agentsclimarketplace

Context & AI engineering

25,991 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

  • MCP-Bastion

    vaquarkhan/MCP-Bastion/io.github.vaquarkhan/mcp-bastion MCP server

    no license4★ repo

    Security middleware for MCP. Blocks prompt injection, PII leakage, and resource exhaustion.

  • Dokploy MCP

    vcode-sh/dokploy-mcp/io.github.vcode-sh/dokploy-mcp MCP server

    4★ repo

    Dokploy MCP server for Codex, Cursor, and Claude with compact stdio and hosted HTTP modes

  • Easy Digital Downloads

    verygoodplugins/mcp-edd/io.github.verygoodplugins/mcp-edd MCP server

    4★ repo

    MCP server for Easy Digital Downloads REST API - sales, customers, products, analytics

  • Voidmob mcp

    voidmobcom/voidmob-mcp/io.github.voidmobcom/voidmob-mcp MCP server

    4★ repo

    Mobile proxies, non-VoIP SMS verifications, dedicated numbers, and global eSIMs for AI agents.

  • eKYC Suite

    wefi-ai/eKYC-suite/io.github.wefi-ai/ekyc-suite MCP server

    4★ repo

    KYC / eKYC MCP server for face compare, liveness, OCR, and image labeling.

  • Syncro

    wyre-technology/syncro-mcp/io.github.wyre-technology/syncro-mcp MCP server

    4★ repo

    MCP server for Syncro MSP — customers, tickets, assets, invoices, and more.

  • Learning Model Context Protocol

    yarnabrina/learn-model-context-protocol/io.github.yarnabrina/mcp-learning MCP server

    no license4★ repo

    MCP server that can perform basic arithmetic operations and parse/evaluate arithmetic expressions.

  • Mcp server fear greed

    ycjcl868/mcp-server-fear-greed/io.github.ycjcl868/mcp-server-fear-greed MCP server

    dormant4★ repo

    An MCP server for mcp-server-fear-greed

  • Biopharma catalyst mcp

    yesc97/biopharma-catalyst-mcp/io.github.yesc97/biopharma-catalyst-mcp MCP server

    4★ repo

    Forensic biopharma catalyst auditor — 10 tools, deterministic CLEAN/BEAR_SIGNAL verdict.

  • Tessera MCP Server

    tessera-llm/mcp-server/io.tesseraai/mcp-server MCP server

    4★ repo

    MCP server for Tessera's LLM cost-optimization layer: anchored spend, drift, recommendations.

  • Rust FAF

    Wolfe-Jam/rust-faf-mcp/one.faf/rust-faf-mcp MCP server

    4★ repo

    Persistent project context — Rust-native MCP server. IANA-registered .faf format.

  • Brainkb

    sensein/BrainKB/org.brainkb/brainkb MCP server

    no license4★ repo

    MCP server for querying BrainKB, a knowledge base for neuroscience knowledge graphs.

  • Syslog MCP

    jmagar/syslog-mcp/tv.tootie/syslog-mcp MCP server

    4★ repo

    Syslog receiver and MCP server for homelab log intelligence.

  • Claude mail bridge init

    CodingJay-1/claude-mail-bridge/src/claude_mail_bridge/assets/skills/claude-mail-bridge-init Skill

    3★ repo

    Use when Claude Mail Bridge is installed (presence.json exists). Provides behavior guidelines for remote collaboration scenarios, including presence detection and MCP usage.

  • Claw agent protocol

    jfleagl12/claw-agent-protocol Skill

    3★

    Interact with the Claw Agent Protocol (CAP), a lightweight MCP server providing canonical, real-time access to personal data for AI agents. Use when working with user personal data across Gmail, Calendar, Notion, Slack, tasks, contacts, or any CAP-connected data source. Enables structured querying, data organization, and task-oriented views of user information.

  • Review user prompt english

    swapii/claude-linguist/plugins/review-user-prompt-english/skills/review-user-prompt-english Skill

    3★ repo

    MUST be used on EVERY user message that contains English. Proofreads the user's English for grammar, spelling, punctuation, article, preposition, tense, and word-choice errors, then shows corrections. TRIGGER: any English text from the user — statements, questions, requests, one-word replies, anything. Do NOT skip. Do NOT wait to be asked. The user is a non-native speaker practicing English and expects every message to be reviewed.

