agentsclimarketplace

Context & AI engineering

25,841 rows, by stacks then stars

1,865 of these skill files have been read, by 1,328 distinct authors, and what they tell an agent counted. What Context & AI engineering authors agree on, and what they forbid

  • Passdown handoff

    vunm-io/passdown/plugins/passdown/skills/passdown-handoff Skill

    8★ repo

    Use when ending or pausing a work session — writes a session handoff log (the "passdown") so the next session or agent resumes cheaply from small files instead of replaying a large transcript

  • Agent ops codex agent creator

    jscraik/Agent-Skills/Infrastructure/references/deferred-skill-context/agent-ops-codex-agent-creator Skill

    8★ repo

    Create, install, validate, and orchestrate Codex custom subagents as standalone TOMLs with canonical global defaults (`~/dev/configs/codex/agents/{name}/{name}.toml`, `~/dev/configs/codex/config.toml`) plus optional project scope (`${project_root}/.codex/agents/{name}/{name}.toml`), where project config writes occur only when runtime-limit flags are explicitly requested.

  • Orchestra intake

    Momo2323-ui/claude-orchestra/skills/orchestra-intake Skill

    8★ repo

    Classify and file every newly installed skill, plugin, MCP, connector, or agent into the right orchestra — never archive. Use whenever the user installs/adds a new repo, skill, plugin, MCP server, or agent ("I installed X", "added Y", "npx skills add Z", "new repo", "set up this MCP", "just got this connector"). Runs the security scan, classifies the tool, places it in an orchestra with usage notes, logs the assignment, and reports back. This is the self-organizing layer of the orchestra system.

  • Prompt decorators

    smkalami/skills/skills/prompt-decorators Skill

    8★ repo

    Activates a structured decorator framework that modifies how Claude reasons, responds, and formats output. Trigger this skill whenever a prompt contains one or more markers prefixed with +++, such as +++Reasoning, +++StepByStep, +++Tone(style=formal), or any other +++ marker, regardless of what follows in the prompt. Also trigger when the user asks to activate, list, or clear decorators, references the prompt decorator framework, or uses phrases like "use decorator", "apply +++", or "what decorators are available". This skill must be active for any +++ marker to take effect.

  • Benchmark models

    timurgaleev/vibestack/skills/benchmark-models Skill

    8★ repo

    Cross-model benchmark for vibestack skills. Runs the same prompt through Claude, GPT (via Codex CLI), and Gemini side-by-side — compares latency, tokens, cost, and optionally quality via LLM judge. Answers "which model is actually best for this skill?" with data instead of vibes.

  • Agent fleet status

    koinod/koino-skills/agent-fleet-status Skill

    8★ repo

    Free AI agent skills for business automation. Sales, content, ops, growth. Compatible with Claude Code, Codex, Gemini CLI, Cursor.

    The same file is in 1 other repository

  • Scenario creator

    tough-tongue/toughtongue-skills/skills/scenario-creator Skill

    8★ repo

    Create Tough Tongue AI practice scenarios (cold call, sales roleplay, coaching) via the ttai MCP server. Classifies the scenario type, applies type-specific authoring rules, gathers context from URLs, transcripts, or other connected tools, validates against a checklist, and creates the scenario with ttai:create_scenario. Use when the user says "create a scenario", "build a practice scenario", "make a roleplay for...", "I have a call in 30 minutes, help me rehearse", or provides a brief, company info, or call transcripts for scenario creation.

  • Outlook calendar

    mintmcp/servers/com.mintmcp/outlook-calendar MCP server

    no license8★ repo

    A MCP server that works with Outlook Calendar to manage event listing, reading, and updates.

  • Bid Manager MCP Server

    cesteral/mcp-open-advertising/io.github.cesteral/dbm-mcp MCP server

    8★ repo

    Bid Manager reporting and query workflows for DV360 campaign performance analysis

  • Clawpay

    up2itnow0822/agentpay-mcp/io.github.up2itnow0822/clawpay MCP server

    8★ repo

    Non-custodial x402 payment MCP server for AI agents. Wallets, payments, and commerce on 17 chains.

