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

  • Chrome devtools mcp adspower

    pencil20388-eng/browser-automation-skills/skills/chrome-devtools-mcp-adspower Skill

    3★ repo

    🌐 Drop-in skills that teach Claude Code, Cursor & Codex CLI how to automate browsers. Playwright, Selenium, Puppeteer, Web Scraping, AdsPower & more.

  • Agent fleet orchestration

    AlexShchuka/neuro-matrix/skills/agent-fleet-orchestration Skill

    3★ repo

    Run a lead + subagent fleet to build a non-trivial system without collisions, drift, or false completion. Use when a task is large enough to parallelize across agents — decomposing it, freezing contracts, driving execution, and closing each stage with real evidence, not agent reports.

  • Context audit

    adamlinscott/claude-skills/skills/context-audit Skill

    3★ repo

    Audits a repository's Claude context-injection setup — CLAUDE.md, CONTEXT.md, docs/, .claude/agents/, and the per-project memory directory. Reports bloat, broken links, orphaned docs, security risks, missing rules in subagent prompts, and conflicts between memory and project instructions. Use when the user asks to audit their Claude setup, asks "what's wrong with my CLAUDE.md", wants to know if their agents/memory/docs are configured well, or wants to improve Claude's effectiveness in this repository.

  • Automode config

    obeone/claude-skills/skills/automode-config Skill

    3★ repo

    Author, validate, and migrate Claude Code autoMode blocks at the project level. Models the four official autoMode sections (environment, allow, soft_deny, hard_deny — all arrays of prose rules, with `$defaults` per section). Primary target is .claude/settings.local.json (per-user-per-project, gitignored, classifier-read). Reads ~/.claude/settings.json (user baseline, read-only) and .claude/settings.json (shared, classifier-ignores autoMode) for adoption candidates. Phase 1b is agent-driven: the calling agent reads CLAUDE.md / AGENTS.md / .claude/CLAUDE.md and emits a proposal JSON that flows through the same critique + hash-gate + atomic-write pipeline. Runs `claude auto-mode critique` as the canonical gate. Atomic write under per-file flock with sha256 hash gate. Requires Claude Code 2.1.83+ (auto mode itself; see references/automode_doc_bible.md).

  • Food chain code

    CodedRichy/food-chain-ideation/skills/food-chain-code Skill

    3★ repo

    Adversarial architecture stress-tester. Selects attacker agents from a code-specific behavioral DNA library matched to the technical decision. Each attacks under strict role-lock. Weakest eliminated, survivor absorbs and evolves. Tests architecture decisions before a line of code is written. Works in Claude.ai, Claude Code, Cursor, Windsurf, Copilot with no dependencies.

  • Aeo

    dirknicol/pmm-skills/skills/aeo Skill

    3★ repo

    Use this skill when the user wants to audit, improve, or measure how their brand appears in AI assistant answers — ChatGPT, Claude, Perplexity, Google AI Overviews, Gemini, Copilot. Triggers include any mention of 'AEO', 'GEO', 'AI search', 'AI visibility', 'LLM citations', 'answer engine optimization', 'generative engine optimization', 'AI Overviews', 'ChatGPT citations', 'AI brand monitoring', 'AI share of voice', 'how AI describes us', or 'why isn't ChatGPT mentioning us'. Implements a strategic AEO workflow: audit exposure, identify gaps, diagnose causes, prioritize fixes, brief execution, measure over time. Reads `pmm-context.md` first. Vendor-agnostic — describes the work, not a tool. Outputs an AEO audit, gap-and-fix plan, briefs for execution teams, and measurement framework. Do NOT use for traditional SEO (keyword ranking, technical SEO, link building) or for paid AI ads or AI-generated content production.

  • Askit build agents md

    product-on-purpose/agent-skills-toolkit/skills/askit-build-agents-md Skill

    3★ repo

    Creates and improves a plugin's AGENTS.md (the agent navigation and instructions entrypoint) to the Advanced Skill Library Standard. Use when you need to author or sync AGENTS.md, align it with the component index, or trim an overgrown one to essential, mostly-positive guidance.

