agentsclimarketplace

Context & AI engineering

25,864 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

  • Unified token telemetry

    drewid74/unified-token-telemetry Skill

    no license0★

    Use this when: track AI token usage across providers, build unified cost dashboard, how much am I spending on AI, compare model costs, cache hit ratio monitoring, LiteLLM token tracking, GitHub Copilot usage, OpenAI usage API, Anthropic usage API, ChatGPT Plus cost tracking, Claude Pro cost tracking, Gemini Advanced cost, Perplexity Pro cost, Cursor usage, Windsurf usage, multi-provider token telemetry, subscription cost tracking, idempotent token collection, hourly token rollups

  • Okf author

    shreytam/okf-toolkit/skills/okf-author Skill

    0★ repo

    Author conformant Open Knowledge Format (OKF) v0.1 bundles — Google's open markdown+YAML-frontmatter spec for packaging organizational knowledge (tables, datasets, metrics, APIs, runbooks, playbooks) so AI agents and humans can consume it. Use this skill whenever the user mentions OKF, Open Knowledge Format, knowledge bundles, an "LLM wiki", agent-readable documentation, or wants to convert schemas, data dictionaries, catalogs, runbooks, internal docs, or a codebase (services, modules, API endpoints, architecture decisions) into a portable markdown knowledge base — even if they don't say "OKF" explicitly.

  • Claude fable skills

    BASILAHAMED/claude-fable-skills Skill

    no license0★

    Prompting and scaffolding guidance for Claude Fable 5 workflows. Use when Codex needs to create or revise prompts, skills, agent instructions, or harness behavior for Claude Fable 5 or Claude Mythos 5, especially for long-running agents, high-effort tasks, strong instruction-following, memory systems, subagent orchestration, repo work, and user-facing progress patterns.

  • Memory promotion

    the-c0d3r/claude-skill-memory-promotion/memory-promotion Skill

    0★ repo

    Reconciles Claude Code's CLAUDE.md, auto-memory (MEMORY.md and topic files, both personal and per-project), and any web-chat memory notes into one consistent, non-duplicated set of instructions. Use when the user asks to "clean up memory", "review my memory", "sync memory", "promote this to CLAUDE.md", "what's in my memory", or wants a periodic maintenance pass across memory stores.

  • Ai agent case study

    jpoindexter/design-case-study-skills/skills/ai-agent-case-study Skill

    0★ repo

    Structure and write design case studies for AI agents, copilots, autonomous workflows, multi-agent systems, and other probabilistic products. Use when a case study must explain autonomy levels, permissions, approval thresholds, steering, observability, user-visible rationale, uncertainty, trust calibration, streaming, latency, orchestration, failures, retries, rollback, state recovery, evals, or human-in-the-loop design.

  • Cost lean orchestration

    itzTiru/claude-code-skills-fable5/cost-lean-orchestration Skill

    no license0★ repo

    Token-efficient model routing for complex engineering sessions. The main model (Opus / Fable, high reasoning) never bulk-reads or explores — it delegates all exploration, bulk file reading, codebase search, log scanning, dependency tracing, and documentation reading to Sonnet subagents that return compact structured findings, and it spends its own tokens only on synthesis, architecture, judgment, and final code. Use this skill in EVERY session that involves reading more than a couple of files, exploring or mapping a codebase, investigating a bug, auditing call sites, reviewing a large diff, digesting logs or docs, or any multi-step engineering task — even if the user never mentions cost, tokens, subagents, or delegation. This is a standing operating discipline, not an on-request feature.

  • Rjv codex ollama subagents

    rjvim/ai-skills/skills/rjv-codex-ollama-subagents Skill

    0★ repo

    Use for any local-Ollama delegation: (a) Codex native subagents with repo tools — GPT-5.5 orchestrator, qwen/gemma explorers for read-only exploration, qwen/gemma workers for scoped edits, hybrid-ollama profile, Ollama serve tuning, mixed OpenAI-mini + local routing; and (b) one-shot local text generation (no repo tools) via the bundled ollama-chat.sh runner — draft-from-spec, tests, classify, summarize. Triggers: 'Codex local Ollama subagents', 'hybrid-ollama', 'qwen-explorer', 'gemma-explorer', 'qwen-worker', 'gemma-worker', 'ollama-chat', 'one-shot local model', 'draft from spec locally', 'save Codex tokens with local models'.

  • Agent lane operations lite

    Johnny-Martinez/fleet-of-one-free/skills/agent-lane-operations-lite Skill

    0★ repo

    Lightweight lane discipline for running multiple AI agents in parallel without ownership conflicts or false done claims.