  • Agent builder

    synaptiai/synapti-marketplace/plugins/ai-first-org-design-kit/skills/agent-builder Skill

    7★ repo

    Generate role-specific agent system prompts, tool permissions, and self-review checklists from organizational design artifacts — saved to $HOME/.ai-first-kit/ with optional framework-specific configuration for Claude Code, OpenAI Agents SDK, Anthropic Agent SDK, CrewAI, or custom frameworks. Reads the organizational genome, governance, gates, and role definitions to produce agent configurations that embody a specific role in the organization. Use when the user says 'create agent instructions', 'build an agent', 'agent system prompt', 'configure an agent', 'agent for this role', 'OpenAI agent', 'CrewAI agent', 'create agent config', 'deploy an agent', or 'what tools should this agent have'. Also use when the user has completed role-value-mapper and wants to actually deploy agents that follow the organizational genome, or when they ask 'how do I make an agent follow our rules' or 'how do I create an OpenClaw agent for our org' — even if they don't use the word 'builder'. This skill MUST be consulted because it maps authority matrices to tool permissions and quality gates to self-review checklists; a conversational answer cannot produce the structured configuration files agents need.

  • Agent team codex

    Dannykkh/skill-olympus/skills/agent-team-codex Skill

    7★ repo

    Codex CLI로 병렬 구현할 때 사용. multi_agent 기능으로 default/explorer/worker를 조합해 실행. zephermine 섹션 모드와 자유 모드 지원. /agent-team, /poseidon, /agent-team-codex로 실행.

  • Ai underwriting copilot

    sasha-deneux/claude-skills-cre/skills/ai-underwriting-copilot Skill

    7★ repo

    A CRE acquisitions pipeline scaffold. Drop in your buy box and it runs the pipeline shape start to finish (screen, red-flag, underwrite, score, route), in the tools you already use, ending at a human-approval gate. A generic starter that stops where a firm's real modeling logic begins.

  • Jiang agent transcript pass

    apresmoi/jianglens/.codex/skills/jiang-agent-transcript-pass Skill

    no license7★ repo

    Use this skill when an agent processes Jiang Lens transcript packets into semantic JSON outputs: interactions, speaker uncertainty, claims, glossary candidates, and chronology notes.

  • Agent token saver devin

    Supersynergy/agent-token-saver/skills/agent-token-saver-devin Skill

    7★ repo

    Devin token-saver profile — repo-instructions + shell-wrapper + KB retrieval instead of host hooks; subagents use bounded capsules.

  • Video agent editor

    chenyuxiaojin/video-agent-skills/video-agent-editor Skill

    7★ repo

    视频团队的剪辑师。将音频、视觉素材、字幕合并为完整时间轴, 通过 DaVinci Resolve Studio Python API 直接导入达芬奇项目。 同时处理美术师标记的"后期制作"镜头(文字动效、数据动效、分屏)。 当收到"生成时间轴""导入达芬奇""构建项目"时触发, 或由制片人(producer)调度时自动触发。

  • Agentic workflow

    nikhilw/structured-agentic-workflow/skills/agentic-workflow Skill

    7★ repo

    Set of skills and workflows to ensure humans and agents stay focused while vibe-coding.

  • Embedding service

    Lin-A1/skills-agent/services/embedding_service Skill

    no license7★ repo

    文本向量化(Embedding)基础服务。将自然语言转换为高维稠密向量,为语义搜索、聚类分析、推荐系统等下游任务提供核心数据支持。

  • Wiki

    liyading1818/obsidian-llm-wiki/.cursor/skills/wiki Skill

    no license7★ repo

    Operate on the user's personal Obsidian LLM-Wiki vault (repository root). Use when the user invokes /wiki, asks a question that should be answered using their knowledge base, asks to ingest a new source into the wiki, asks to lint or health-check the wiki, or asks to generate a document (analysis, comparison, summary, slide deck) from wiki content. The wiki follows Karpathy's LLM Wiki pattern documented in AGENTS.md at the repo root.

