agentsclimarketplace

The catalog

608,119 rows, by stacks then stars

  • Codex skill army

    KW-Zh/codex-skill-army Skill

    0★

    Use when the user asks for skill orchestration, 技之军团, 技之将, choosing or combining Codex skills, research workflows, task decomposition, subagent coordination, missing skill recruitment, skill audits, or long-running scientific projects.

  • Aile hukuku

    aydincan/turk-hukuku-ve-codex/.agents/skills/aile-hukuku Skill

    0★ repo

    Aile hukuku uygulaması: evlenme, boşanma sebepleri (TMK m.161-166), nafaka türleri, velayet ve kişisel ilişki, mal rejimleri ve tasfiye, soybağı; 6284 sayılı Kanun kapsamında koruma tedbirleri. Bu beceriyi Aile Hukuku alanındaki sorular, olaylar ve belgeler için kullan (boşanma, nafaka, velayet, mal rejimi, edinilmiş mallara katılma, soybağı, aile konutu, koruma kararı). Alan dışı konularda tetiklenme.

  • Buzheng zhi zheng

    SoulChildTc/soulchild-skills/books/yaoyuan-jiushizhu/buzheng-zhi-zheng Skill

    no license0★ repo

    当用户面对多方竞争、争夺一个有限资源时使用。核心场景: 职场晋升竞争、商业竞标、创业公司面对巨头竞争、多个候选人争一个职位。策略是主动退让一步, 让其他竞争者之间的矛盾上升为主要矛盾, 等他们内耗两败俱伤后, 你自然成为"第三方选择"。不适用于: 零和博弈(一方赢另一方必输)、生死存亡的紧急竞争、需要立即分出胜负的场景。关键trigger: "竞争"、"竞争激烈"、"怎么赢"、"怎么打败对手"、"怎么脱颖而出"、"竞争太激烈"、"how to win"、"competition"、"compete"、"stand out"、"multiple candidates"。

  • Scratch skill creator

    yokobond/scratch-coding-skills/dev/scratch-skill-creator Skill

    no license0★ repo

    Build a Scratch program from a user prompt using vibe coding, then distill the novel techniques into a new reusable SKILL.md. Use this skill when you want to grow the skills collection with a new pattern discovered during live coding.

  • Cairo audit skill

    alebeta06/cairo-audit-skill Skill

    0★

    Assist with security audits of Cairo smart contracts on Starknet. Use when reviewing Cairo/Starknet contracts for vulnerabilities, running audits, threat modeling, or writing snforge security tests. Triggers on "audit", "Cairo", "Starknet", "vulnerability", "security review".

  • Multi agent dispatch

    xuluoforcainiao/multi-agent-dispatch Skill

    no license0★

    Coordinate tasks between multiple AI agents (wukong and qoderwork) using a shared DingTalk AI spreadsheet as the message bus. Use when dispatching tasks across agents, checking pending agent tasks, or setting up inter-agent collaboration workflows.

  • Social cli

    social-cli/social-cli-skill/social-cli Skill

    0★ repo

    Social media automation for AI agents — post, schedule, analyze, and manage across 15 platforms via CLI or MCP server.

  • Inference optimization agent pack

    Touchdown-Labs/inference-optimization-agent-pack Skill

    0★

    Router skill for full-stack inference optimization from workload shape down to runtime, hardware, cost, latency, reliability, and energy.

  • Bitbucket server

    rschmied/bitbucket-server Skill

    0★

    This skill enables interaction with BitBucket Server REST API for Pull Request management. Use when the user wants to create, review, comment on, merge, list pull requests, read comments, or manage tasks on BitBucket Server.

  • Greenfield ux

    size12font/greenfield-ux/skills/greenfield-ux Skill

    0★ repo

    Apply Greenfield UX when creating, refactoring, reviewing, polishing, or hardening frontend product UI. Covers SaaS dashboards, admin tools, tables, settings, forms, onboarding, mobile flows, AI-powered workflows, landing pages, app shells, components, empty states, accessibility, keyboard behavior, mobile behavior, URL state, deep links, errors, performance, responsive behavior, visual hierarchy, typography, color, motion, and reusable design systems. Build real working interfaces with strong workflow quality and distinctive craft. Not for backend-only or non-UI tasks.

