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

  • Simple mcp server

    ormastes/simple/io.github.ormastes/simple-mcp-server MCP server

    no license2★ repo

    Simple Language MCP server — code intelligence, debugging, build, test, and VCS tools

  • Tencent Lexiang MCP Server

    tencent-lexiang/lexiang-mcp-server/io.github.tencent-lexiang/lexiang-mcp-server MCP server

    2★ repo

    Tencent Lexiang AI knowledge base MCP server for searching, managing entries, and editing docs.

  • Chain

    vdappdev2/verusidx-mcp/io.github.vdappdev2/chain MCP server

    2★ repo

    Foundation MCP server — chain discovery, daemon management, health checks, raw transactions

  • Agent browser wsl2 setup

    ArthurZakirov/AgentDesk/skills/agent-browser-wsl2-setup Skill

    1★ repo

    Install and configure `agent-browser` on a Windows machine with WSL2 after a browser path is already working. Use when a user wants the `agent-browser` CLI, its downloaded runtime, the `vercel-labs/agent-browser` repository, or an `agent-browser` attachment to a Windows host browser bridge from WSL2.

  • Handoff

    ronniepinnell/casper/collection/communication/handoff Skill

    1★ repo

    Context-rot prevention: write a structured handoff document capturing the current session state so you can /clear and continue in a fresh session without losing context. Use when: context >70%, session >15 turns, hitting limits, or switching tasks mid-work. Invoke: /handoff [optional-filename]

  • Context handoff

    aimasteracc/harness-kit/skills/context-handoff Skill

    no license1★ repo

    Produce a structured handoff document that lets work survive a context reset, compaction, or a fresh session without losing the thread. Use when the user says "context handoff", "save context before compaction", "hand this off", or when an agent is approaching its context limit mid-task.

  • Skill zero

    anshmajumdar121/skill-x/skills/skill-zero Skill

    1★ repo

    Use this skill when the task involves coding-agent interpretability, hidden states, residual streams, linear probes, latent programming horizons, edit-outcome prediction, or monitor-and-steer workflows for coding agents. Applies the linear-probe procedure (Silva, Tu, Monperrus 2026) with expected AUC numbers, horizon k≈25, mid-layer inverted-U, and cross-benchmark transfer. Trigger when the user says "skill zero", "interpret the coding agent", "probe the agent's hidden states", or asks to predict/monitor a coding agent's edit outcomes. Do NOT trigger for general non-trivial tasks without an interpretability angle — use `think-like-gpt-5-6` or `super-skill` for those instead. This skill also contains a legacy General-mode rigor framework in its body for backward compatibility; new callers should prefer `think-like-gpt-5-6` for that use case.

  • Claude code dissect

    kohoj/skills/claude-code-dissect Skill

    1★ repo

    Navigate and extract reusable design patterns from the Claude Code 2.1.88 source code for application in our project. It covers nine subsystems: startup/bootstrap, conversation engine, context compaction, tool system, permissions, hooks, multi-agent orchestration, memory, and extensions (MCP/plugins/skills/UI). Use this skill whenever a user wants to study, reference, or adapt architectural patterns from Claude Code. Also use it when the user asks questions such as "how does Claude Code do this?", "learn from Claude Code", "dissect Claude Code", "reference Claude Code source", or requests implementation details for any Claude Code feature. This skill is the primary entry point: it routes to the appropriate reference file by topic, then reads the source code and returns extractable patterns. Even when the question appears simple (for example, "how does Claude Code implement X?"), use this skill because the reference files provide precise file paths, reading order, and architectural context that substantially improve answer quality.

  • Rem execute

    darbin/claudecraft/plugins/rem-dev-core/skills/rem-execute Skill

    1★ repo

    Execute an approved implementation plan with maximum discipline - git worktree isolation, TDD per task (RED to GREEN), complexity-scaled review, Codex delegation for mechanical work, one commit per task, and risk-scaled human checkpoints. Distinct from rem-plan (which WRITES the plan), rem-review-plan (which VALIDATES the plan before execution), rem-verify (which runs build/test without executing tasks), and rem-branch (which finishes the branch after execution). Use for "execute", "execute the plan", "run the plan", "implement the plan", "build it", or after /rem-review-plan sets Status to Approved.