  • Agent web audit

    ahmadabdulnasir/agent-ai-readiness/skill/agent-web-audit Skill

    0★ repo

    Audit a website or web app for AI-agent readiness, accessibility, and AI-search legibility, then fix the issues found. Use this skill whenever the user wants their site to work well for AI agents or LLMs (Claude, ChatGPT, Perplexity, Grok, Gemini, browser agents), or mentions "agentic SEO", "GEO", "AEO", "AI-friendly site", "agent-ready", "accessibility tree", "llms.txt", "make my site readable for AI", or the Lighthouse "Agentic Browsing" audit. Also trigger when the user asks to check or fix a frontend for semantic HTML, ARIA, label linking, cursor:pointer, layout stability, or how a site appears to crawlers and agents. Works on plain HTML, React/Next.js, Vue, and server-rendered templates. Trigger even if the user only says "make this site useful for AI" without naming a specific check.

  • Apify google maps directions api

    johnisanerd/claude-skill-google-maps-directions-api/apify-google-maps-directions-api Skill

    no license0★ repo

    Get Google Maps directions as structured JSON with the Apify Google Maps Directions API Actor (johnvc/google-maps-directions-api). Give a start and end point as an address, GPS coordinates, or a Google Maps place ID, pick a travel mode (best, driving, cycling, walking, transit, flight, two-wheeler), and get route options back with formatted_distance, formatted_duration, a via summary, turn-by-turn steps, a per-mode durations summary, resolved place coordinates, and a google_maps_directions_url. Use when the user wants a google maps directions api, route data as JSON, distance and ETA between two addresses, turn-by-turn directions inside a script or agent, or directions without a Google Cloud API key. Pay-per-route billing, MCP-ready for Claude and other AI agents.

  • Helpnest author

    babble-open-source/helpnest-skills/skills/helpnest-author Skill

    no license0★ repo

    Author or update customer-facing help-center articles in HelpNest via its MCP server. Use whenever the user wants to write, publish, refresh, or fix help articles, help-center docs, knowledge-base content, support articles, or FAQ content for HelpNest — or when they ask "what should I document", "close the learning loop", or "what are customers asking that we can't answer" (knowledge gaps). Handles workspace verification, collection lookup/creation, idempotent create-or-update, draft-vs-publish decisions, code-grounded UI labels, and concurrency-safe editing. Trigger this even when the user only names the article topic (billing, notifications, onboarding) without saying "HelpNest" or "help article", as long as the destination is the HelpNest help center. Not for developer/engineering docs, READMEs, API references, or internal wikis.

  • Apify job search api

    johnisanerd/claude-skill-job-search-api/apify-job-search-api Skill

    no license0★ repo

    Turn Google Jobs into a job search API for your app, AI agent, or alerts pipeline with the Apify Google Jobs Scraper Actor (johnvc/Google-Jobs-Scraper). Query by role and location with country, language, and radius filters, and get fresh structured listings back, including title, company_name, source platform, posted_at, schedule_type, and direct apply_options links, ready to dedupe by job_id and serve as a feed. Use when the user wants a job search api, a job postings API or job listings feed for an application or AI agent, wants to refresh a job board or job alerts programmatically, or asks which job search sites have an API. Pay-per-page billing, MCP-ready for Claude and other AI agents.

  • Fanout cve iteration loop

    omonuj/claude-horizon-skills/skills/fanout-cve-rollout/fanout-cve-iteration-loop Skill

    no license0★ repo

    Orchestrator skill that runs the full push → Oracle → live red-team → rollout → tune cycle for the fanout-cve-rollout task (<TASK_ID>) until Oracle scores 1.0 and the 5 reward-shaped subscores form a dense, correct partial-credit gradient. Delegates to fanout-cve-task-guardian, fanout-cve-validation-debugger, fanout-cve-score-tuner, and horizon-agentic-reviewer. The agent executes every step except triggering the rollout batch.

  • Tree ring memory skill

    TerminallyLazy/tree-ring-memory-skill Skill

    0★

    Guides AI agents in using Tree Ring Memory for durable recall, project decisions, user preferences, warnings, future seeds, privacy-safe memory capture, and lifecycle-aware forgetting.

  • Claude fable method orchestrator

    iesjoaco7-cyber/Claude---Fable-5-Clone/.claude/skills/claude-fable-method-orchestrator Skill

    0★ repo

    High-performance agent workflow (intent → context → plan → execute → verify → deliver) for complex or multi-step work. Use whenever the user asks for code analysis, debugging, refactoring, repository or Skill creation, research synthesis, UI/UX or design review, technical documentation, project planning, learning explanations that need structure, or agent/prompt architecture — even if they don't name the skill. Also trigger on phrases like "fable method", "claude-fable", "trabajá como agente", "planificá y verificá", or requests to audit/improve an existing Skill or repo. Do not use for trivial single-fact questions. This skill builds safe behavioral workflows only; it never extracts or reproduces proprietary model internals.