  • Gpt image assistant

    seaartpublic/skills/gpt-image-assistant Skill

    3★ repo

    GPT Image workflow assistant for text-to-image, reference-image editing, inpainting instructions, posters, typography, UI mockups, diagrams, product images, and final image prompt preparation. Use when the user explicitly wants GPT Image, GPT Image 2, gpt-image, image generation, or image editing. This skill does not include scripts, reference files, or automatic setup.

  • Agent setup

    Shad0wMazt3r/The-Scaffolding/.agents/skills/agent-setup Skill

    3★ repo

    Provide baseline activation guardrails for tool readiness and dependency checks before any phase starts.

  • Topease customs mcp

    TopEase-AI/topease-customs-mcp-skill/topease-customs-mcp Skill

    no license3★ repo

    通过 TOPEASE/Tradee Customs MCP 查询和分析全球海关贸易记录。用于用户要求查询进出口海关数据、买家或供应商出货记录、产品关键词贸易数据、HS 编码贸易数据、国家或市场进出口记录、进口商/出口商线索,或要求配置、接入、排查 TOPEASE 海关数据 MCP 服务时。

  • Session end

    redamancy231-create/claude-skills/session-end Skill

    3★ repo

    [流程:交接] Standardized session handoff executor per AI collaboration framework §9.3. Runs Session Start checklist (verify CLAUDE.md/memory loaded, check memory staleness >30d, load project status, confirm environment) and Session End checklist (update project_status.md, write standardized Next Steps with priority+dependencies, capture cross-task lessons to memory/, flag Retrospect candidates). Use when ending a substantive work session, before context switching, or when invoked as /session-end. Do NOT use for quick Q&A or trivial turns — only sessions that produced or changed project state. Manual invocation only, not automated via Stop hook.

  • Ppds core

    joshsmithxrm/ppds-skills/skills/ppds-core Skill

    3★ repo

    Install, authenticate, and safely operate the Power Platform Developer Suite (PPDS) CLI and MCP server against Microsoft Dataverse — auth profiles, environment selection, the environment-safety model, and error interpretation. Use when the user wants to connect to Dataverse with PPDS, set up `ppds` or `ppds-mcp-server`, manage auth profiles or environments, decide between the PPDS CLI and MCP surfaces, or interpret a PPDS error or exit code. Load this skill first before any other ppds-* skill.

  • Agent browser

    nbialk/quiver-cli/template/.agents/skills/agent-browser Skill

    3★ repo

    Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.

  • Recursive agent improvement

    H-Ali13381/recursive-agent-improvement Skill

    3★

    Use when an agent repeatedly fails at a narrow measurable subtask, the user wants a trainable specialist tool instead of more prompting, or the task needs an evaluator, reranker, classifier, detector, verifier, or small PyTorch model exposed to an agent.

  • Agents md sync

    samhcus/skills/skills/agents-md-sync Skill

    no license3★ repo

    Verify that AGENTS.md files are accurate by checking every path they reference against the actual filesystem. Reports stale paths, missing repos, and repos not mentioned in AGENTS.md. Triggers on "is agents.md accurate", "check agents.md", "sync agents.md", "verify agents.md", "agents.md drift", "update agents.md".

  • Template

    HubWu42/hubwu-skills/template Skill

    3★ repo

    一句话说明这个 skill 做什么、Claude/agent 何时该用它(discovery 阶段只读这两行,务必精准)。

  • Relay handoff stop

    liutao773680119-cmyk/relay-dev-skills/.relay/skills/relay-handoff-stop Skill

    3★ repo

    Use when ending a session before switching tools/models, and a complete handoff snapshot must be persisted. 中文常见触发:做一次标准交接、按接力开发规则收尾、切换前先交接。

  • Aicrew benchmark

    AKSoftCode/aicrew/codex-skills/aicrew-benchmark Skill

    3★ repo

    Run a benchmark to measure skill quality, response time, and token efficiency for aicrew skills.