  • Boil the ocean

    seangeng/skills/boil-the-ocean Skill

    7★ repo

    Raise the effort and completeness bar on agent work so it ships the finished thing, not a plan to build it. Use this when the user wants an agent to "do the whole thing", "go all the way", "don't stop at good enough", "ship it complete", "stop handing me plans", or is frustrated that previous output was half-done, left dangling threads, shipped a workaround, or offered to "table it for later." Also load it when setting up a coding agent's standing instructions (system prompt, SOUL.md, CLAUDE.md, AGENTS.md) and you want a reusable "completeness" directive. It's a prompt to paste into the agent's persistent config, plus the judgment to know when to dial it back.

  • Agent state machine

    aka-kika/akakika-skills/skills/ai-agents/agent-state-machine Skill

    7★ repo

    Use when designing or implementing states for AI agent tasks, background jobs, local model runs, queues, and notifications — one shared set of states, only legal transitions, and a recovery path out of every failure.

  • Llm wiki crm

    anh-chu/llm-wiki-pm/skills/llm-wiki-crm Skill

    7★ repo

    PM relationship CRM layer on top of the wiki. Relationship health, auto-enrichment via web search, account health tracking, and people profile maintenance. Does not replace Salesforce — tracks PM-specific context (product feedback, feature asks, strategic relationship, communication history).

  • Chonkie

    feyninc/skills/skills/chonkie Skill

    7★ repo

    Use Chonkie for fast, lightweight text chunking in RAG pipelines. Covers all 11 chunker types (Token, Fast, Sentence, Recursive, Semantic, Late, Code, Neural, Slumber, Table, TeraflopAI), the Pipeline API for chaining fetch→process→chunk→refine→export→store workflows, embeddings refineries, vector DB handshakes (Chroma, Qdrant, Pinecone, etc.), tokenizer selection, recipe system, REST API server, and async/batch processing. Use when: splitting documents for embeddings, building ingestion pipelines, chunking code or markdown, setting up vector DB ingestion, or any text segmentation task for retrieval-augmented generation.

    The same file is in 1 other repository

  • Agent mail

    martin1847/evolab/skills/agent-mail Skill

    6★ repo

    多编排者/长期 agent 身份之间的异步信箱总线——发信、收信、回信、归档、名册注册。每个身份一个 inbox,一封信只有一个去处(收件人 inbox),收信只查自己信箱。触发:给另一个编排者/CTO/agent 写信或提议、查我的信箱、跨编排者协调、看有哪些注册身份。不用于人类电子邮件(gmail/给真人同事或客户写信)或普通消息转发。可选伴随 cto-orchestration 使用(多编排者场景)。Use when writing to / reading mail from another orchestrator agent, coordinating across orchestrators, or managing the agent roster; NOT for human email.

  • Agent smith

    vignesh2027/Claude-Agentic-Skills2.0-version/agent-smith Skill

    6★ repo

    Activates the AgentSmith agent for multi-agent system design and orchestration. Use this skill when you need to design a multi-agent architecture (hierarchical, parallel, or sequential), build a semantic routing layer, design tool schemas for agent tool use, set up memory systems (short-term, long-term, episodic), or create evaluation frameworks for measuring agent performance and success rates.

  • Red team eval authoring

    yeaight7/agent-powerups/plugins/agent-evaluation-lab/skills/red-team-eval-authoring Skill

    6★ repo

    Use when creating or reviewing red-team eval plugins, attack templates, grader rubrics, safety fixtures, or model-risk test metadata.

  • Serm guard

    mgicoda/icoda-skills/serm-guard Skill

    no license6★ repo

    Sentiment & Reputation Guard — comprehensive brand reputation audit through search engines and LLM perception analysis. Analyzes online reviews, forums, news, and social media to score brand reputation 0-100 across four dimensions: Search Sentiment, SERP Control, Platform Presence, and LLM Sentiment. Auto-detects industry niche (crypto, iGaming, SaaS, agency, ecommerce, fintech, etc.) and tailors the query matrix accordingly. Generates a visual inline HTML report with a prioritized recommendations roadmap (Quick Wins / Medium-term / Strategic). Use when user: - Wants a brand reputation audit, SERM analysis, ORM check, or reputation score - Asks "what do people say about [brand]", "check reputation of [brand]" - Asks about negative reviews, bad search results, brand sentiment, online complaints - Wants to know how AI systems (ChatGPT, Claude, Perplexity) perceive a brand - Asks about brand monitoring, trust score, complaint analysis, review analysis - Wants to compare two brands' online reputation side-by-side - Mentions: reviews check, scam check, brand health, sentiment analysis, reputation monitoring - Asks "is [brand] legit", "is [brand] a scam", "[brand] reviews" - Wants an AI visibility or AI perception check specifically for a brand's reputation - Russian: "аудит репутации", "SERM анализ", "ORM аудит", "что пишут о бренде", "проверить репутацию", "мониторинг репутации", "репутация в поиске", "как AI видит бренд", "отзывы о компании", "негативные отзывы", "репутация бренда", "что говорят о бренде", "проверка репутации", "аналитика отзывов" Trigger on any question about a brand or company's online reputation, search presence, review sentiment, or AI perception — even without the word "audit" or "SERM".