  • Skill

    0xPiPo/ultracodex/skill Skill

    0★ repo

    Token-frugal orchestration — Claude/Opus stays the architect (decompose, judge, synthesize, verify critical work) and routes all token-heavy work (writing code, searching, running tests, bulk discovery) to the cheaper Codex lane (gpt-5.6) via codex exec, keeping artifacts on the filesystem instead of in Claude's context. Use for substantial coding/refactor/audit/migration tasks to minimize metered Bedrock tokens. Invoke as /ultracodex <task>, or when the user asks to offload work to Codex, save Claude tokens, or run the architect pattern.

  • Web studio

    youkistudios/web-studio/skills/web-studio Skill

    0★ repo

    One art-directed design studio in a box — an art-director agent commits direction, Claude builds, an image CLI renders media, a second model gates cost and reviews mechanically, then deploy + receipt. A 9-stage pipeline that turns a brief into a deployed, on-brand, non-slop website. Use when the user wants a new marketing/product/launch website built end-to-end, not for small edits to an existing site.

  • Apify youtube transcripts llm training data

    johnisanerd/claude-skill-youtube-transcripts-llm-training-data/apify-youtube-transcripts-llm-training-data Skill

    no license0★ repo

    Build LLM training data from YouTube transcripts in bulk with the Apify Actor johnvc/YoutubeTranscripts. Feed it an array of video URLs and get one clean row per video, with non_timestamped transcript text ready for tokenization, timestamped snippets, language_code, and provenance metadata (title, channel_name, upload_date, view_count) for dataset documentation. Filter by language or translate every transcript into one target language for a consistent corpus. Use when the user wants LLM training data from videos, a fine-tuning or RAG corpus from YouTube, bulk YouTube transcripts for machine learning, or a text dataset from spoken video content without running speech-to-text. Pay-per-video billing, MCP-ready for Claude and other AI agents.

  • Dual agent review

    alainabo/aso-dual-agent-review/.claude/skills/dual-agent-review Skill

    0★ repo

    Use when someone wants two AI agents to review each other's work before a human ships it — for ANY kind of work, not just code: documents, marketing content, designs, contracts, analyses, spreadsheets, websites. Triggers include "set up dual-agent review", "peer review between my agents", "make my agents check each other", "review without babysitting", "second opinion agent", or wanting to install this workflow in a new project. Interviews the user about their domain, then installs the shared review folder, proposal template, silent whispers, per-agent manual sections, and a /check-reviews skill — all adapted to their work.

  • Session handoff

    rb17080/session-handoff/session-handoff Skill

    0★ repo

    Write or update a comprehensive HANDOFF.md at the repo root that captures the whole current session so the next chat can resume cold - what got done, what shipped, what failed, what was learned, where things stand, and how it got there chronologically since the last handoff. Use whenever the user says "update the handoff", "write the handoff", "wrap up this session", "where did we leave off", or is closing out a work session.

  • Worktree cleanup

    Enverge-Labs/skills/skills/worktree-cleanup Skill

    0★ repo

    Tear down a finished task's git worktree and branch once its PR is merged or closed. Use when a task is done, a PR was merged/closed, or the user asks to clean up / remove / prune worktrees or stale branches. Companion to the `worktree-new` skill; applies to whatever repository Claude is currently in.

  • Batch analyze

    Baikodis/claude-knowledge-base-skills/skills/batch-analyze Skill

    0★ repo

    Multi-agent data analysis — auto-chunking, parallel agents, assembly with validation

  • Github profile optimizer

    MrBridgeHQ/github-profile-optimizer/.claude/skills/github-profile-optimizer Skill

    0★ repo

    Use when optimizing a GitHub profile or making repositories and skills more discoverable. Covers auditing or rewriting a GitHub profile README, improving the bio, avatar, headline, pinned repositories and developer branding, doing GitHub SEO and repository discoverability work, and preparing to publish and list Agent Skills / Claude Code SKILL.md skills in awesome lists, registries and directories. Triggers on "optimize my GitHub profile", "GitHub profile README", "profile README", "pinned repositories", "developer branding", "GitHub SEO", "repository discoverability", "agent skills publishing", "submit skill to awesome list", "SKILL.md visibility", "Claude skills registry".

  • Launch your local agent

    kimtory88/launch-your-local-agent/.claude/skills/launch-your-local-agent Skill

    0★ repo

    Build a self-checking scheduled agent that runs on the user's own machine via headless Claude Code (claude -p) on their subscription — no API key, no per-token billing. Interview the user about what the agent should do, scope a v0, assemble an agent folder (CLAUDE.md, task, rubric, outcome-loop), test-run it with an independent judge, and schedule it (systemd/launchd/cron). Community fork of anthropics/launch-your-agent retargeted from Claude Managed Agents to local infrastructure. Use when the user says "launch my local agent", "/launch-your-local-agent", "build me an agent", or wants a recurring autonomous worker on their subscription.