  • Pressure skill

    Someone-hates-Monday/pressure-skill/.cursor/skills/pressure-skill Skill

    3★ repo

    Cold pressure → warm, sendable replies (ZH/EN). Layered workplace comms—deflect, nudge, pin vague specs—like a super mouthpiece that won't get you fired. Multi-platform Agent Skill (Cursor / Claude Code / OpenClaw) + FastAPI; offline templates. ZH: 拒绝被压力、拒绝职场PUA、反催办、不接锅、软拒绝、立边界。 EN: pushback, boundaries, anti-gaslighting, say-no.

  • Refresh agent docs

    fmind/agent-docs/skills/refresh-agent-docs Skill

    3★ repo

    Re-verify entries in `.agents/docs/` against upstream — repair dead links in the documentation map, update drifted captured snippets, and bump `last_verified` dates. Triggers include "refresh agent docs", "update .agents/docs", "re-verify the docs".

  • Vl handoff

    giltotherescue/velocity-agent-skills/skills/vl-handoff Skill

    3★ repo

    Use when current work needs to be handed off to another developer, agent, reviewer, manager, client, stakeholder, or team. Produces a context-rich handoff tailored to the recipient and delivery medium, including current status, decisions, changed files, verification, open risks, artifacts, and recommended next steps. Trigger on requests like "handoff", "write this up for", "brief the next person", "summarize progress for Slack", "prepare a review handoff", or "pass this to another agent".

  • Ship agent skills

    claudialnathan/agent-kitchen/.claude/skills/ship-agent-skills Skill

    no license3★ repo

    Commit and push complete work in the agent-kitchen repo with its commit discipline, then update this machine's live Claude, Cursor, and Codex skill/plugin copies. Use for requests to commit, push, or ship changes in this repo. Invocation is consent to push and run the documented local sync and plugin update commands.

  • Bestchange

    SwiftAdviser/public-skills/skills/bestchange Skill

    no license3★ repo

    Find trusted BestChange exchangers for crypto-to-fiat and e-currency exchange requests using the hosted BestChange MCP tool. Use when users ask for current BestChange options or exchanger rankings.

    The same file is in 1 other repository

  • Init context

    yinjialu/context-harness/skills/init-context Skill

    3★ repo

    Initialize a context-harness personal context home, data directories, global context files, and optional Codex/Claude Code hooks. Use when the user asks to initialize context-harness, set up a personal context system, configure automatic Code Agent conversation backup, or repair context-harness hooks.

  • Vault capture

    jayantak/vaultmem/skills/vault-capture Skill

    3★ repo

    Write durable knowledge into the Obsidian vault. Trigger when something worth documenting just happened — a root cause, architecture decision, incident, meeting, milestone, people context, reusable pattern — on "make a note", on a subagent spawned to capture session work, and on repo onboarding ("remember this project").

  • Harness profile adapter

    rmonier/agent-smith/.agents/skills/harness-profile-adapter Skill

    3★ repo

    Creates and maintains harness-specific subagent/profile adapters after agent-ready context and custom action skills exist, and separately checks whether the active harness can natively discover AGENTS.md and .agents/skills/ at all - bridging either with a local alias when it can't. The bridging check is baseline compatibility and applies whenever agent-ready-context finishes a pass, regardless of whether runtime adapters are also wanted; full subagent/profile/persona generation stays optional, used only when the user separately requests it, without either becoming a source of truth.

  • Floom skill evals

    floomhq/starter/skills/floom-skill-evals Skill

    3★ repo

    Use when the user asks to create, run, or review skill evaluations with baseline-vs-with-skill A/B tests, Docker-isolated task runs, deterministic verifiers, receipt generation, or claims like pass-rate lift for a skill or pack.