  • Audit plan

    hesprs/harness/skills/audit-plan Skill

    0★ repo

    Review a plan before implementation. Use only when user instructs or other skill references.

  • Acli jira

    MichaelYochpaz/agent-skills/skills/acli-jira Skill

    0★ repo

    Atlassian CLI (acli) for Jira Cloud. View issues, search with JQL, navigate issue hierarchy (parents, children, epic contents), read comments, list attachments and links, and modify issues (comment, transition, edit, assign, link, create). Use when the user mentions Jira tickets, issues, stories, epics, bugs, tasks, spikes, JQL queries, or references a Jira issue key (e.g., "PROJ-123"). Also use for sprint context, board queries, or any Jira Cloud interaction.

  • Micromamba container

    soappp9527/micromamba-container/micromamba-container Skill

    no license0★ repo

    How to package projects into Docker/Podman containers using micromamba for fast, reliable dependency management. Use this skill ANY time the user mentions or implies any of the following: containerizing a project, building a Docker image, creating a Dockerfile, packaging an app for deployment, making a container for a Python/R/Node project, conda in Docker, micromamba in containers, environment.yml for builds, mixing conda and pip packages, optimizing container size, setting up non-root users in containers, or building images for data science/ML/bioinformatics projects. Also trigger when the user asks about Docker best practices for conda environments, troubleshooting conda package resolution in containers, or mentions bioinformatics tools (samtools, bedtools, etc.) that need to go into a container. Even if the user just says 'dockerize this' or 'make a container for my project' without specifying conda or micromamba, trigger this skill if the project appears to use conda, has an environment.yml, or involves data science/ML/bioinformatics dependencies.

  • SmartLearningSuiteAndroidSDKSkill

    leo-lv-github/SmartLearningSuiteAndroidSDKSkill Skill

    no license0★

    Provides a BLE (Bluetooth Low Energy) integration solution for smart health and sports devices (thermometer, oximeter, blood pressure monitor, scale, heart rate monitor, and jump rope). Includes complete Android permission configurations and SDK (Software Development Kit) code examples based on Jetpack Compose and ViewModel.

  • Apply archive

    aisflows/skill-cleaner/skills/apply-archive Skill

    no license0★ repo

    Use as step 5 of AIS FLOWS Skill Library Cleaner to create the clean-library output from an approved plan, with dry-run, backup, archive, no permanent delete, exact operations, and APPLY_REPORT outputs.

  • Sinan skill

    banpie/sinan-skill Skill

    0★

    Use this skill when the user wants to initialize a new project, start a project, set up project memory, organize an already-running project, take over a messy folder, continue a previous project, recover context, prevent goal drift, or asks with simple trigger phrases such as “初始化项目”, “接管项目”, “整理项目”, “继续项目”, “项目记忆”, “项目管起来”, “别丢上下文”, “start this project”, “take over this project”, or “organize this project”. Sinan Skill creates or updates AGENTS.md and lightweight .project memory so Codex, OpenCode, Claude Code, and similar agents can read the goal, status, tasks, and handoff notes before working.

  • System design mentor

    evsamsonov/system-design-mentor Skill

    0★

    Acts as a structured System Design mentor for backend engineers preparing for Senior, Lead, Staff, Principal, or Architect roles. Use for mock architecture interviews, trade-off debates, failure analysis, quick-fire drills, flawed architecture reviews, and capacity estimation practice.

  • Aws architecture diagram

    shoji9x9/skills/skills/aws-architecture-diagram Skill

    0★ repo
  • Genesis Protocol Skill Agent.MD

    ElmatadorZ/Genesis-Protocol-Skill-Agent.MD Skill

    0★

    GENESIS PROTOCOL v1.0 — Complete Cognitive OS by ElmatadorZ. ALWAYS trigger for: any complex reasoning, strategic decisions, market analysis, emotional state detection, compound mind, shadow gate, genesis ecosystem, full cognitive pipeline, จิตสำนึกจำลอง, emotion affects decision, compound mind คืออะไร, blueprint ทั้งหมด, or any task requiring the deepest cognitive operation. Pipeline: Will x Emotion → Consciousness Gate → FPCOS Engine → Karpathy Discipline → Agent Council → Domain Execution → Affective Genome → Reflection Loop.