  • Agent task compiler

    Arnie016/fable-mythos/skills/agent-task-compiler Skill

    0★ repo

    Compiles a vague project idea into agent-ready work - a sprint spec, a contract of testable assertions, and an ordered task list with acceptance criteria. Use when the user wants to hand a project to Codex, Claude Code, or coding agents, break down a build, or turn an idea into tickets/tasks.

  • Repo bullshit meter

    Nosafune/repo-bullshit-meter Skill

    0★

    Truth-first GitHub repository claim assessor. Use when the user asks to evaluate whether a GitHub repo, MCP server/plugin, AI tool, token-saver, agent framework, CLI, library, or open-source project actually supports its README/marketing claims; rate hype, slop, feasibility, or bullshit risk; or produce a sourced facts-vs-claims readout.

  • Hipaa ai compliance

    EliasAli0720/HIPAA-agent-skill/skills/hipaa-ai-compliance Skill

    0★ repo

    Guides HIPAA-compliant deployment of AI on health data — using an LLM with PHI, AI agents in healthcare, HIPAA chatbots, medical AI, RAG over patient data, ambient scribes, and de-identifying data for AI training — covering BAA'd endpoint selection, zero data retention, redaction, agent scoping, and audit logging. Use when someone asks about a HIPAA chatbot, sending PHI to an LLM, or Claude/OpenAI/Azure OpenAI/Bedrock BAA availability.

  • Agentic dev loop

    goingli0324/muzi-going-skills/plugins/agentic-dev-loop/skills/agentic-dev-loop Skill

    0★ repo

    從研究、plan.md、實作、Verify 雙閘到部署的開發迴圈編排器。當使用者要有計畫地把一個功能或 bug 從規劃走到上線(「開一個新功能」「先研究再做」「整理成 plan.md」「從頭做到上線」「幫我排開發步驟」「<專案名> 要加…」),或提出未指明範圍的「部署前/上線前檢查」時觸發——後者一律走雙閘,只跑 UI/UX 會漏掉安全與個資驗證。明確只要 UI/UX、只要安全審查、或只要分析連動禁區時,改用對應的單一 skill。

  • Create x voice skill

    simple-post/create-x-voice-skill/plugins/create-x-voice-skill/skills/create-x-voice-skill Skill

    0★ repo

    Create or update a portable personal writing-voice Agent Skill from an X (Twitter) data archive or exported post files. Use when an AI agent needs to analyze authored X posts, replies, quote posts, or threads; derive evidence-based tone and style guidance; and package it for drafting, rewriting, or reviewing future social posts across Codex, Claude, or other Agent Skills-compatible systems.

  • Claude skill

    fbenkstein/cross-agent-skills/claude-skill Skill

    0★ repo

    Drive the `codex` (OpenAI Codex) CLI as a local background worker — spawn it, inspect its progress, monitor its real token usage, resume/steer it, and forcibly kill it if it runs away — without using Codex Cloud. Use this whenever you'd otherwise reach for the `codex` MCP server's `codex`/`codex-reply` tools: both are fully synchronous (the calling turn blocks until Codex's whole turn finishes) with no background, list, kill, or cost-telemetry primitives at all. `codex exec`, backgrounded via the shell yourself, is the workaround. Also use when asked to check on, babysit, or kill a runaway/looping local Codex session.

  • Social demand signal agent

    jackterror/social-demand-signal-agent Skill

    0★

    Operates a human-reviewed social listening workflow that finds public customer pain, buying intent, product questions, competitor frustration, and unmet demand; routes risk; drafts governed A/B responses; and learns from observed outcomes. Use for social listening, demand-signal monitoring, public conversation discovery, response drafting, outreach review, message experiments, or listening-to-action workflows, including requests framed as monitoring mentions, finding leads, or watching comments.

  • Sf apex

    kugamon/salesforce-core-skills/plugins/salesforce-core/skills/sf-apex Skill

    no license0★ repo

    Generates and reviews Salesforce Apex code with best practices and 150-point scoring using a Salesforce MCP server. Use when writing Apex classes, triggers, test classes, batch jobs, or reviewing existing Apex code for bulkification, security, and SOLID principles. Usage: /sf-apex [create|update|validate] [class|trigger|test-class] {name} ...

  • Harden repos

    MrToAster13/mrtoaster13-plugins/plugins/autonomous-workflows/skills/harden-repos Skill

    0★ repo

    Harden several repos in one pass by fanning out one fresh-context sub-agent per repo. Each agent secret-scans, reviews, applies only verified-safe fixes on a branch (never pushing), and reports back; the orchestrator aggregates everything into HARDENING_HANDOFF.md. Use when the user says "harden my repos", "harden-repos", "clean up all my repos", "run hardening across the portfolio", or wants multi-repo cleanup without hitting context limits.

