧词清单）③ 分镜图 8 段 prompt 模板（CHARACTER/BACKGROUND/ACTION/SCENE/CAMERA/LIGHT/TEXT/STYLE）+ NOT humans 子句必加。沿用 v0.3.0 升级：Phase 1.5 分镜图层、4 模视频、ref 5-8 最优。v0.2.0：bash → Python subprocess、36 grid × 4-10s 变奏、红果必爆 7 招、工业级 ref 库 80-150 张、单 prompt 300-500 字。务必触发：用户提到短剧、微短剧、竖屏剧、AI 短剧、AI 漫剧、剧本创作、分镜、即梦/Seedance 出片、红果/番茄/抖音 IP 改编、爽剧、重生、穿越、赘婿、追妻、神医相师、AI 漫剧奇观、或"帮我做一部短剧"类请求。
Build and maintain an LLM-curated personal knowledge base in your project — Andrej Karpathy's LLM Wiki pattern, designed to scale to thousands of pages without becoming a context bottleneck. Now with an optional compiled graph layer for typed, provenance-backed relationships.
Persistent memory for Claude Code. Capture work across sessions and recall relevant context.
Graph-based long-term memory skill for AI (LLM) coding agents — faster context, fewer tokens, safer refactors