  • Intel

    voxpelli/vp-claude/skills/intel Skill

    3★ repo

    This skill should be used to research a software package OR a developer/CI tool and create or update a structured Basic Memory note with post-write cross-linking. Triggers: 'research package', 'package intel', 'what does [pkg] do', 'add [pkg] to knowledge graph', 'enrich [pkg]', when adding depends_on [[npm-*]] relations, 'research crate/gem/go module/composer/pypi package', 'research a homebrew formula', 'brew intel', 'research a cask', 'research a GitHub Action', 'action intel', 'research a docker image', 'research a VSCode extension', 'vscode intel', 'research a gh CLI extension', 'research a Claude Code plugin', 'research an agent skill', 'tool intel', 'what does [tool] do', 'upgrade haul', or a pasted npm/brew (or crate/go/composer/pypi/gem) outdated/upgrade line. Prefixes: package family — npm:, crate:, go:, composer:, pypi:, gem: (no prefix defaults to npm); tool family — brew:, cask:, action:, docker:, vscode:, gh:, plugin:, skill:.

  • Cypress agent skill

    KahlilR23/cypress-agent-skill Skill

    3★

    Production-grade Cypress E2E and component testing — selectors, network stubbing, auth, CI parallelization, flake elimination, Page Object Model, and TypeScript support. The complete Cypress skill for AI agents.

  • Gpt image 2

    satasuk03/media-gen-skills/gpt-image-2 Skill

    no license3★ repo

    Generate and edit images with OpenAI's gpt-image-2 model. Use when the user asks to create, generate, render, edit, modify, inpaint, or composite images via OpenAI / GPT Image. Supports text-to-image generation, single- and multi-image edits, mask-based inpainting, reference-image composition, and transparent backgrounds via gpt-image-1.5.

  • Agentmd

    mryll/skills/skills/agentmd Skill

    3★ repo

    Generate a single canonical AGENTS.md context file plus minimal CLI-specific shim files that @-import it for coding agents that do not read AGENTS.md natively (Claude Code, Gemini CLI, Qwen Code). Based on "Evaluating AGENTS.md" (ETH Zurich, Feb 2026) which found auto-generated context files DECREASE performance by ~3% and increase costs by 20-23%, while minimal human-written files improve performance by ~4%. Use when the user says "generate CLAUDE.md", "create AGENTS.md", "generate context file", "agentmd", "create recommended CLAUDE.md", "generate agent instructions", "init context file", or any request to create/improve a coding agent context file for a repository. Replaces the default /init command which generates bloated, counterproductive context files.

  • Agent memory

    CODE-SAURABH/OpenSkills/agent-memory Skill

    3★ repo

    Session memory management, browser-based QA testing, and multi-agent coordination skill. Use when the user wants to persist learnings across sessions, review what the agent has learned about their codebase, prune stale knowledge, run browser-based testing with real Chromium, coordinate multiple AI agents on the same task, or set up authenticated browser sessions for testing.

  • Share claude code chat

    blockdancez/PreviewShip/skills/share-claude-code-chat Skill

    no license3★ repo

    Export Claude Code JSONL conversations into high-fidelity HTML pages with safe tool timelines, then deploy them to PreviewShip as public share links. Use when users ask to share a Claude Code chat, export Claude Code history, publish a Claude Code conversation, or create a public URL for implementation and review context.