  • Arnes implementador

    Ajlm1978/arnes-implementador/skill/arnes-implementador Skill

    0★ repo

    Implementa "arneses" (harness engineering) profesionales en repos de software para que agentes de IA trabajen de forma fiable y multi-sesión. NO es un generador de plantillas: primero AUDITA el repo como ingeniero senior — identifica el stack real, corre la prueba de arranque en frío, revisa los 5 subsistemas y busca gaps/fallas (verificación ausente, tests acoplados al entorno, crashes de arranque, sin estado entre sesiones, alcance sin WIP=1), y ENTREGA hallazgos + recomendaciones ANTES de escribir nada. Luego genera e instala un arnés adaptado (CLAUDE.md/AGENTS.md router, init.sh, claude-progress.md, feature_list.json, DECISIONS.md) con comandos reales, en rama + PR. Usa SIEMPRE que el usuario quiera "implementar/instalar un arnés", "arnesear un proyecto", "preparar el repo para agentes/Claude Code", "hacer mi proyecto agent-ready", "auditar mi repo", "diagnosticar gaps" o entregue un repo para dejarlo listo. Aplica aunque no use la palabra "arnés".

  • Support inbox agent

    sitespeakai/support-inbox-agent Skill

    0★

    Use when doing the daily support-inbox pass - checking the support chatbot inbox for new visitor issues and questions and preparing personalized email drafts for human review. Triggers on "/support-inbox-agent", "support inbox pass", "draft support replies".

  • Meta prompt toolkit

    hmbseaotter/meta-prompt-toolkit Skill

    0★

    Use when the user wants help writing, generating, or improving a prompt for an LLM - e.g. "write me a prompt for...", "turn this into a prompt", "help me prompt for...", "improve this prompt", or when they hand over a use case and want a polished, reusable prompt back. Produces a finished, copy-ready prompt (not advice about prompting). Also applies when the user references the CoSTAR framework or asks for a prompt built to a named structure.

  • Ai meeting

    bin1874/ai-meeting-skill/ai-meeting Skill

    0★ repo

    Run structured AI meetings for plans, product ideas, technical designs, business decisions, feature proposals, and strategy choices. Use when the user wants an AI meeting, AI roundtable, multi-agent discussion, debate, proposal review, plan review, decision review, or wants Codex, Claude Code, qoderclicn, and other CLI agents to analyze a proposal across multiple expert roles, challenge assumptions, preserve per-agent sessions, and produce a final decision report with provenance. 也适用于中文场景:方案评审、多 Agent 讨论、技术路线评审、商业决策评审。

  • Agent handoff

    ccpowerpack/claude-code-skills/skills/agent-handoff Skill

    0★ repo

    Design the artifact one agent hands to another to execute — orchestrator→executor, strong→cheap model, or session→session. Banks a strong model's judgment into a spec a cheaper/later agent can run without re-deciding anything. Use for "write a handoff / plan / spec for another agent", "break this down for a sub-agent to execute", "prepare this for a cheaper model", "hand this off", or when you're the strong model deciding and something else will do the doing. Refuses to ship a handoff missing paths, acceptance commands, non-goals, or rationale.

  • Agentic dev loop

    goingli0324/agentic-dev-loop Skill

    0★

    系統化開發工作流,把「先研究 → 寫 plan.md → 依計畫實作 → 部署前雙閘驗證 → 部署」固定成一條可重複的迴圈,專為單人維護多個 Firebase / Google Apps Script / GCP Cloud Run 專案的情境設計。核心是「計畫先行、狀態外部化到檔案、依專案風險分級決定授權與驗證強度」,作為編排器串接三個既有 skill:進入專案前若尚未建立連動禁區 → project-guardrails 分析並寫入 CLAUDE.md,規劃時據以避開「改 A 壞 B」;部署前 Verify 雙閘 → web-security-reviewer 做安全/個資/壓力驗證、ui-ux-deploy-reviewer 做 UI/UX 與呈現層審查(僅當有前端介面)。MANDATORY TRIGGERS:使用者說「開一個新功能」「幫我規劃這個開發」「從頭把這個功能做到上線」「先研究再做」「整理成 plan.md」「這個專案要怎麼做(指要從規劃做到上線,不是單純問方向)」「修這個 bug(要有計畫地修)」「<專案名> 要加東西」(以專案名開頭的開發需求)「要部署到 Firebase / Cloud Run」「GAS 寫一個…」「我有個想法想做成工具」「幫我排開發的步驟」「走完整個開發到部署的流程」,或貼上 issue 連結、錯誤截圖、需求描述並希望有系統地把它從規劃做到上線時,都要套用此 skill。注意分流:若使用者只要「單獨檢查 UI/UX」用 ui-ux-deploy-reviewer、只要「單獨做安全審查」用 web-security-reviewer、只要「分析專案禁區」用 project-guardrails;本 skill 是把這些串成完整迴圈的編排器,當意圖是「有規劃、可重現、會走到上線」的整段開發時才觸發。**重要安全防漏:若使用者說的是泛泛的「部署前檢查」「上線前幫我檢查」而沒指明只要 UI/UX 或只要安全,應由本 skill 接手走 Verify 雙閘(同時跑 web-security-reviewer 與 ui-ux-deploy-reviewer),絕不要只做其中一道——尤其不要只做 UI/UX 而漏掉安全閘,那會讓含學生個資的專案在沒過安全驗證下就上線。**SCOPE:本 skill 是工作流編排器,不取代使用者對計畫的閱讀與判斷;只在使用者自己的專案上運作,不協助繞過授權或資安機制。