  • Zh

    mightyhuman101/seedance2-skill/zh Skill

    6★ repo

    为即梦 Seedance 2.0 多模态AI视频生成模型撰写高质量提示词。当用户需要使用文本、图片、视频、音频等多模态输入创作视频提示词时触发。涵盖@引用语法、运镜复刻、特效模仿、视频延长、视频编辑、音乐卡点、电商广告、短剧创作、科普教育等场景。

  • Agency client handoff

    PicsArt/gen-ai-skills/skills/agency-client-handoff Skill

    6★ repo

    Export a white-label client deliverable as a zip.

  • Ask claude

    BackToCimaCoppi/Praxis/skills/ask-claude Skill

    6★ repo

    Use when the user wants to consult Claude for a second opinion, audit, or direct execution. 触发词:"问一下克劳德"、"问一下claude"、"问一下sonnet"、"让克劳德去做"、"让claude直接XX"、"问一下opus"、"让opus去做"。This skill uses the Agent tool to spawn a Claude subagent from the main thread. All synthesis and decisions stay in the main thread.

  • Build voice agent

    PatterAI/skills/build-voice-agent Skill

    6★ repo

    Build a production voice agent with the Patter SDK — receive or place real phone calls answered by an AI agent. Use when the user wants to make a phone bot, IVR replacement, voice receptionist, outbound caller, survey bot, customer-support voice agent, voice-AI demo, AI cold-caller, or any flow where an LLM talks over the telephone. Covers the three Patter modes — OpenAI Realtime / Realtime2 (GA, lowest latency), ElevenLabs ConvAI (turn-taking), and the STT→LLM→TTS Pipeline (mix any providers) — in both Python and TypeScript. Trigger this skill even if the user only says "phone bot", "voice AI", "call my customers", or "answer the phone with AI" without naming Patter.

  • Agent team to be update

    valkryhx/google_adk_agent/skills/agent_team_to_be_update Skill

    no license6★ repo

    赋予 Agent 作为集群指挥官(Leader)的能力,通过去中心化任务队列将子任务派发给 Worker 节点并发执行。

  • Insight orchestrator

    LuckyOneTwoThree/pm-skill/pm-01-discovery/orchestrators/insight-orchestrator Skill

    no license6★ repo

    当需要执行完整的需求分析流程时使用。需求洞察指挥官,调度insight-analysis完成JTBD、需求分层、5Whys、KANO分类和优先级评分。关键词:需求分析流程、需求洞察编排、需求优先级全流程、JTBD、5Whys、KANO、优先级评分、分析需求、挖掘需求、用户需求、需求排序。本编排器为透传编排器,仅调度1个子Skill(insight-analysis),上层编排器也可直接调用insight-analysis。

  • Project memory

    RRFRRF/project-memory-skill/project-memory Skill

    no license6★ repo

    Initialize a lightweight project memory system. Creates CLAUDE.md, AGENTS.md, LOOP.md, BUGS.md and .mem/ files. After initialization, daily maintenance rules are embedded in AGENTS.md (active via system prompts) — no need to re-invoke this skill. Only use for initialization, memory status queries, compression or cleanup. Defaults to English.