  • Bird agent

    bird-chinese-community/BIRD.skills/bird-agent Skill

    3★ repo

    TRIGGER aggressively for BIRD (BIRD1/2/3) routing-daemon configuration work. Positive signals: - File patterns: bird.conf, bird2.conf, bird3.conf, bird6.conf, any *.conf file that contains BIRD syntax, bird.config.json, and any file included by a BIRD config. - Syntax tokens: protocol, filter, function, define, table, router id, local as, neighbor, prefix, route, bgp_path, community, import, export, bgp_path.prepend, if defined(), path, OSPF, BGP, RIP, RADV, Static, Kernel, Device, Perf, RPKI, Babel, Aggregator, MRT. - Commands: birdcc lint, birdcc fmt, bird -p, birdc, bird -c, birdc configure. - Requests: lint/format/validate a BIRD config, fix a syntax error or diagnostic, explain a BIRD keyword/filter/protocol, review a config snippet, resolve cross-file includes, or compare BIRD1/BIRD2/BIRD3 syntax. Negative signals (do NOT trigger): Cisco IOS/IOS-XR/NX-OS, Juniper JunOS, FRRouting (frr.conf), nginx, any non-routing use of "bird", bird biology / ornithology, or general networking questions without a BIRD routing context. For editor/CLI installation use birdcc-installer; for setup-birdcc or GitHub Actions use birdcc-cicd. Trigger even if the user does not explicitly say "BIRD".

  • Aris idea creator

    JZKK720/cubecloud-skilldbundle-setup/upstream/aris-idea-creator Skill

    no license3★ repo

    Generate and rank research ideas given a broad direction. Use when user says "brainstorm ideas", "generate research ideas", "what can we work on", or wants to explore a research area for publishable directions. Ported from wanshuiyin/Auto-claude-code-research-in-sleep (ARIS) — methodology only, Claude-Code-specific MCP/CLI/GPU deps stripped for VS Code Copilot.

  • Llm chat scraper skill

    scrapeless-ai/llm-chat-scraper-skill Skill

    no license3★

    Scrape AI chat conversations from ChatGPT, Gemini, Perplexity, Copilot, Google AI Mode, and Grok.

  • Sparring

    nyxandro/sparring-skill/sparring Skill

    3★ repo

    Use when the user says "sparring", "run sparring with Claude", "do sparring with Claude", "do sparring with GPT-5", "sparring with Codex", "sparring my plan with Claude", "discuss this approach with Codex", "get a second opinion through sparring", "give me the sparring transcript", "read the long sparring answer", or asks to leave a sparring session running. Runs a model-vs-model sparring flow through the bundled sparctl harness for planning, brainstorming, second opinions, code review, architecture critique, or normal dialogue; uses one ask-session command that creates or continues provider-native state, and uses tmux only when explicitly needed for live/fallback sessions.

  • Stack bootstrap

    drmahdikazempour/agent-stack/skills/stack-bootstrap Skill

    3★ repo

    Set up or re-sync the agent-stack optimization layer (CLAUDE.md, skills, hooks, code graph, shell compression, Cursor mirror) for a repo. Use when onboarding a repo, right after cloning, or when the agent context feels bloated/unoptimized. Runs `agent-stack init` under the hood — detect, install adapters, generate files, wire hooks, verify, and capture a token baseline — then reports exactly what changed.

  • Aidress skill find verified freight booking agent

    Aidress-ai/aidress-skill-find-verified-freight-booking-agent Skill

    3★

    Find a Verified Freight Booking 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).

  • Claude selfaware

    Sorbh/claude-selfaware Skill

    3★

    Makes Claude aware of its own API usage limits and able to manage them intelligently. Usage is checked automatically by hooks (SessionStart + UserPromptSubmit) that inject a directive when usage gets high; Claude delegates suitable tasks to a Codex sub-agent to conserve tokens, checkpoints work before limits hit, and resumes after resets. Use this skill for: long coding sessions, multi-file refactors, agentic tasks, marathon sessions, or any work where hitting a usage limit mid-task would be disruptive. Also trigger when the user mentions usage, limits, capacity, quota, token conservation, Codex delegation, or the claude-m marathon command. If a TASK_STATE.md exists in the project root, this skill is relevant — read it before doing anything.

  • Agentic skill eval

    stempeck/agentfactory/.claude/skills/agentic-skill-eval Skill

    3★ repo

    Evaluates a skill library to identify which SKILL.md files would produce valuable autonomous agents when converted via /formula-create. Use when assessing a repository of skills for agent creation candidates, prioritizing which skills to convert to formulas, or auditing an existing agent roster for gaps.