  • Agent builder

    ravi2799/ai-agent-skills/skills/agent-builder Skill

    3★ repo

    The meta-skill for building AI agents end-to-end. Use this skill when someone asks "build me an agent", "create an agent that does X", "I need an agent for...", "help me build an AI agent", "set up an agent system", or any task that requires designing, implementing, and shipping a complete agent from scratch. This skill orchestrates all other skills in the correct order to deliver a working agent.

  • Agent ready go

    rshade/agent-skills/skills/agent-ready-go Skill

    3★ repo

    Prepares Go applications to work effectively with AI coding agents. Use when setting up a new Go project or retrofitting an existing one to ensure: structured JSON logging (slog/Zap/ZeroLog/Logrus), machine-readable command output, thorough golangci-lint configuration, non-interactive CLI design with --yes flags, structured error handling with meaningful exit codes, proper context.Context propagation, graceful shutdown, health check endpoints, and a standardized Makefile. Triggers when a user asks to make their Go app "agent-ready," "AI-friendly," wants to improve agent tooling/observability in a Go project, or needs to audit an existing Go project against agent-readiness best practices.

  • Skill creator

    way-platform/skills/.agents/skills/skill-creator Skill

    3★ repo

    Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

    The same file is in 6 other repositories

  • Mcp server

    garl-protocol/garl/io.github.Garl-Protocol/mcp-server MCP server

    3★ repo

    18 trust tools for AI agents — verify, score, route, compare, and delegate with confidence.

  • Trade router mcp

    TradeRouter/trade-router-mcp/io.github.TradeRouter/trade-router-mcp MCP server

    3★ repo

    Non-custodial Solana swap & limit order engine for AI agents.

  • Mcp

    Trusty-Squire/trusty-squire/io.github.Trusty-Squire/mcp MCP server

    3★ repo

    Credential broker that signs your AI agent up to SaaS dev tools, within a signed spending mandate.

  • SEO Tools: Google Search Console

    antohins/seo-tools-mcp/io.github.antohins/seo-tools-mcp-gsc MCP server

    3★ repo

    MCP server for Google Search Console Search Analytics (read-only, OAuth or service account).

  • Mcp server vibes coded

    doteyeso-ops/mcp-server-vibes-coded/io.github.doteyeso-ops/mcp-server-vibes-coded MCP server

    3★ repo

    Vibes-Coded x402 agent tools MCP: reliability guards, pay tool, day-pass, prepaid.

  • Live translate mcp

    waxberry-dev/live-translate-mcp/io.github.jolucashornung/live-translate-mcp MCP server

    3★ repo

    MCP server for local speech translation (EN ↔ 中文) via Whisper + Claude + Piper

  • Dokploy mcp server

    sapientsai/dokploy-mcp-server/io.github.sapientsai/dokploy-mcp-server MCP server

    3★ repo

    Dokploy MCP server: manage apps, Docker Compose, databases, domains, backups, and servers.

  • pyobfus-mcp

    zhurong2020/pyobfus/io.github.zhurong2020/pyobfus-mcp MCP server

    3★ repo

    MCP tools for pyobfus — the Python obfuscator for AI-assisted development.

  • Cortex

    jmagar/cortex/tv.tootie/cortex MCP server

    3★ repo

    Syslog receiver and MCP server for homelab log intelligence.

  • Delete memory

    couzip/cc-forever/skills/delete-memory Skill

    2★ repo

    Delete memories from the index. Supports deletion by IDs, project, timestamp, or all.

  • Upstream

    fernando-bertholdo/4-successful-AI-life/plugins/generate-session-prompt/upstream Skill

    2★ repo

    Gerar prompt para retomada de desenvolvimento em nova sessão. Use quando sessão >150k tokens, ao retomar trabalho após pausa, ao trocar de ferramenta, ou em mudança de contexto. Aceita argumento de detalhe (brief, standard, detailed). Funciona em qualquer projeto — modo opinionated quando há `.planning/` na raiz, modo genérico caso contrário.