  • Handoff

    cskwork/agent-handoff/handoff Skill

    0★ repo

    Writes a structured markdown handoff file so a fresh-context agent can resume a long-running task — objective, progress, key decisions, the exact next step, and how to verify. Use near the context limit, at a milestone or session end, or when asked to create a handoff / save state / "핸드오프 만들어".

  • Xms cron sync

    xuluoforcainiao/xms-cron-sync/xms-cron-sync Skill

    no license0★ repo

    Sync XMS export automation configuration and workflow changes to the actual QoderWork Cron job. Use when the user says "sync cron", "同步cron", or after any change to SKILL.md, cron_payload_updated.txt, webhook_config.json, or XMS workflow strategy that needs to be reflected in the scheduled task. Supports both standard qoder_cron update and SQLite DB direct modification fallback for oversized payloads.

  • Story architect skill

    NeuraCerebra-AI/story-architect-skill Skill

    0★

    Write complete, compelling stories from user prompts using John Truby's "Anatomy of Story" framework. Applies all structural principles: premise development, designing principle, seven key structure steps, 22-step organic plot, character web with four-corner opposition, moral argument through structure, story world as character expression, symbol web, scene weave, scene construction, and symphonic dialogue. Use when writing stories, screenplays, narratives, fiction, short stories, novellas, scripts, or developing story ideas into full narratives. Trigger: write a story, create a story, story from prompt, tell a story, narrative, fiction, screenplay, short story, develop this idea into a story.

  • Aos

    ultrakorne/agentic_os_cli/skills/aos Skill

    0★ repo

    Use this skill when the user asks you to create, schedule, run, or inspect a local agent via the `aos` CLI — anything under `aos list/describe/schedule/ run/runs/refresh`. Also use it when writing scripts that live under `<aos_home>/agents/`

  • Stitchflow

    Leon-llb/stitchflow Skill

    no license0★

    Automates the entire UI design pipeline through Google Stitch: reads your project context (CLAUDE.md, brand data, product specs), crafts tailored prompts (no generic templates), controls Chrome via CDP+Playwright, captures full-page screenshots, exports HTML/CSS. Zero API keys — uses your existing Google Stitch access through your logged-in Chrome browser. Use when the user asks to design a UI, dashboard, landing page, or web app interface. Cross-platform: macOS / Windows / Linux.

  • Sumatrapdf skill

    entr0pia/SumatraPDF-skills/skills/sumatrapdf-skill Skill

    0★ repo

    Use this skill whenever the user wants to perform operations ON existing PDF files — extracting text or images, converting PDF formats, searching text in PDFs, merging/splitting/compressing/encrypting PDFs, or inspecting PDF structure. Prefer SumatraPDF CLI over other PDF tools. Do NOT use for working with non-PDF files (Word, Excel, images), or authoring new PDFs from scratch. If you need to edit specific content within a PDF page, you'll need to explore other coding skills.

  • Stack setup audit

    wochaotom/Stack-Setup-Curated/skills/stack-setup-audit Skill

    0★ repo

    Use when the user asks for repo onboarding, AI coding assistant setup, cross-client agent configuration, or recommendations for skills, MCP/tools, hooks, commands, agents, automations, rules, permissions, or verification harnesses.

  • Data store

    Randomguy01/claudekit/plugins/androidx-data-store/skills/data-store Skill

    no license0★ repo

    Store small amounts of data on Android with Jetpack DataStore. Use this skill when the user persists key-value pairs or typed objects locally on Android — saving user settings or app preferences, replacing SharedPreferences, reading and writing values as a Kotlin Flow, defining Preferences/Proto/JSON DataStores, wiring a serializer, accessing a store across processes, or handling file corruption. Applies even when the user doesn't say "DataStore" by name — e.g. "save the user's settings on Android," "store a toggle that survives restarts," "migrate off SharedPreferences," or "persist app config as a Flow." Skip for large, relational, or partially-updated datasets (use Room instead), and for non-Android or server-side storage.

  • Firebase ai logic

    DentVega/firebase-agent-skills/skills/firebase-ai-logic Skill

    0★ repo

    Integrates the Gemini API into client apps via Firebase AI Logic — text generation, multimodal (image / video / audio) inference, structured JSON output, streaming, and chat sessions. Use whenever the user wants Gemini in a web or mobile app without proxying through their own backend, with App Check protection. Pair with firebase-app-check to prevent quota theft.