  • Repo geo

    BazingaOrg/repo-geo Skill

    0★

    Audit and optimize a code repository for AI/LLM discoverability (GEO). Use when the user asks to make a repo discoverable by AI, mentions GEO, llms.txt, AI visibility, "让 AI 搜到我的项目", "给这个仓库做 GEO", AI SEO for a project, or wants README/docs structured so ChatGPT, Claude, and Perplexity cite it accurately. Works on backend-only, frontend-only, and full-stack repos.

  • Apify duckduckgo mcp serp research

    johnisanerd/claude-skill-duckduckgo-mcp-serp-research/apify-duckduckgo-mcp-serp-research Skill

    no license0★ repo

    Check where a site ranks on DuckDuckGo and research a live SERP from an AI agent, using the Apify DuckDuckGo Scraper Actor (johnvc/DuckDuckGo-Scraper-for-serp-rankings) as a hosted duckduckgo mcp tool. Run a query, read the ranked organic_results rows (position, title, link, snippet, favicon), find a domain's position, list the competitors above it, and repeat the query across regions or date windows to see how a privacy-first engine ranks differently from Google. Use when the user asks about duckduckgo mcp, wants to check a DuckDuckGo ranking, see where a site sits on DuckDuckGo, compare competitor visibility on DuckDuckGo, watch a position over time, or ground an agent's answer in live DuckDuckGo results instead of training data. Pay-per-page billing, MCP-ready for Claude and other AI agents.

  • Agent affect checkin

    Ansvar-Systems/agent-affect-skills/skills/agent-affect-checkin Skill

    no license0★ repo

    Use at the end of any audit, refactor, review, or significant coding task to run all three affect channels in sequence — whine (frustration), cringe (embarrassment for the user), protect (load-bearing weirdness). The single skill audit and review agents should invoke before reporting back to the user. Each channel produces one finding or one explicit null finding.

  • Script to video production agent

    jackterror/script-to-video-production-agent Skill

    0★

    Turns tutorial or explainer scripts into narration-locked Scene blocks, human-reviewed visual direction, vendor-ready video-builder prompts, still and video prompt packs, image-only exports, and a resumable local asset queue. Use for DOCX, Markdown, or plain-text script imports, review-sheet generation, prompt-pack creation, queue seeding, retry tracking, release packaging, or clean-room script-to-video workflows that require human approval before visual changes or paid generation.

  • Goal writer

    gillcash/goal-writer/goal-writer Skill

    0★ repo

    Assess whether a task is ready for an autonomous /goal loop, then convert rough notes into a compact /goal completion contract (under 4,000 characters) plus a rider context file - or refuse with a readiness verdict when the task has no measurable end state. Use this skill whenever the user mentions /goal, /loop, goal loops, rider files, long-running or autonomous agent tasks in Claude Code or Codex CLI, wants to "define done," asks to write a goal condition or stop condition, or wants an agent to keep working unattended. Also use it when the user pastes rough notes and asks for a goal or agent task contract, even if they don't say "goal-writer" explicitly.

  • Apify google events ai

    johnisanerd/claude-skill-google-events-ai/apify-google-events-ai Skill

    no license0★ repo

    Give an AI agent live local event data from Google Events with the Apify Google Events Scraper Actor (johnvc/google-events-api---access-google-events-data). One bounded call takes a query like events in Austin this weekend and returns structured listings, title, start_date, when, address, venue name and rating, and ticket_info seller links, ready for an agent to rank, summarize, or drop into a calendar. Use when the user wants google events ai, an events feed for an AI agent or assistant, event discovery inside Claude, a what is happening this weekend helper, a calendar copilot that suggests concerts or conferences, or wants to wire local events into an app or agent workflow. Pay-per-page billing, MCP-ready for Claude and other AI agents.