  • Agent team

    donatassimkus/claude-ai-skills/skills/agent-team Skill

    1★ repo

    Auto-spawn a coordinated team of Claude Code teammates (each with own context, can DM each other, share a task list) when the user describes work that spans multiple domains and would benefit from specialists working in parallel with feedback loops. Triggers on phrases like "create a website for X", "build me an app for Y", "spin up a landing page for Z", "make me a site about W", "I need this built end-to-end", "review this from multiple angles", "debug this with competing hypotheses", or any request that implies multi-specialist parallel work with a quality loop. Auto-classifies the request, picks team composition + model-per-role + file ownership + hand-off graph, then spawns. Skip for single-domain tasks (use matching specialist skill), sequential pipelines (use subagents), or simple one-shot work. Requires the host's multi-agent team feature to be enabled; on Claude Code that means setting CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 in settings.json.

  • Installation

    scagogogo/versions-skills/skills/installation Skill

    1★ repo

    One-time setup for versions-skills plugin, SDK, CLI, and MCP server. Run first before using any version-* skill.

  • Audit orchestrator

    claude-hangar/claude-hangar/core/skills/audit-orchestrator Skill

    1★ repo

    Universal Pre-Scan → Analysis → Optimization → Report orchestrator for ANY project type — web apps (Astro/SvelteKit/Next), infrastructure/homelab repos, CLI tools, libraries, backend services, monorepos, data/ML projects, docs. Self-detects project type and runs the matching analysis track. Session state lives in `.audit-session/<date>-<slug>/` with INDEX.md + STATUS.md so any instance (or a different LLM) can resume after a crash. Delegates to /audit + /project-audit + /astro-audit + /sveltekit-audit + /db-audit + /auth-audit for web projects. Use when: "full audit", "audit everything", "complete audit", "infra audit", "homelab audit", "repo audit", "orchestrate audit", "pre-scan analysis optimization report".

  • Skill creator

    limerickgds/dashi-skills/.agents/skills/skill-creator Skill

    1★ repo

    Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

    The same file is in 66 other repositories

  • Curator fixes

    odere-pro/claude-wiki-pages-plugin/skills/curator-fixes Skill

    1★ repo

    The curator's supplemental diagnostic checks, the nine safe auto-fixes, the automatic judgment-fix procedure, and the lint-report template for claude-wiki-pages. Documents what the curator checks and how it repairs wiki structure under a git checkpoint, so the curator agent can apply fixes without inlining the catalog. Trigger when an agent or user asks "what does the curator check/fix", "how are wiki lint issues repaired", or invokes /claude-wiki-pages:curator-fixes. Reference, not action.

  • Business growth skills

    timdevai/proteus/skills/community/from-alireza/business-growth/skills/business-growth-skills Skill

    1★ repo

    4 business growth agent skills and plugins for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw. Customer success (health scoring, churn), sales engineer (RFP), revenue operations (pipeline, GTM), contract & proposal writer. Python tools (stdlib-only).

    The same file is in 1 other repository

  • Creating skills

    pgoell/pgoell-claude-tools/plugins/agent-system-management/skills/creating-skills Skill

    1★ repo

    Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

  • Oatda compare models

    devcsde/oatda-skills/skills/oatda-compare-models Skill

    1★ repo

    Use when the user wants to compare outputs from multiple LLM models side-by-side in a single request. Sends one prompt to multiple providers (OpenAI, Anthropic, Google, DeepSeek, etc.) in parallel via OATDA's /api/v1/compare endpoint and returns each model's response. Triggers on "compare models", "which model is best", "side-by-side LLM", "benchmark models", "gpt-5 vs claude", "evaluate multiple models".