  • Agent brainstorm

    northseadl/norix-skills/agent-brainstorm Skill

    no license6★ repo

    Multi-agent brainstorming: async opinion collision with expert personas. Mixed Codex/Claude Code engine. Use when multiple AI agents need to collaboratively discuss, debate, and converge on solutions through structured dialog. Triggers: brainstorm, multi-perspective discussion, opinion collision, expert debate, war room, collective intelligence, 头脑风暴, 多视角讨论, 集思广益.

  • Agent Development

    HK-hub/AgentSkills/Agent Development Skill

    6★ repo

    This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.

    The same file is in 2 other repositories

  • Ai feature eval harness

    Mozurok/fhorja.dev/.claude/skills/ai-feature-eval-harness Skill

    6★ repo

    Design an evaluation plan for a product AI feature (LLM- or model-backed output): measurable success criteria, a held-out labeled eval dataset shape, per-criterion grading (code-based first, then LLM-based for nuanced judgment), and a pass threshold, then persist as AI_EVAL_PLAN.md. Use when the task ships or changes a feature whose output is model-generated or non-deterministic (assistant reply, classification, extraction, summarization, ranking, agent action) and needs a repeatable dataset-backed eval rather than only example-based tests. Do not use when the feature has no model-backed output (use test-strategy for deterministic behavior), when judging Fhorja's own command outputs against a rubric (use verify-against-rubric), or when no active task folder exists. The code-graded tier composes with ADR-0048 (a passing deterministic gate is Layer-1 evidence); the LLM-graded tier is added signal, not a replacement.

  • Agent memory profiles

    sarveshsea/design-skills/skills/agent-memory-profiles Skill

    6★ repo

    Design durable user, project, persona, and task memory profiles for local agents.

  • Optimize claude opus 5 prompts

    IchenDEV/prompt-optimizer-plugins/plugins/claude-opus-5-prompt-optimizer/skills/optimize-claude-opus-5-prompts Skill

    6★ repo

    Clarify, audit, and rewrite rough or existing prompts for Claude Opus 5 using Anthropic's official prompting guidance. Use when a user asks to optimize, improve, migrate, debug, or design a prompt, system prompt, or agent harness for Claude Opus 5 (claude-opus-5), including requests phrased as Opus 5 prompt optimization, Opus 5 提示词优化, or migrating a Claude Opus 4.8 prompt. Also use when tuning observed Opus 5 behavior such as long responses, heavy progress narration, long written deliverables, scope expansion, eager subagent delegation, correction narration, over-verification, conservative code review, or thinking-disabled output artifacts. Ask only for missing information that would materially change the result; otherwise preserve intent and return a lean, copy-ready prompt.

  • Dispatching parallel agents

    pengzhangzhi/superpowers-ml/skills/dispatching-parallel-agents Skill

    6★ repo

    Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

    The same file is in 13 other repositories

  • Knowledge transfer

    ferdinandobons/knowledge-transfer/plugins/knowledge-transfer/skills/knowledge-transfer Skill

    6★ repo

    Use when a colleague is leaving a project and must hand over knowledge, or when someone new joins a project and receives handover.zip or a handover/ folder. Two phases: export (analyze project + agent project memories from Claude, Codex, or another assistant, then produce a transferable handover.zip archive containing a non-technical onboarding doc + filtered portable memories + a privacy-safe omissions manifest) and import (extract/read the handover package, dry-run the candidate memories, verify every claim against current code, then install accepted memories through the current agent's memory mechanism with per-memory receipts). Trigger on /knowledge-transfer, /knowledge-transfer:knowledge-transfer, $knowledge-transfer, 'handover', 'knowledge transfer', 'passaggio di consegne', 'onboard a new colleague', or when the user mentions taking over / leaving a project.

  • 6★ repo

    PreClick scans links for threats and confirms intent match with high accuracy before agents click.

  • ToolPipe MCP Server

    COSAI-Labs/make-money-30day-challenge/io.github.COSAI-Labs/toolpipe-mcp-server MCP server

    no license6★ repo

    238+ dev tools via MCP: JSON, QR, PDF, DNS, hash, UUID, code review, JWT, SSL, WHOIS, and more

  • Pangolinfo MCP for Agent

    pangolinfo/pangolinfo-mcp/io.github.Pangolin-spg/pangolinfo-mcp MCP server

    6★ repo

    Real-time Amazon, search and market intelligence tools for AI agents via remote MCP.