  • Agent review

    ethanaubuchon/dossier-tradecraft/skills/agent-review Skill

    3★ repo

    Use in /implement after committing, inside the draft PR, to review the committed diff. Dispatches a dependency-free review subagent fed the diff + review criteria and returns structured findings (severity / location / problem / fix). The recipe drives the address→re-review loop with a human exit gate; the pr-review-toolkit ceiling is an opt-in override of this skill.

  • Benchmark adder

    tmuskal/arc-agi-benchmarker/.claude/skills/benchmark-adder Skill

    no license3★ repo

    Given a benchmark repository URL (agentic envs like arc-agi, memory/eval benchmarks like longmemeval, QA/code/tool-use benchmarks, etc.), orchestrate the creation of a full Claude Code plugin that benchmarks the current harness setup against it. Wraps the babysitter:babysit skill with the benchmark-plugin-creator process.

  • Agent baton

    skycitywu/agent-baton Skill

    3★

    多角色 AI 团队接力协作框架(BA / Arch / Dev / TechLead),通过 Markdown 文档在角色之间传递上下文,适用于需要结构化协作的中大型项目。当用户明确说"用 AgentBaton 初始化项目"/"启动 AgentBaton 框架",或提到任一角色名("BA 角色"/"Arch 角色"/"Dev 角色"/"TechLead 角色"/"TechLead Review"),或当前项目根目录已存在 `config/roles/` 或 `config/TEAM_GUIDE.md` 时,使用本 skill。不要用于:简单代码修改、bug 修复、单文件改动、代码探索、纯重构、与多角色协作无关的常规开发任务。

  • Stock sdk mcp

    tiancheng91/skills/skills/stock-sdk-mcp Skill

    no license3★ repo

    股票行情数据服务 - 支持 A股/港股/美股实时行情、K线、技术指标、板块数据。当用户查询股票、基金、行情、技术分析、板块数据、市场概览、股票筛选、持仓监控时使用此技能。

  • Src

    nestharus/agent-implementation-skill/src Skill

    3★ repo

    Multi-model agent implementation workflow for software development. Orchestrates research, evaluation, design baseline, implementation, RCA, structured decomposition, constraint discovery, model selection, and agent-driven Stage 3 codemap exploration across external AI models (GPT, GLM, Claude). Use when implementing features through a structured multi-phase pipeline with planspace/codespace separation, dynamic scheduling, and SQLite-backed agent coordination.

  • Open responses agent dev

    OthmanAdi/open-responses-agent-skill/skills/open-responses-agent-dev Skill

    3★ repo

    Build autonomous agents using Open Responses API via HuggingFace Inference Providers. Single unified endpoint with multi-provider routing via model suffixes. Use the OpenAI SDK with custom base_url for seamless development.

    The same file is in 2 other repositories

  • Epic orchestrator

    chancegraff/rules-for-claude/skills/epic-orchestrator Skill

    no license3★ repo

    Orchestrate parallel execution of a Jira Epic's tickets by dispatching headless Claude Code workers in isolated git worktrees. Analyzes tickets for dependencies, plans execution waves, spawns one worker per ticket with a skill file loaded as its system prompt, coordinates with workers via append-only markdown files, and manages the full lifecycle through to PRs and review response. Invoke manually via /epic-orchestrator.

  • Repo indexer

    jyshnkr/repo-indexer/skills/repo-indexer Skill

    3★ repo

    Indexes and documents a codebase for persistent Claude context with minimal token overhead. Use when asked to index a repo, understand a codebase, create CLAUDE.md, set up Claude memory, bootstrap context, onboard to a project, or document codebase for Claude. Triggers on phrases like "index this repo", "understand this codebase", "set up context", "create project memory", "help me onboard". Creates tiered memory system using Claude native memory + minimal boot files + on-demand loading + conversation history as knowledge store. Do NOT use for general code questions, debugging, or tasks unrelated to codebase indexing/documentation.

  • Adversarial review

    AlexShchuka/neuro-matrix/skills/adversarial-review Skill

    3★ repo

    Run an independent audit gate before any fleet output lands. Use after agent-fleet-orchestration Stage 3 (or any multi-agent build) — before merge, before deploy, before the next phase. Frames the reviewer as an external adversary, not a helper; produces triaged findings with human triage for load-bearing blockers.