  • Enhance for

    SivaJyothiPamarthy/prompt-enhancer-pack/skills/enhance-for Skill

    1★ repo

    Enhance a prompt optimized for a specific AI platform (ChatGPT, Gemini, Cursor, Copilot, Claude). Each platform responds differently to prompt structures. Use when user types /enhance-for followed by platform name and their prompt. Useful for copying optimized prompts to other AIs.

  • Pickup

    cabaynes/charles-claude-skills/skills/session-continuity/pickup Skill

    1★ repo

    Use when the user says "pickup", asks "where were we" after opening a fresh window, or wants to resume/pick up their work from a prior session that ended with /putdown — loads the most recent putdown file (the handoff note) for the current project and primes the agent with full context before continuing. Do NOT use for reopening a previous Claude conversation (that is the built-in /resume picker) or for resuming media, downloads, paused processes, or VMs.

  • Session handoff

    Amit-Tabibi/claude-code-skills/plugins/session-skills/skills/session-handoff Skill

    1★ repo

    Use when the user wants a CHAT-ONLY end-of-session summary so a fresh agent can continue seamlessly after /clear - phrases like "session handoff", "hand off", "handoff summary", "brief the next agent", "summarize so the next instance can pick up", "I'm about to clear, write a handoff". Produces a structured handoff (decisions, shipped changes, key files, running state with background shell IDs, verification steps, deferrals, open questions) printed in chat - it never writes files or updates memory. This is the EPHEMERAL path - output stays in the conversation. Do NOT use it when the user wants the work PERSISTED INTO PROJECT FILES on disk so nothing is lost; this skill writes nothing.

  • Ebay draft

    hansohn/marketplace-skills/skills/ebay-draft Skill

    1★ repo

    Create an eBay listing draft (inventory item + offer) via the eBay MCP server, leaving publication to the user. Use whenever the user wants to push a prepared listing to eBay without copy-pasting, asks to "create an eBay draft", "make an eBay offer", "push to eBay", or after /marketplace:listing finishes generating copy and the user wants the eBay portion auto-drafted. Never publishes the offer — always leaves it as a draft for the user to review and publish manually in Seller Hub.

  • Linkedin hook writer

    BhaveshKhaple/bhavesh-claude-skills/linkedin-hook-writer Skill

    1★ repo

    Write LinkedIn posts that actually get distributed. Generates hooks in the 5 formats that earn the see-more click on the 360 Brew algorithm, respects mobile pixel-width, and structures the body for maximum dwell time. Use when drafting any LinkedIn post.

  • Skill creator

    FarzamMohammadi/dev-toolbox/.claude/skills/skill-creator Skill

    no license1★ repo

    Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

    The same file is in 7 other repositories

  • Claude code slash commands

    JamesPrial/claude-plugins/.claude/skills/claude-code-slash-commands Skill

    1★ repo

    Create custom slash commands for Claude Code. Use when the user wants to create, generate, or build a slash command (.md file) for Claude Code, or when they ask about slash command syntax, frontmatter options, argument handling, or want help organizing their commands. Triggers on phrases like "make a slash command", "create a command for Claude Code", "write a /command", or questions about $ARGUMENTS, allowed-tools, or command frontmatter.

    The same file is in 3 other repositories

  • 30x seo ai visibility

    norahe0304-art/30x-seo-cn/skills/30x-seo-ai-visibility Skill

    1★ repo

    监控品牌在 AI 平台的可见性(Google AI Overview、ChatGPT、Claude、Gemini、Perplexity)。 追踪 LLM 提及、分析 AI 生成的引用、识别 AI 搜索机会。 当用户说"AI可见性"、"LLM提及"、"AI Overview"、"ChatGPT可见性"、 "AI搜索"、"生成式搜索"、"AI引用"或"品牌在AI中"时使用。

  • Boss

    LaserPhaser/teamwork-plugin/skills/boss Skill

    no license1★ repo

    Use when the user wants to execute a large programming task with a multi-agent team — Boss orchestrator dispatches Developer, Code Reviewer, QA, and Product agents autonomously

  • Agent designer

    DROOdotFOO/agent-skills/skills/agent-designer Skill

    1★ repo

    Multi-agent system design with orchestration patterns, tool schemas, and guardrails. TRIGGER when: user asks to design an agent system, choose agent architecture, define tool schemas, add guardrails, or evaluate agent performance; user runs /agent-design or /agent-architect. DO NOT TRIGGER when: using a specific agent framework (use framework docs), writing prompts for single-turn LLM calls, general API integration without agent orchestration.