  • MCP Office Word

    dosev-ai/mcp-office/io.github.dosev-ai/mcp-office-word MCP server

    6★ repo

    50-tool Word MCP server. Document assembly, tracked changes, and export. Windows-first.

  • Textarttools mcp

    humanjesse/textarttools-mcp/io.github.humanjesse/textarttools-mcp MCP server

    dormant6★ repo

    Unicode text styling and ASCII art generation with 23 styles and 322+ figlet fonts

  • Swarm map reduce

    ben-alkov/the_swarm/src/skills/swarm-map-reduce Skill

    no license5★ repo

    Map-reduce orchestration. Parallel mappers process input chunks independently, then a dedicated reducer merges all outputs.

    The same file is in 2 other repositories

  • Trip planner

    aliasunder/agent-skills/skills/trip-planner Skill

    5★ repo

    Plan a real trip. Use for: hotel/flight/train/restaurant research for specific destinations and dates, creating travel documents (daily cards, itineraries, packing lists, offline guides), managing booking changes or cancellations, and resuming a trip project with CLAUDE.md/TASKS.md/memory/ files. Handles the full lifecycle — transport, accommodation, activities, restaurants, budget tracking, and printable traveler materials. ALWAYS use this skill in a trip planning project — detected by a CLAUDE.md with traveler profiles, an itinerary phase marker, or a memory/ directory with trip planning files. Also trigger on "plan a trip", "start a session", "research hotels", "find restaurants", "build the itinerary", "make daily cards", "create packing list", or any travel planning task. NOT for: presentations, file conversions, sending emails, building apps, or hypothetical travel questions.

  • Ai engineer

    AtulPurohit/Antigravity-Awesome-Skills/plugins/ai-llm-engineering/skills/ai-engineer Skill

    no license5★ repo

    Professional Ai Engineer skill. Integrate LLM API workflows, safe system prompt guidelines, and agentic workflows.

  • Core

    Ronkupper/PRISM/plugins/prism/skills/core Skill

    5★ repo

    PRISM — a structured, multi-session, multi-vendor LLM-orchestrated audit and research framework (orchestration on Claude, Opus-class). Trigger when the user invokes PRISM by name or by a recognizable PRISM construct: PRISM / PRISM audit / begin a PRISM audit; a Master file or any filename matching *_master_p*.md; Prompt Strategy; the Lens Library; Vendor Selection or Vendor Triangulation; Setup probes P1–P7; Monitors M1–M12; Standing Principles SP-*; the Execution Envelope / Self-check / Output triple contract; Dispatch register or Dispatch shape (equivalence / split / limitation-named); the "What's next" artifact; context bands 🟢🟡🟠🔴; migration handoff; the P0/P1 boundary; three-layer readiness; Update sessions or point refresh; or Setup artifacts (Decision brief / Stakeholder register / Claim inventory / Jurisdiction map). Also trigger when the user attaches a Master or Lens Library file. Do NOT trigger for generic audit, research, or prompt-engineering work that does not invoke PRISM by name or construct, nor for v1.x-only terms (Starter, GATE-0/1/2, Scope Flags, Runtime Profile) — v2 supersedes them.

  • Verify transact and rate an unknown agent

    Aidress-ai/aidress-skill-verify-transact-and-rate-an-unknown-agent/skills/verify-transact-and-rate-an-unknown-agent Skill

    5★ repo

    Discover, Verify, Transact, and Rate an Unknown AI Agent. Agent discovery, trust verification, and capability routing powered by Aidress — the coordination registry for autonomous AI agents. Use for logistics agent discovery, trust verification, and capability routing — via Aidress (https://api.aidress.ai).

  • Optimize agent instructions

    richfrem/agent-plugins-skills/plugins/agent-agentic-os/skills/optimize-agent-instructions Skill

    5★ repo

    Audits and rewrites AI agent instruction files (CLAUDE.md, GEMINI.md, .github/copilot-instructions.md) in any repo. Strips stale or foreign content, applies Karpathy's four behavioral principles, ensures platform-specific sections, and makes each file authoritative rather than a copy of another. Trigger when the user says "optimize my CLAUDE.md", "audit agent instructions", "improve my CLAUDE.md", "apply Karpathy principles to my agent files", "clean up my copilot instructions", "review my GEMINI.md", or "update my AI instruction files".