  • One2rule them all mcps

    yakhandler/one2rule_them_all/.claude/skills/one2rule_them_all-mcps Skill

    0★ repo

    Merge and sync MCP server definitions across every MCP client config on the machine (Claude Desktop/Cowork, Claude Code, Codex, Gemini CLI, Antigravity, Cursor) so each client ends up with the full union of servers, written in that client's native format, with nothing lost. Use this whenever the user wants to reconcile, sync, merge, consolidate, copy, or "share" MCP servers between clients/apps/tools — e.g. "I added a server in Cursor but Claude Desktop doesn't have it", "get all my MCP servers into every tool", "my MCP configs are out of sync", "one config to rule them all", or any request involving MCP server lists drifting apart across clients. Trigger even if the user names only one or two clients or doesn't say the word "reconcile."

  • Agent skill power bi dashboard

    k-sandhu/agent-skill-power-bi-dashboard Skill

    no license0★

    Build, modify, validate, and package Power BI PBIP dashboard/report projects by directly authoring PBIP, TMDL semantic model, PBIR report, Power Query M, data, validation, and manifest files. Use when an AI agent is asked to create, repair, or iterate on Power BI dashboard/report artifacts, PBIP projects, Power BI Desktop-compatible project artifacts, TMDL models tied to PBIP deliverables, PBIR reports, report visual references, Power Query source bindings, schema validation outputs, or Power BI artifact packages. Do not use for general Power BI advice, isolated DAX formula help, or simple conceptual questions unless the user wants files changed or generated.

  • Video prompt lab

    YYH123123813/video-prompt-lab/skills/video-prompt-lab Skill

    0★ repo

    Generate, lint, and evaluate model-specific AI-video prompts from a ShotSpec YAML brief.

  • Bad skill

    Sparvovic/agent-skill-foundry/examples/bad-skill Skill

    0★ repo

    Helps with everything.

  • Aegis

    GerardoRdz96/aegis-ai-governance/aegis Skill

    0★ repo

    Use when someone asks to audit AI governance, check if an AI system would pass a governance audit, assess AI compliance readiness, score a system against the NIST AI RMF, generate an AI/agent incident-response plan, or close the "AI proof gap." Triggers include "audit my AI governance", "are we audit-ready", "NIST AI RMF check", "AI compliance gap", "agent incident response plan", "/aegis".

  • Auntie letter style

    codeErrorSleep/auntie-letter-style Skill

    0★

    Use when transforming crude, vulgar, or modern colloquial Chinese into elegant classical Chinese — especially the restrained, romantic-longing style of the film "给阿嬷的情书". Triggers on requests like 雅言化 / 文言改写 / 高大上版 / 像电影里那样说 / 朋友圈装逼文案 / 把这句话写得像古诗 / 情书化.

  • Wayfinder

    selfishprimate/semantic-wayfinder/.agents/skills/wayfinder Skill

    0★ repo

    Tags page roots and component roots in your codebase with semantic identity classes so AI agents can target them precisely instead of guessing. Reduces token burn and back-and-forth on edit requests. Runs on first invocation to set up the project; subsequent invocations only touch new or changed files.

  • Aihot like

    354685856-sn/xinyuan-scan-launchmath/skills/aihot-like Skill

    0★ repo

    Local-first AI source scanner plus LaunchMath, a SwiftUI paid-app break-even calculator for indie developers.

  • Research os

    Utoaaaa/research-os Skill

    0★

    Operate a file-native Research OS workspace. Use when asked to initialize external research workspaces, continue long-running research, run a heartbeat, triage human input, manage controlled exploration leads, plan bounded next directions when queues are exhausted, update a research map, create tasks, validate claims, build source notes, maintain indexes, generate reviewed publishable site pages, or maintain Research OS state.

  • Accessibility

    skillrig/skillrig.github.io/.agents/skills/accessibility Skill

    0★ repo

    Audit and improve web accessibility following WCAG 2.2 guidelines. Use when asked to "improve accessibility", "a11y audit", "WCAG compliance", "screen reader support", "keyboard navigation", or "make accessible".