  • Memory cleanup

    ladyiceberg/openclaw-memory-quality/skills/memory-cleanup Skill

    1★ repo

    Guided two-step cleanup for OpenClaw long-term memory (MEMORY.md) — audit first, confirm with user, then clean. Handles report_id automatically so the user never sees it. Use this skill whenever the user wants to clean, purge, or tidy their OpenClaw memories, mentions stale or old memories, or uses phrases like "clean memory", "cleanup memory", "delete old memories", "remove stale memories", "清理记忆", "删除旧记忆", "记忆清理". Always use this skill for memory cleanup requests — don't attempt cleanup without it.

  • Eval generator

    varunk130/AI-Eval-Skills/skills/eval-generator Skill

    1★ repo

    Generates eval test cases for AI agents from an eval suite plan (output of /eval-suite-planner) or a plain-English agent description. Supports both single-response and conversation (multi-turn) evaluation modes. Outputs a test set table, a CSV file in the Copilot Studio import format (single-response only - used here as the primary worked example; trivially adaptable to any harness that accepts tabular test cases), and a docx report for human review.

  • Github security audit

    Consultora-AMDT/claude-github-security-audit/es/github-security-audit Skill

    1★ repo

    Auditoría de seguridad para repositorios GitHub antes de integrarlos en tu stack. 7 dimensiones: salud del proyecto, seguridad del código, supply chain, calidad, licencia, superficie MCP/plugin y señales de confianza externas. Scoring ponderado con veredicto ADOPT/EVALUATE/CAUTION/AVOID e informe HTML. Inspirado en los frameworks de Trail of Bits (supply-chain-risk-auditor, insecure-defaults). Actívalo con: auditoría repo, audit repo, seguridad repo, analizar repo, evaluar repo, evaluar librería, evaluar herramienta, review repo, supply chain, repo seguro, debería usar este repo, evaluar dependencia, es seguro este repo, security audit github, repo risk, evaluar MCP server, evaluar plugin, evaluar skill, evaluar integración. También cuando el usuario comparta un enlace a GitHub y pregunte si integrarlo. NO activar para análisis de código propio ni auditorías SEO.

  • Skill

    hoveychen/claude-skills/npm/cli-with-claude-skill/skill Skill

    1★ repo

    Use when creating, scaffolding, or adding/renaming/removing subcommands or flags in a CLI tool that ships an installable Claude Code skill (e.g. `<tool> install-claude-skill`), or when asked to "update the <tool> skill" / "the skill is out of date" for such a tool

  • Linear

    andresd/jot-skills/linear Skill

    1★ repo

    Capture, triage, and plan work on Linear issues from natural language, across one or many teams. Auto-triggers on phrases like "capture this in Linear:", "what should I work on next in Linear", "what's on my plate in Linear", "tidy the Linear backlog", "find duplicate Linear issues", "all <X> Linear bugs to @<user>", references to Linear issue keys (e.g. "ENG-123"), and explicit `/jot-linear <cmd>`, `linear:`, or `jot-linear:` prefixes. Use when the user wants to turn brain-dump text into a well-formed Linear issue, decide what to work on next in Linear, run dedup/stale passes, or bulk-edit Linear issues by natural-language intent. Requires the Linear MCP server to be configured in Claude Code (`https://mcp.linear.app/sse`).

  • Cursor cli

    Ottili-ONE/skills/skills/curated/cursor-cli Skill

    1★ repo

    Use when automating or invoking Cursor CLI (agent/cursor-agent) for non-interactive tasks, CI pipelines, or multi-agent delegation.