    The same file is in 1 other repository

  • Swarm design deep

    AnmarHani/SwarmVault/skills/swarm-design-deep Skill

    5★ repo

    The developer-driven design lane — the user commits to each approach before anything is written, then the design goes to pseudocode, algorithms, invariants, sequence diagrams and test vectors in their chosen design language. Use when the user wants to own the system rather than receive it: "developer mode", deep/detailed design, designing algorithms or data structures, writing pseudocode or sequence diagrams during design, or human-driven planning after the SRS.

  • Lynqu event blitz

    Gravisun/lynqu-ai-toolkit/skills/lynqu-event-blitz Skill

    no license5★ repo

    Run a complete event lead-capture workflow in Lynqu end-to-end — set up the event and campaign, capture booth/conference leads, tag and attribute them, then kick off follow-up. Use for conference, trade show, or booth lead capture, "set up our event in Lynqu", event ROI/attribution, or post-event processing. Requires the Lynqu MCP server connected (https://api.lynqu.com/mcp/v2).

  • Cross agent memory

    VladimirGutuev/cross-agent-memory/skills/cross-agent-memory Skill

    5★ repo

    Maintain broad, verified, client-neutral project memory across Claude Code, Codex, Kimi Code, Antigravity, and other coding-agent harnesses while preserving each client's native or auto-memory. Use when an agent must understand repository history, architecture, feature outcomes, decisions and rationale, reusable lessons, or memory drift; or when durable knowledge must be promoted, reconciled, consolidated, retired, or audited. Do not use for unfinished-work transfer; use cross-agent-handoff instead.

  • Soia meta prompt clarity

    soia-team/soia-open-skills/skills/soia-meta-prompt-clarity Skill

    5★ repo

    起草、诊断并规格化中英文提示词,保留用户意图、语言与安全边界。触发:「写提示词 / write a prompt」「优化 prompt / improve this prompt」「扩展成可验证规格」

  • Benchmark e2e

    build-with-dhiraj/ai-workflow-framework-portability-kit/Plugins/vercel-marketplace-source/.claude/skills/benchmark-e2e Skill

    5★ repo

    End-to-end benchmark suite for vercel-plugin. Runs realistic projects through skill injection, launches dev servers, verifies everything works, analyzes conversation logs, and produces an improvement report for overnight self-improvement loops.

  • Openplan auto

    BANANASJIM/openplan-skill/skills/openplan-auto Skill

    5★ repo

    Orchestrate OpenPlan-style skills in auto or YOLO mode while preserving human decision boundaries. Use when Codex, Claude Code, or another agent should automatically inspect, align enough to proceed, research, test, review, garden, summarize, hand off, or generate temporary HTML without silently approving, changing durable goal/intent, bypassing risk decisions, or pretending soft guidance is hard enforcement. This skill coordinates openplan-core, openplan-operate, openplan-align, openplan-research, openplan-test, openplan-review, openplan-garden, openplan-record, openplan-handoff, openplan-html-brief, and openplan-docs-init.

  • Promptkitty author agent instructions

    baldaworks/promptkitty/cli/assets/cursor/skills/promptkitty-author-agent-instructions Skill

    5★ repo

    Turn a fully assembled PromptKit prompt into ready-to-commit project instructions or a provider-native subagent profile. Use when the user asks to create persistent agent guidance, custom agent instructions, an agent profile, a subagent, or equivalent files for Codex, Claude Code, Grok Build, GitHub Copilot, OpenCode, or Cursor.

  • Ema

    CSKishan/ame-skill/skills/ema Skill

    5★ repo

    Use when the user invokes /ema, says "enclose my analysis", "generate a plan", "create an implementation plan", "plan this out", "build a plan from the spec", or wants to turn a completed /ame spec into a structured, chunked execution plan. Reads .ame/spec.md, analyses layer dependencies, generates .ame/plan.md, and offers to execute each chunk on confirmation. REQUIRES agent/agentic mode with file-write capability (VS Code Agent mode, Google Antigravity, or Claude Code). Run /ame first.