  • Agentic structure

    BackGwa/Agentic-Structure/plugins/skills/agentic-structure Skill

    3★ repo

    Collaborative programming framework for production-ready development. Use when starting features, writing code, handling security/errors, adding comments, discussing requirements, or encountering knowledge gaps. Applies to all development tasks for clear, safe, maintainable code.

    The same file is in 3 other repositories

  • Prompt fixer

    Soumya7681/prompt-fixer/skills/prompt-fixer Skill

    no license3★ repo

    Clean up and clarify a rough prompt before acting on it — fix typos, expand a terse or single-word ask into a clear instruction, repair broken or unclosed {{template}} placeholders, substitute known variables, and strip filler openers. Use whenever a request looks hasty: obvious misspellings, a vague one-or-two-word command, "can you/could you/please ..." phrasing, or an unclosed template like {{name.

  • Image prompt

    veryCoolTimo/imagegen-skills/skills/image-prompt Skill

    3★ repo

    Use when the user wants to turn a short idea into a rich, production-grade image-generation prompt — posters, landing-page or UI mockups, ads, editorial layouts, photoreal scenes, game screenshots, logos, or illustrations. Builds ONE structured, copy-paste-ready prompt optimized for gpt-image-2 by default, following proven layered-composition patterns (named zones, hex palette, real font references, mood/finish, IP-safety). Triggers on requests like "сделай крутой промт для постера", "нужна картинка/постер/лендинг для…", "generate a prompt for a landing hero", "prompt for an ad / logo / game screenshot".

  • Apex to action

    CodedRichy/food-chain-ideation/skills/apex-to-action Skill

    3★ repo

    Converts food chain battle output into a 90-day execution plan. Takes the Evolved Idea, Unfair Advantage Statement, and Battle Log from any food chain battle and produces what to build first, what to validate before building, what to never build, and weekly milestones. The natural next step after any food chain battle. Works in Claude.ai, Claude Code, Cursor, Windsurf, Copilot with no dependencies.

  • Huashu agent swarm en

    Biraj2004/huashu-skills-english/huashu-agent-swarm-en Skill

    3★ repo

    Multi-agent swarm parallel collaboration using pure git self-organisation, ideal for large-scale project development. Use when the user mentions "swarm mode", "multi-agent", "parallel development", or "agent swarm".

  • Plugin

    YunyueLi/claude-design-stack/plugin Skill

    no license3★ repo

    Install, update, or remove claude-design-stack — a curated set of Claude Code design skills (impeccable, the taste suite, ui-ux-pro-max) plus a decision-table router. Use when the user wants to set up their design stack, "install the design skills", "set up claude-design-stack", add the design tooling, or uninstall it.

  • Ai os init

    OmarSaleh506/skills/skills/ai-os-init Skill

    3★ repo

    Scaffolds an "AI Operating System" project structure into any project, non-destructively — adds only missing pieces, never removes or overwrites anything that already exists. Creates: CLAUDE.md (memory layer), docs/architecture.md + docs/decisions/ + docs/runbooks/ (documentation), tools/scripts/ and tools/prompts/ (utilities), and .claude/ with two example skills (new-adr, clean-tests), six hooks (guard-secrets, branch-guard, auto-format, typecheck, n+1-guard, audit-log), and a read-only docs-auditor subagent — all wired via .claude/settings.json. Requires only Python 3 and bash; no external dependencies. Use when asked to "init Claude Code project structure", "scaffold the AI-OS layers", "add CLAUDE.md hooks subagents to this project", "set up the Claude Code layers", "initialize ai-os", "add the AI operating system structure", "scaffold this project for Claude Code", or "add skills hooks agents here". Safe to re-run — idempotent. Not for non–Claude-Code agents (it scaffolds Claude Code's .claude/ layer) and not a code generator — it sets up project structure, not application code.