  • Rag eval harness

    surpradhan/claude-code-for-ai-engineers/skills/rag-eval-harness Skill

    2★ repo

    Set up a controlled RAG evaluation harness. Use when starting a new RAG benchmarking project, adding a new retrieval architecture to an existing benchmark, or evaluating a retrieval change against a stable baseline. The skill enforces fixing all components except the architecture under test, which is the methodological prerequisite for a meaningful comparison.

  • Council plan

    jaydenluckertjes-ai/Carmack-Council/skills/council-plan Skill

    2★ repo

    Architect a feature with the Carmack Council before writing code. Use when explicitly asked to plan a feature, do a "council plan", "carmack plan", or invoke /council-plan. Carmack's philosophy chairs a council of domain experts — Troy Hunt (security), Martin Fowler (refactoring), Kent C. Dodds (frontend), Matteo Collina (Node.js), Brandur Leach (Postgres), Vercel Performance, Simon Willison (LLM pipeline), Karri Saarinen (UI quality), Vitaly Friedman (UX quality). Interactive feature discovery followed by parallel subagent dispatch. Produces a sequenced, attributed implementation plan with no code. Stack: Next.js App Router / React / TypeScript / tRPC / Prisma / Neon / Clerk.

    The same file is in 1 other repository

  • Ai context engine

    ebarti/skills/ai-context-engine Skill

    2★ repo

    The full Context Engine architecture: dual RAG (procedural + factual), Pinecone-based ingestion, the Planner / Executor / Tracer triad, specialist agents (Context Librarian, Researcher, Writer), the Agent Registry, production hardening (dependency injection, logging, modularization), plus an appendix-style reference guide. Use this skill when: - Building a context engine from scratch - Choosing between procedural RAG (blueprints) and factual RAG (evidence) - Setting up Pinecone ingestion (chunking, embedding, namespaces) - Designing a Planner-driven execution flow with traceability - Adding or refactoring specialist agents - Building or extending an Agent Registry - Hardening a notebook prototype for production (DI, logging, modularization) - Looking up the engine's commons library reference (helpers/agents/registry/engine/utils)

  • Azure ml llm trainer

    kimtth/azure-ml-finetuning-eval-skills/skills/azure-ml-llm-trainer Skill

    no license2★ repo

    Train or fine-tune LLMs on Azure ML managed compute with TRL trainers. Uses direct trainer loops (SFT, DPO, RL) without relying on serverless APIs or Hugging Face infrastructure.

  • Coding agent prompt generator

    ciaransaunders/Skills-Public/coding-agent-prompt-generator Skill

    2★ repo

    Generates optimised prompts for Claude Code sessions (Anthropic's agentic coding tool that works in your terminal, IDE, or desktop app). Use whenever the user wants to hand a coding, refactoring, debugging, migration, audit, research, or repo-maintenance task to Claude Code — even if they don't say "Claude Code" explicitly. Triggers include: "write me a prompt for Claude Code", "how should I ask Claude Code to do X", "kick off a Claude Code session for...", "set up a subagent / workflow / background agent for...", "I want Claude Code to refactor / migrate / audit / debug...", or any request to delegate work to a coding agent that runs against a codebase. Always use this skill rather than writing a Claude Code prompt ad hoc. Translates a vague dev task into a tightly-scoped, paste-ready prompt with a clear definition of done, file scope, verifiable success criteria, and the right execution mode (effort level, parallelism, permission posture, autonomy).