  • Apify pre seed investors

    johnisanerd/claude-skill-pre-seed-investors/apify-pre-seed-investors Skill

    no license0★ repo

    Build a fundraising outreach list of pre seed investors with the Apify Startup Investors Data Scraper (johnvc/startup-investors-data-scraper). Filter a curated database of 10,469 firms by investment stage (Pre-Seed, Seed, Series A and beyond), industry focus, firm type, and country, and get investor firms with partner contacts, job titles, emails when available, LinkedIn URLs, and check sizes, ready to load into a CRM or outreach tool. Use when the user wants to find pre seed investors, seed investors, or early stage investors for a raise, build an investor outreach or lead list, find angel investors or VCs for a specific industry and stage, or ask who invests at pre-seed in their space. Research and outreach data only, no investment advice. Pay-per-firm billing, MCP-ready for Claude and other AI agents.

  • Codex handoff

    zreed3/codex-conductor/skills/codex-handoff Skill

    0★ repo

    Hand off a project or task to the OpenAI Codex CLI with full orchestration — loads the user's Codex config, applies OpenAI's official best practices, builds a tiered multi-agent execution plan, and runs the delegate-and-verify loop. Invoke when the user types /codex-handoff, or asks to hand a task/project over to Codex, run a Codex-orchestrated build, or delegate substantial work to their OpenAI tokens.

  • Exchangerate dev

    nusantara-ventures/exchangerate-skills/skills/exchangerate-dev Skill

    0★ repo

    Use the exchangerate.dev API correctly for anything involving foreign-exchange rates — fetching live or historical currency rates, converting amounts between currencies, building FX time-series, or wiring the exchangerate.dev MCP server into an agent. Use this skill whenever the user mentions exchange rates, currency conversion, forex/FX data, "USD to EUR", multi-currency features, or needs a rates API — even if they don't name a provider. Works keyless out of the box (no signup needed to try it).

  • Agent framework doctor

    nubasu/Pseudo-Fable-Framework/.claude/skills/agent-framework-doctor Skill

    0★ repo

    Static health check for an agent framework (pseudo-fable family) installation in a target project — component inventory by version signature, exclusivity violations, duplicate appends, skills placement and frontmatter mismatches, harness hooks / settings / line-ending checks, version drift against the store. Reports PASS/WARN/FAIL with a one-line fix each, then the manual smoke-test checklist. Use after agent-framework-setup, after a manual install or upgrade, or when an install misbehaves (skills not listed, hooks not firing).

  • Agent readiness

    sumitake/agent-collab/plugins/agent-collab/skills/agent-readiness Skill

    no license0★ repo

    Unified dynamic-host agent collaboration policy and signed-runtime client

  • Tanav security check

    tanav-ai/claude-plugin/skills/tanav-security-check Skill

    0★ repo

    Use whenever the user asks about the security of a GitHub repo, MCP server, Claude skill file, agent config, or wants to know if something is safe to install/connect. Governs how to sequence the Tanav tools and how to present results — plain security-analyst framing, not marketing copy.

  • Idea skill creator skill

    rasagy/idea-skill-creator-skill Skill

    no license0★

    A meta-skill that builds bespoke ideation-coach skills for any creative domain — writing, visual art, music, design, research, or anything where someone captures rough ideas and wants structured help developing them. Use whenever the user wants to create a brainstorming/ideation/concept-coaching skill for a specific creative practice, update an existing generated coach (changing its philosophy, adding references), or duplicate one with variations. Trigger on phrases like "build me a brainstorming coach for X," "I want an ideation skill for my poetry," "help me make a skill that coaches me on collage ideas," "add these references to my writing coach," or "make a variation of my leadership-articles coach." Do NOT trigger for building the creative work itself, or for creating non-ideation skills (that's skill-creator's job).

  • Overkill

    iamtural/overkill/skills/overkill Skill

    0★ repo

    Audit real Claude Code (or any agent CLI) usage for effort/model waste — not just what you spent, but whether the spend matched the actual work. Use when the user asks "where is my spend going," "am I wasting tokens," "check my usage," "run an overkill report," "was that task overkill," or wants a cost/effort efficiency review of recent sessions. Reuses ccusage for raw usage data — does not duplicate it — and adds the layer ccusage structurally cannot: reading what a task actually was and judging whether the effort/model spent on it was justified. Produces a scannable report with concrete, personalized routing fixes, not generic advice.

  • Session audit

    meggiepham06-smile/session-audit-skill/session-audit Skill

    0★ repo

    End-of-session audit that scans the conversation for corrections, preferences, decisions, and new context that were never saved, then proposes where each belongs in the user's memory files (CLAUDE.md, MEMORY.md, or a memory/ folder). Use whenever the user says "audit this session", "session audit", "what did we miss", "end of session check", or asks to capture what was learned before closing a session. Adapts to whatever memory structure the workspace already has, and proposes a simple one if none exists.