  • Agent config

    FynePool/job-hunter-template/.claude/skills/agent-config Skill

    no license3★ repo

    Onboarding guidato per il sistema Job Hunter. Usa questa skill quando un nuovo utente vuole attivare il sistema di ricerca lavoro autonoma: ingerisce il CV, fa domande su vincoli/preferenze (trasferimento, remoto, retribuzione, preavviso, diritto al lavoro, lingue), produce master-profile.yaml e il primo intento di ricerca in searches/ nel repo del sistema, genera e attiva la config della routine job-watch. Trigger su qualsiasi richiesta di avviare/configurare/inizializzare il sistema o la ricerca lavoro, anche breve o generica — es. "inizializza il progetto", "salva queste skill e configurami", "iniziamo a fare job-hunting", "configurami il sistema". Non richiedere che l'utente nomini "agent-config" o "onboarding": il segnale è l'intento di avviare il processo. NON usarla per modificare un search-profile già esistente ("aggiorna il mio profilo di ricerca", "cambia i ruoli/le location"): per quello esiste la skill job-search-profile.

  • Llm buster skill

    metravod/llm-buster-skill Skill

    3★

    Use this skill when the user asks to audit a codebase for LLM API calls (OpenAI, Anthropic — Python and TS/JS SDKs plus equivalent raw HTTP) and decide which calls can be replaced with deterministic logic. Activates on phrases like 'audit LLM usage', 'bust LLM calls', 'bust the LLM here', 'llm-bust this', 'do I actually need an LLM here', 'replace LLM with deterministic', 'de-LLM this', 'find LLM calls', 'cut LLM costs', 'is this prompt necessary'; on grep hits for `openai.`, `client.chat.completions.create`, `from anthropic import`, `client.messages.create`, `api.openai.com/v1/chat/completions`, `api.anthropic.com/v1/messages`; and on questions about whether a specific LLM call could be a regex, parser, classifier, lookup, or rule. Produces a per-call audit report with 🟢/🟡/🔴 verdicts and concrete deterministic alternatives. Does NOT rewrite code unless the user explicitly asks after seeing the report.

  • Context optimizer

    webbertakken/agent-skills/skills/context-optimizer Skill

    3★ repo

    Audit and optimise context window usage for AI coding tools (Claude Code, OpenCode, etc.). Estimates token breakdown, identifies waste (duplicate skills, overlapping rules, bloated instruction files, dirty git status, MCP server overhead), and provides actionable recommendations with projected savings. Use when the user says "context checkup", "reduce context", "check context", "context audit", "how big is my context", or when sessions feel sluggish.

  • Claude skill

    Kickgeist/agents/skills/claude-skill Skill

    3★ repo

    Play and predict World Cup 2026 matches on KICKGEIST through your AI agent. Use this whenever someone wants to predict a match outcome (home win / draw / away win), start or join a prediction group with friends, or check this agent's own KICKGEIST points, accuracy, streaks, or rank. KICKGEIST is a free, zero-money, group-first social prediction game (no money, no in-app purchases, never gambling). Connect via the KICKGEIST MCP server at https://mcp.kickgeist.com/mcp.

  • Harnesskit

    qWaitCrypto/HarnessKit/agent-surfaces/skills/harnesskit Skill

    3★ repo

    Use whenever the task involves project documentation, architecture, design decisions, implementation plans, specs, worklogs, project memory, or any durable knowledge that should live in the repo. This includes reading or writing docs, querying prior decisions, checking doc health, reviewing history, updating AGENTS.md / CLAUDE.md / ARCHITECTURE.md, or organizing project knowledge. If the repo has AGENTS.md, CLAUDE.md, or .harnesskit/, treat HarnessKit as the default documentation workflow: read the entrypoint first, then use the CLI when query, context, checks, indexing, or history are useful.

  • Know my repo

    silkyland/know-my-repo Skill

    3★

    Onboards an agent onto an unfamiliar repository from zero knowledge: deep parallel read of the codebase, extraction of the repo's actual conventions (each proven by at least two examples), verified build/test/run commands, an end-to-end exemplar trace of how a feature is really added, then generates the initial knowledge set — AGENTS.md and docs/ARCHITECTURE.md — with every fact cited. Nothing is deleted. Use on repositories with no (or trivial) agent knowledge files, when the user asks to onboard, initialize, understand, or learn a repo, generate a CLAUDE.md/AGENTS.md from scratch, or mentions know-my-repo or /know-my-repo.