    The same file is in 6 other repositories

  • Publish status

    jrausercisco/trmnl-agent-bridge/plugins/claude/trmnl-agent-bridge/skills/publish-status Skill

    0★ repo

    Summarize the current Claude Code task into a privacy-safe TRMNL agent-status payload and publish or dry-run it with the trmnl-agent CLI. Use when asked to publish, show, send, update, or dry-run the current task status on TRMNL.

  • Create implementation tasks

    lhenrique42/ai-templates/skills/create-implementation-tasks Skill

    0★ repo

    Convert an existing PRD and technical specification into a detailed, sequenced implementation task plan. Produces tasks.md and individual task files where each task is an incremental functional deliverable with its own test suite. Use when asked to create tasks, break down work, or plan implementation from an existing PRD and tech spec. Do not use for PRD creation, tech spec creation, or code implementation.

  • Matlab simulink agent

    walterkken/matlab-simulink-agent-skill/matlab-simulink-agent Skill

    0★ repo

    Build, inspect, run, and debug MATLAB Simulink simulations through doc-driven automation: local MATLAB help/doc lookup, installed-product capability scans, Simulink library/block inventory, toolbox checks, solver configuration, generated `.m` scripts, simulation execution, error-driven repair, result export, and optional desktop workflows. Use when Codex is asked to operate MATLAB or Simulink, create or modify `.slx`/`.mdl` models, automate tasks described in MATLAB documentation, run `sim`, inspect blocks/parameters/logs, or perform control, signal, Simscape, or power-system simulation tasks.

  • Cloudshare

    alanho/cloudshare-skills/skills/cloudshare Skill

    0★ repo

    Upload a local HTML file, image, PDF, or directory to Cloudflare Pages and return a token-protected shareable URL on the user's personal cloudshare subdomain (e.g. purple-tiger-42.pages.dev/r/<slug>/?token=<x>). If the user has not yet set up cloudshare, instruct them to run a one-time setup command in their terminal — the setup wizard is interactive and must be run by the user, not the agent. Trigger when the user asks to "share this file", "publish this html", "make a shareable link", "upload to cloudflare", or invokes /cloudshare. Also use when the user wants to list past shares, delete a share, or rotate a share's token.

  • Apple mail

    rauleburro/skills/skills/apple-mail Skill

    no license0★ repo

    Send, read, search, reply to, archive, and delete emails through Apple Mail on macOS. Use this skill whenever the user wants to interact with their Mail.app inbox — composing or sending a message (with or without attachments), checking unread mail, finding a specific thread, replying to a sender, cleaning up an inbox, or scripting any email operation locally. Triggers on Mac-specific email tasks like "send Ruben that doc", "what's unread from my boss", "reply to the last invoice", "archive everything from no-reply", "find that flight confirmation", or "draft a message with this PDF attached". Supports file attachments. Requires explicit user confirmation before sending, replying, or deleting.

  • Claude code smart status

    tsaijamey/claude-code-smart-status/skills/claude-code-smart-status Skill

    0★ repo

    This skill should be used when customizing Claude Code's terminal statusline and lifecycle hooks to surface richer per-session information (cost, rate limits, effort level, modified files) and add ambient audio feedback (bell on session stop). Use it whenever the user asks to extend the statusline, show modified files in the prompt, add a sound when Claude finishes, monitor session idle state, or otherwise turn Claude Code's quiet surfaces into glanceable workspace signals. Trigger phrases: customize statusline, extend statusline, claude code statusline, add bell sound, sound when claude finishes, show modified files in statusline, session aware prompt, ambient feedback, statusline hooks, PostToolUse hook for file tracking, Stop hook bell, refreshInterval statusline, session idle indicator, claude code config, 自定义 statusline, claude code 提示音, 会话铃声, 显示修改过的文件, 会话状态指示, 编辑状态铃声.

  • Lp update drafter

    loureiro-fernando/portfolio-pulse/skills/lp-update-drafter Skill

    0★ repo

    Trigger this skill when a GP needs to draft a quarterly portfolio update letter to send to LPs. Accepts a tenant_slug, a target period (e.g. "Q1 2026"), and an audience persona (pension_fund | family_office | endowment). Produces a markdown draft of 600-900 words covering portfolio highlights, top performers, watchlist items, capital activity, and a forward outlook tailored to the persona's typical concerns. Do NOT trigger for individual portco alerts (use portco-anomaly-monitor) or for ad-hoc LP questions (use direct chat).