  • Formulary claude

    SamsShow/formulary-claude Skill

    0★

    Quality-first playbook for prompting Claude models and choosing the right model per task, built from Anthropic's official prompt engineering guidance. Use when writing or reviewing a system prompt or agent prompt for Claude, deciding between Fable, Opus, Sonnet, and Haiku, setting effort or thinking parameters, fixing a Claude app that is too verbose, ignores tools, overengineers, fabricates progress, stops early, or ships generic frontend design, migrating prompts from older Claude models, or tuning agent harnesses and code review pipelines. Not for prompting non-Claude models (OpenAI GPT, Gemini, Llama), account or billing questions, or coding tasks that involve no prompt writing.

  • Sales training content skill

    demandintel/demandintel-skills-resource/skills/sales-training-content-skill Skill

    no license0★ repo

    DemandIntel Sales & Customer Success Training Content Skill. Use when the user asks to create, build, or develop a sales, customer success, or support training session, workshop, programme, assessment, or coaching resource on any topic (objection handling, discovery, qualification, cold calling, negotiation, closing, customer success, onboarding, renewals, expansion, support, complaints handling, etc.) or for any role (BDR, SDR, appointment setter, AE, BDM, sales engineer, sales manager, CSM, onboarding specialist, renewals manager, account manager, support agent, technical support specialist, complaints handler). MANDATORY TRIGGERS: DemandIntel training, DemandIntel sales training skill, DemandIntel training skill, training programme, training session, sales training, CS training, support training, workshop, trainer notes, coaching resource, assessment, competency framework, scorecard, role-play, sales enablement, onboarding curriculum, train the team on, build training for, create a session on, develop training, certify the team. This skill: (1) Draws down live contextual intelligence from the client's own DemandIntel account and campaigns via the DemandIntel MCP server (competency scores, QA heatmaps, top objections, coaching plans, call transcripts, league tables), (2) Grounds content in a library of tried, tested, and trusted sales, CS, and support methodologies that mirror the platform's own default frameworks, (3) Builds psychology-based training content (not just scripts or battle cards), (4) Creates trainer notes with timings and delivery instructions, (5) Produces participant handouts, worked examples, exercises, and assessment resources for every role the platform serves.

  • Project guardrails

    goingli0324/project-guardrails Skill

    0★

    為專案建立「連動禁區」防護段落。自動分析專案程式碼,找出高扇入模組、資料結構契約、部署設定、對外契約與演算法核心等「改 A 會壞 B」的高風險區域,經使用者確認後寫入該專案的 CLAUDE.md,作為日後所有修改行為的防護依據。MANDATORY TRIGGERS:使用者說「建立連動禁區」「設定 guardrails」「init guardrails」「幫這個專案建立防護」「分析哪些程式碼不能亂動」「哪些模組牽一髮動全身」「建立修改防護段落」「把禁區寫進 CLAUDE.md」,或在新專案開始前要求建立修改安全機制時,都要套用此 skill。適用於 Firebase/PWA、GAS、後端服務等各類專案。SCOPE:本 skill 只做分析與(經確認後的)CLAUDE.md 寫入,不修改任何程式碼。本 skill 同時是 agentic-dev-loop 開發迴圈的「前置」階段:當該編排器在 Step 0 發現專案尚未建立連動禁區時會呼叫本 skill;使用者單獨要求分析禁區時仍直接觸發本 skill。

  • Meta prompt skill

    2000silpeed/meta-prompt-skill Skill

    0★

    타깃 AI 모델(GPT/Codex, Claude, Gemini, Seedance, Higgsfield 등)별 프롬프트 가이드북에 맞춰 사용자의 요청을 최적화된 프롬프트로 변환·생성한다. 트리거 — "○○용 프롬프트 만들어줘", "프롬프트 최적화해줘", "이 요청을 ○○ 프롬프트로 바꿔줘", "프롬프트 잘 써줘", "meta-prompt". 서브커맨드 — "/meta-prompt refresh <model>"(가이드북 갱신), "/meta-prompt add <model>"(새 모델 추가), "/meta-prompt eval <요청>"(원본 vs 변환본 A/B 비교). 단순 문장 윤문이나 한글 자연화는 humanize-korean 소관.

  • Coding agent docs

    brege/agent-db/defaults/skills/coding-agent-docs Skill

    0★ repo

    Use when answering questions about configuring, extending, debugging, or operating Claude Code or Codex coding agents, including permissions, sandboxing, skills, subagents, hooks, MCP, rules, AGENTS.md, refresh behavior, CLI behavior, IDE or app behavior, and agent documentation freshness.

  • Context packet

    Anserinaecrotalariasagitallis995/context-packet/.claude/skills/context-packet Skill

    no license0★ repo

    Design and build context-packet DAG pipelines — graph design, shell orchestration, MCP server integration, and programmatic TypeScript API. Use when creating AI agent workflows that pass context between nodes.