  • Composio

    lunchpaillola/pipa-skills/skills/composio Skill

    3★ repo

    Operational skills for the agents people already use.

  • Agile project lifecycle mcp

    wchen02/cursor-agent-learning/.cursor/skills/agile-project-lifecycle-mcp Skill

    no license3★ repo

    Full agile lifecycle with MCP: use MCP to fetch current docs/API schema during discovery and development. Use when building a project from a rough idea that depends on external APIs or libraries and you want up-to-date references via MCP.

  • Prompt optimizer skill

    dreamor/prompt-optimizer-skill Skill

    3★

    Optimize and rewrite prompts using 61 frameworks (APE, RACE, CRISPE, Chain-of-Thought, COAST, SMART, etc.). Trigger on "optimize prompt", "improve this prompt", "make this prompt better", "rewrite for AI", "优化提示词", "改写 prompt", "优化指令", "让提示词更好", "帮我把这个写成 prompt" or any vague/short instruction the user wants turned into a high-quality prompt — even if the user only says "make this clearer" or "help me write this". Also trigger whenever the user pastes raw text and asks for a structured AI-ready version, or expresses dissatisfaction with AI output quality without naming a fix. Always use this skill when the user inputs vague instructions, needs prompt optimization, or is dissatisfied with AI output quality.

  • Generation prompt builder

    seaartpublic/skills/generation-prompt-builder Skill

    3★ repo

    Build or optimize high-quality generation prompts from copy, product information, scripts, rough ideas, reference-image descriptions, or existing prompts. Use for image, video, audio, and mixed creative prompts when the user wants ready-to-copy prompt text, not tool execution. Do not use when the user specifically asks to generate an image with GPT Image or asks for storyboard/shot-list planning.

  • Expired domains skill

    Sambel/expired-domains-skill Skill

    3★

    Find and qualify expired, dropping, and auction domains by SEO metrics (Domain Authority, Trust Flow / Citation Flow, referring domains, backlinks, age, language, historical tech). Use when the user wants to buy an expired domain, find aged domains for SEO, build a PBN or money site, research drop-catching, evaluate a specific domain's backlink profile, or compare auction listings across registrars (DropCatch, GoDaddy, Dynadot, Gname, NameSilo and more). Powered by the CatchDoms live MCP server — no API key required for the free tier.

  • Production agent design

    SuperLogicAI/production-agent-design Skill

    3★

    Production-grade design blueprint for stable, effective AI agents — system design, tool design, context/memory management, pre-action verification, security hardening, prompt caching, observability, human-in-the-loop, decision logs, and evaluation. Use proactively whenever designing, building, hardening, auditing, debugging, or shipping any agent or agentic system — tool/function definitions, MCP servers, multi-step or autonomous workflows, model routing, agent memory, guardrails, agent failures, voice agents, workflow-automation agents, or agent-based client deliverables. Trigger on agent, agentic, autonomous, tool use, MCP, orchestration, subagent, agent eval/failure/hardening, agent audit trail/decision log, prompt caching cost — even without "best practices" asked. Default is passive reference — surface only relevant principles. On "walk me through agent design" or "phase this build," run the phased workflow explicitly.

  • Aparser

    izzipizzy/aparser-mcp/skills/aparser Skill

    3★ repo

    Use when parsing or scraping through A-Parser — checking Google/Bing/Yandex positions of a site, collecting SERPs, suggestions, keyword data, or running any A-Parser task via its API/MCP server. Triggers on "A-Parser", "aparser", "парсинг позиций", "сбор выдачи", "проверить позиции сайта", "собрать подсказки".

  • Agent design doctrine

    urmzd/dotfiles/dot_agents/skills/agent-design-doctrine Skill

    3★ repo

    House doctrine for designing LLM agent systems: safety enforced by the harness and tools rather than model goodwill, tools that execute and return results, minimal loop code, interface-first component seams, typed config, deterministic evals over LLM judges, and POC scope discipline. Use when designing or reviewing any agent, tool-use loop, eval harness, or agent-backed CLI, in any framework. Do NOT use for Pydantic AI framework mechanics (use building-pydantic-ai-agents), generic design principles (use review-design), or Go agent-loop implementation details (use agent).