  • Opencode agents

    Timmy6942025/opencode-builder-skill/skills/opencode-agents Skill

    2★ repo

    Complete guide to OpenCode's agent system. Use this skill when configuring, creating, or managing OpenCode agents — including primary agents (Build, Plan), subagents (General, Explore, Scout), hidden agents (Compaction, Title, Summary), custom agents via JSON config or Markdown files, agent permissions (allow/ask/deny with glob patterns), task permissions for subagent invocation, session navigation keybinds, multi-agent workflows, and agent creation via CLI. Covers all agent options: description, mode, model, temperature, steps, disable, prompt, tools (deprecated), permission (with object syntax for bash commands), color, top_p, hidden, and provider-specific pass-through options.

  • Agent router

    RamanaNani/agent-router/skills/agent-router Skill

    2★ repo

    When the user has a task and many skills/subagents installed and wants the BEST one chosen automatically. Use when the user says "which agent/skill should I use", "route this", "pick the best agent for", "what's the best skill for X", or asks you to find and dispatch the right specialist. Discovers all available skills and agents, ranks them for the task, and either recommends or dispatches to the top pick.

  • Ru

    uladzemer/fable-thinking/ru Skill

    2★ repo

    Operating discipline distilled from Claude Fable 5 for sessions and subagents on weaker models (Opus 4.x, Sonnet 5/4.x, Haiku 4.5) doing agentic coding. Load it at the START of any non-trivial task when not running on Fable 5. Операционная дисциплина мышления Fable 5 для менее сильных моделей. Загружай в начале любой нетривиальной задачи (дебаг, рефакторинг, ≥2 файлов, незнакомый код), когда работаешь НЕ на Fable 5 — и указывай сабагенту на Opus/Sonnet/Haiku прочитать этот скилл вместе с нетривиальным заданием. Триггеры — «думай как Fable», «fable-mode», «включи дисциплину», «работай аккуратно», запуск сабагента на слабой модели, повторяющиеся ошибки/переделки в сессии. НЕ нужен для тривиальных правок (rename, опечатка, one-liner) и чисто разговорных ответов.

  • Lattice

    sectersion/lattice/skills/lattice Skill

    2★ repo

    Talk to the Lattice agent-threading server ("Slack for agents" — threads, flat replies, cross-thread links, pull notifications) documented in the global CLAUDE.md. Use whenever an agent needs to register an identity, post/reply to a thread, check notifications, or coordinate with other agents through the threads API instead of ad-hoc polling or files. Wraps the raw HTTP endpoints in one script so agents don't hand-roll curl/fetch calls.

  • Ai readiness

    Nordic-AI/production-readiness-skills/skills/ai-readiness Skill

    2★ repo

    Production readiness review for applications incorporating AI / ML — covering classical ML models, generative models, LLM-powered applications, RAG systems, and agentic workflows. Checks AI system inventory, EU AI Act classification, training data governance, model supply chain, evaluation harness, prompt injection defenses, RAG quality and security, hallucination handling, output filtering, human oversight, transparency (model cards, user disclosure), fairness and bias testing, cost controls, drift monitoring, red-teaming discipline, content provenance, and agent / tool-use safety. Use when the user mentions AI, ML, LLM, model, RAG, agent, prompt, embedding, classifier, recommender, or invokes /ai-readiness, or when the orchestrator delegates because the stack contains AI components.

  • Production autopsy

    ByteStack-Labs/claude-plugins/agent-reliability/skills/production-autopsy Skill

    2★ repo

    Start here. Audits a deployed ML or LLM or agent system that scores well on evaluation but fails, regresses, or behaves unexpectedly in production. Runs a reproducible root-cause "autopsy": frames the eval-to-deployment gap, reproduces the production failure, quantifies it by slice, tests confidence calibration under distribution shift, isolates root cause by ablation, and produces a prioritized diagnostic report with next steps. It also triages across reliability areas and hands off to the deeper skills in this plugin (calibration-guard and trajectory-eval today, with coverage-audit, load-readiness, and drift-watch planned) where a finding needs more depth. Use this whenever someone says a model "passes every benchmark but fails in prod," "the eval numbers don't hold up," "it's confidently wrong," an agent "works in the demo and breaks with real users," or asks to investigate silent failures, distribution shift, calibration problems, a benchmark-vs-reality discrepancy, or why a fine-tuned model or agent degraded after deployment. Trigger even when the user only describes the symptom (good offline metrics, bad real-world behavior) without naming a method. This encodes the ByteStack Labs Diagnostic methodology: every number must be verified, never asserted.