  • Agent eval coverage

    vikast908/agent-repo-card/skills/agent-eval-coverage Skill

    1★ repo

    Use when the user wants to know whether their AI/agent repo has the evals and tests needed to trust changes — checking for golden/regression test sets, prompt regression tests, LLM-as-judge, behavioral & tool-use tests, hallucination/safety checks, CI gating, and metrics. Triggers on "do I have enough evals", "how do I test my agent", "would I know if a prompt change broke things", "eval coverage", "regression tests for prompts".

  • Llm council

    1marcelserrano/mscreative-skills/skills/llm-council Skill

    no license1★ repo

    Passa qualquer pergunta, ideia ou decisão de alto custo de erro por um conselho de 5 conselheiros de IA que analisam o caso de forma independente, revisam o trabalho uns dos outros de forma anônima (peer review) e sintetizam um veredito final. Baseado no método LLM Council de Andrej Karpathy. Cada conselheiro pensa por uma lente diferente — o Contrário, o Pensador de Primeiros Princípios, o Expansionista, o Forasteiro e o Executor — que criam tensão proposital entre si. Entrega onde o conselho concorda, onde diverge, os pontos cegos que só a revisão cruzada pegou, uma recomendação direta e o primeiro passo concreto. Gera relatório HTML + transcrição. TRIGGERS: passa no conselho, roda o conselho, convoca o conselho, leva pro conselho, conselho disso, conselho dessa decisão, war room isso, sala de guerra, põe à prova, pressiona essa ideia, stress test disso, testa essa decisão, debate isso, debate essa ideia. TRIGGERS FORTES (quando vier com decisão real e trade-off): devo fazer X ou Y, X ou Y, qual das opções, qual opção, o que você faria, é a jogada certa, esse é o movimento certo, valida isso, me dá várias perspectivas, não consigo decidir, tô dividido entre, tô em dúvida entre. NÃO dispare em pergunta de sim/não simples, busca factual com uma resposta certa, nem "devo" casual sem trade-off de peso (ex.: "devo usar markdown?" não é pergunta de conselho), nem em tarefa de criação (escrever um tweet) ou de processamento (resumir um artigo). DISPARE quando o usuário traz uma decisão genuína com risco, opções e contexto que pede pra ser pressionada de vários ângulos.

    The same file is in 1 other repository

  • Agent memory designer

    imtiazrayhan/agentscamp-library/skills/agent-memory-designer Skill

    1★ repo

    Design a project's CLAUDE.md and memory hierarchy by exploring the repo to learn its real build/test/lint commands, architecture, and non-obvious gotchas, then writing a concise, skimmable memory that keeps only what belongs in context. Use when onboarding a repo to Claude Code with no CLAUDE.md, or when an existing one is bloated, stale, or being ignored.

  • Arcjet

    arcjet/skills/arcjet Skill

    1★ repo

    Add Arcjet security protection to any code path — HTTP route handlers, API endpoints, AI agent tool calls, MCP servers, background jobs, and queue workers. Covers rate limiting, bot detection, email validation, prompt injection detection, sensitive information blocking, content moderation, and abuse prevention. Works with JavaScript/TypeScript, Python, and Go across Next.js, Express, Fastify, SvelteKit, Remix, Bun, Deno, NestJS, FastAPI, Flask, net/http, and non-HTTP contexts. Use this skill when the user wants to add security, rate limiting, bot protection, or abuse prevention to any part of their application — whether they say "protect my API," "rate limit tool calls," "block bots," "secure my endpoint," "add security to my MCP server," or "prevent abuse" without mentioning Arcjet specifically.

  • Add mcp skill

    pol-cc/agentic-data-engineer/skills/add-mcp-skill Skill

    1★ repo

    Add a new BigQuery-backed skill to the MCP server: a tool exposed to AI agents plus the .md context files that describe the underlying data. Invoke when the user wants AI agents (claude.ai, Claude Code, Cursor) to query a new domain of the warehouse.

  • Smart orchestrator

    ZGE26/Claude-Skill/smart-orchestrator Skill

    no license1★ repo

    Use this skill for ALL user requests. It analyzes the true complexity of a prompt and determines the most efficient response depth — avoiding over-thinking on simple tasks and under-delivering on genuinely complex ones. Trigger on every prompt: questions, coding, writing, analysis, strategy, debugging, translation, or planning.

  • Prompt engineer

    omarfarahatoglu-tur/ai-agent-skills/skills/ai-team/prompt-engineer Skill

    1★ repo

    Open-source AI agent skills for Claude Code, OpenAI Codex, Cursor, and modern developer workflows.

  • Create implementation prompt

    itsjavi/skills/skills/create-implementation-prompt Skill

    1★ repo

    Coding agent skills to help projects adopt spec-driven development with durable product memory documents

  • Canopy runtime

    kostiantyn-matsebora/canopy/skills/canopy-runtime Skill

    1★ repo

    Canopy framework execution engine. Interprets canopy-flavored skills (any SKILL.md with a `## Tree` section) at runtime — platform detection, section semantics (`## Agent`/`## Tree`/`## Rules`/`## Response:`), tree notation (`<<`, `>>`, `|`), control-flow primitives (`IF`/`ELSE_IF`/`ELSE`/`SWITCH`/`CASE`/`DEFAULT`/`FOR_EACH`/`BREAK`/`END`), interaction primitives (`ASK`/`SHOW_PLAN`), execution primitives (`EXPLORE`/`VERIFY_EXPECTED`), op lookup chain, category directory semantics, subagent contract. Install this to execute existing canopy skills. Install `canopy` (the authoring agent) too if you need to create/edit/manage them.

  • Design handoff doc

    SkillMedev/designer-to-dev-handoff/skills/design-handoff-doc Skill

    1★ repo

    Writes a complete design handoff document covering components, design tokens, interaction states, and edge cases for engineering implementation. Use when handing off a feature or screen to developers.

    The same file is in 1 other repository

  • Dpdp

    ESR-style/compliance-copilot/skills/dpdp Skill

    1★ repo

    DPDP Act, 2023 (India) compliance expert for developers. Explains Digital Personal Data Protection Act obligations with section citations, covers the finalized DPDP Rules 2025, and scans code for violations specific to India's privacy law. Activate when: building apps for Indian users, handling personal data of Indian residents, implementing consent flows under DPDP, dealing with children's data (age threshold: 18 in India), planning breach notification to Data Protection Board, or comparing DPDP vs GDPR obligations. Key difference from GDPR: only 2 lawful bases (consent + certain legitimate uses — NO legitimate interests for general processing).

  • Delegate

    ominou5/agentic-workflows/Skills/delegate Skill

    1★ repo

    Turn Claude Code into a multi-model orchestration and delegation system. FIRST discovers which model CLIs and Claude models are available on THIS machine, then builds a customized "right model for the right job" routing config plus opt-in subagents that delegate work to external models (Codex/GPT, Gemini, OpenRouter, Ollama, local, etc.) and report results back. Use when a user wants to set up model delegation, route tasks to cheaper or other-provider models, offload token-hungry work, or orchestrate subagents across providers.

  • Brief to prompt

    royvergara/design-team-os/skills/brief-to-prompt Skill

    1★ repo

    Use when converting a design brief into a prompt for an AI builder — v0, Bolt.new, Lovable, Replit, Claude Artifacts, Framer, or any generator. Triggers on a brief plus a request to write a prototype or build prompt for a named tool. Will not output a prompt until the brief defines what good looks like; full-app builders also need the data settled first.

  • Skill eval

    adhi-jp/agent-skills/skills/skill-eval Skill

    1★ repo

    Workflow-focused agent skills and evaluation suites for software development, skill maintenance, and Minecraft modding.

  • Build agent

    nanocodana/nanocodana/packages/cli/example-skills/build-agent Skill

    1★ repo

    Scaffold, write, and test a brand-new NanoCodana agent (a runnable NodeAgent script, plus a skill if useful) from a plain-language description

  • Local sandbox

    Miyamura80/MCP-Template/.agents/skills/local-sandbox Skill

    1★ repo

    Preview an MCP-UI app (mcp_server/apps/*) from fixtures in a browser with no MCP server, Gmail, OAuth, or network. Use when asked to see, screenshot, or test how an MCP App iframe renders, or to render it live in the Claude Code cloud.