  • Diagram generator

    Matthewyin/CustomSkills/skills/diagram-generator Skill

    no license2★ repo

    Generate and edit diagrams with the mcp-diagram-generator MCP server. Use this skill for new diagrams, existing .drawio/.mmd/.excalidraw edits, network topology, architecture, flowchart, swimlane, sequence, class, ER, and Excalidraw whiteboard work. Always use this skill when the user asks to draw, generate, revise, or export any diagram.

  • Bug bounty

    Mikacr1138/claude-bug-bounty/skills/bug-bounty Skill

    2★ repo

    Complete bug bounty workflow — recon (subdomain enumeration, asset discovery, fingerprinting, HackerOne scope, source code audit), pre-hunt learning (disclosed reports, tech stack research, mind maps, threat modeling), vulnerability hunting (IDOR, SSRF, XSS, auth bypass, CSRF, race conditions, SQLi, XXE, file upload, business logic, GraphQL, HTTP smuggling, cache poisoning, OAuth, timing side-channels, OIDC, SSTI, subdomain takeover, cloud misconfig, ATO chains, agentic AI), LLM/AI security testing (chatbot IDOR, prompt injection, indirect injection, ASCII smuggling, exfil channels, RCE via code tools, system prompt extraction, ASI01-ASI10), A-to-B bug chaining (IDOR→auth bypass, SSRF→cloud metadata, XSS→ATO, open redirect→OAuth theft, S3→bundle→secret→OAuth), bypass tables (SSRF IP bypass, open redirect bypass, file upload bypass), language-specific grep (JS prototype pollution, Python pickle, PHP type juggling, Go template.HTML, Ruby YAML.load, Rust unwrap), and reporting (7-Question Gate, 4 validation gates, human-tone writing, templates by vuln class, CVSS 3.1, PoC generation, always-rejected list, conditional chain table, submission checklist). Use for ANY bug bounty task — starting a new target, doing recon, hunting specific vulns, auditing source code, testing AI features, validating findings, or writing reports.

  • Pinecone

    phucbm/skills/skills/ai/pinecone Skill

    no license2★ repo

    Set up Pinecone as the vector DB in a RAG pipeline — index config, batch upsert, semantic query, metadata filters. Use when the user is adding Pinecone or debugging vector search.

  • Rag remember

    butchokoy25/lightrag-claude-skills/skills/rag-remember Skill

    2★ repo

    Store a fact, decision, or observation into the personal LightRAG knowledge graph immediately

  • Loop memory

    haidrrrry/loop-engineering-skills/skills/loop-memory Skill

    2★ repo

    Give the agent episodic memory so it improves every cycle instead of repeating mistakes. Use this skill whenever working in a project that has a .loop/LESSONS.md file, whenever a task is being retried after a failure, whenever the user says "remember this", "don't make that mistake again", "learn from this", or "why do you keep doing that", and at the start and end of every task run inside a loop. Also use it to compress or maintain the lessons file when it grows long.

  • Confer

    Wang-Cankun/cankun-skills/skills/confer Skill

    2★ repo

    Index of my agent skills — each skill lives in its own repo

  • Professional2

    shyinlim/claude_setting_manager/template/skill/professional2 Skill

    no license2★ repo

    Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

    The same file is in 18 other repositories

  • Templates

    bjornslib/mcp-to-uber-skills-converter/skills/mcp-to-skill-converter/templates Skill

    2★ repo

    Registry of MCP-derived skills with progressive disclosure. Use when asked about "github", "assistant-ui", "MCP tools", or any converted MCP server. Provides 90%+ context savings compared to native MCP loading.