  • Claude handoff

    rmerk/crewai-headless-flow/.agents/skills/claude-handoff Skill

    1★ repo

    Hand the current conversation off to a fresh background agent that picks up the work immediately.

    The same file is in 5 other repositories

  • Advanced orchestration

    roronoazoroshao369/vibe-coding-os/skills/agents/advanced-orchestration Skill

    1★ repo

    Vibe Coding OS — Claude/Codex/Cursor skill framework with 139 skills, 111 commands, 95 templates, 22 tracked sources, 28/28 validation gates PASS. Quality Shield, Engineering Discipline Pack, plugin marketplace.

  • Model radar

    primexiao/agent-skills/skills/model-radar Skill

    1★ repo

    Find, filter, compare, and recommend LLM models using OpenRouter's current catalog, price, context, capabilities, popularity, performance, benchmark, and task-spend data. Use when the user targets OpenRouter or accepts it as the comparison dataset for model selection, model-vs-model comparisons, budget/capability constraints, and questions such as "which model should I use", "cheapest vision model", or "what do teams pay for agent planning". Do not use for local-only or provider-specific deployment, training/fine-tuning advice, unrelated architecture, or general AI news.

  • Agents orchestrator

    MarioJames/skill-foundry/skills/agents-orchestrator Skill

    1★ repo

    Production-proven agent skills: agent-swarm, asset-validation, browser-harness, awesome-presentation, workspace-knowledge-graph.

  • Aigd handoff

    ProdaZhang/aigd-zh/aigd-handoff Skill

    1★ repo

    AIGD 阶段4 · 定稿生成交接包。当某系统试玩定稿后,要生成接口契约、验收用例、(按需)美术/客户端/服务端文档、策划版验收清单时使用。产出"另一个 AI 能直接开发"的平台无关交接物。是 aigd 包的一员,方法论见 ../aigd/references/。

  • Handoff resume

    Vertiso/memory-codex/vertiso-memory/skills/handoff-resume Skill

    1★ repo

    Use at session start when hello reports open handoffs, or when the user runs /handoff-resume — finds open handoffs, claims the chosen one, and reconciles it against current reality before resuming work.

    The same file is in 2 other repositories

  • Handoff

    brian8a1/senso-agent-skills/skills/handoff Skill

    no license1★ repo

    Hand a completed design or code change back to the existing Senso Backlog item for human review. Use when a designer has a reviewable artifact or an engineer has a PR, commit, checks, implementation summary, blocker, or technical decision that teammates need in Senso and the item should move to In Review.

  • Caveman compress

    Fatih0234/pi-caveman/skills/caveman-compress Skill

    1★ repo

    Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman-compress FILEPATH or "compress memory file"

    The same file is in 4 other repositories

  • Handoff resume

    Vertiso/memory-cursor/vertiso-memory/skills/handoff-resume Skill

    1★ repo

    Use at session start when hello reports open handoffs, or when the user runs /handoff-resume — finds open handoffs, claims the chosen one, and reconciles it against current reality before resuming work.

    The same file is in 2 other repositories

  • Handoff resume

    Vertiso/memory-claude/vertiso-memory/skills/handoff-resume Skill

    1★ repo

    Use at session start when hello reports open handoffs, or when the user runs /handoff-resume — finds open handoffs, claims the chosen one, and reconciles it against current reality before resuming work.

    The same file is in 4 other repositories

  • Llm wiki agent memory bridge

    po4yka/llm-wiki-skills/skills/llm-wiki-agent-memory-bridge Skill

    1★ repo

    Decide what belongs in LLM-Wiki versus agent memory, AGENTS.md, CLAUDE.md, Auto Memory, Codex project memory, or other runtime memories. Use when instruction files are bloated, domain facts live in agent memory, or the user wants clean memory boundaries.