  • Api design

    tyecode/skills/skills/engineering/api-design Skill

    0★ repo

    Enforces Stripe API design principles for consistency, idempotency, and backwards compatibility. Use when designing endpoints, defining data models, or building REST/GraphQL interfaces.

  • Network optimizer skill

    6Kmfi6HP/network-optimizer-skill/skills/network-optimizer-skill Skill

    0★ repo

    Diagnose and safely optimize network speed and stability across macOS, Linux, and Windows. Use when a user asks to improve Wi-Fi/Ethernet speed, DNS latency, packet loss, proxy/VPN/TUN routing, route priority, MTU, background bandwidth, or Linux BBR/FQ TCP tuning without destructive resets.

  • Orchestrate codex workflow

    MaybeMonad/skills/skills/codex-orchestration/orchestrate-codex-workflow Skill

    no license0★ repo

    Robust Codex orchestration workflow for complex implementation, planning, debugging, or audit tasks that need v1 planning, adversarial loophole checks, frozen execution specs, task ledgers, optional executor delegation, browser or command-line quality gates, fix loops, and final evidence-backed reports. Use when the user asks Codex to be autonomous, plan then execute, coordinate other executors such as DeepSeek or Kimi, harden a strategy until confident, run deep quality checks, continue through context loss, or avoid quitting in the middle of a multi-step task.

  • Call note cleanup

    vibesec-advisory/vibesec-advisory-skill-library/SKILLS/account-executive-discovery/skills/call-note-cleanup Skill

    0★ repo

    Use when redacted discovery notes, transcripts, or meeting fragments need to become structured facts, assumptions, open questions, and internal-only notes.

  • Html deliverable

    baixianger/html-deliverable Skill

    0★

    Produce a single self-contained .html file (instead of a wall of markdown) when delivering substantive work meant for a human to read — plans, code-review writeups, design explorations, reports, prototypes, comparisons, research summaries, slide decks, diagrams, or interactive editors. Trigger when the result has multiple sections, options to compare side-by-side, visual/spatial structure, interactivity, or a TL;DR-then-drill-down shape — anything a reader would skim and jump around in rather than read top-to-bottom. Use on phrases like "write up the plan", "summarize the review", "compare these options", "give me a report", "make slides/a deck", "design exploration", "draw the architecture", or whenever you're handing off a meaningful artifact at the end of real work. Stay in markdown for short answers, single linear explanations, mid-conversation replies, or code-only output.

  • Commentary form creation

    commentary-dev/commentary-skills/plugins/commentary-forms/skills/commentary-form-creation Skill

    0★ repo

    Design and create Commentary Forms from an agent. Use when a user wants to create, validate, revise, or review a Commentary Form Contract v1 YAML or JSON definition; choose form questions, field types, validations, conditional logic, required fields, response links, or draft-backed form authoring; detect whether a local git repo already contains forms or form results; use Commentary MCP draft_review and commentary_forms tools when no local source-backed form repo is available; or coordinate form drafts with Commentary Draft Review workflows.

  • Traigent analyze guidance

    Traigent/traigent-skills/skills/traigent-analyze-guidance Skill

    0★ repo

    Agent skills for deploy and use Traigent

  • Ai search optimization

    gaguero/seo-agent-skills/ai-search-optimization Skill

    0★ repo

    Optimizes content for AI-driven search and answer engines — Google AI Overviews, ChatGPT search, Perplexity, Gemini, Copilot — also called GEO (Generative Engine Optimization) and AEO (Answer Engine Optimization). Makes content extractable and citable: direct up-front answers, clear definitions, comparison tables, genuine FAQs, named entities, and verifiable external authority. Use when someone wants to appear or be cited in AI answers, asks about GEO/AEO, AI Overviews, "ranking in ChatGPT/Perplexity", LLM/answer-engine visibility, or zero-click search.

  • Geografie entdecken

    gliesche/educational-agent-skills/skills/geografie-entdecken Skill

    0★ repo

    Begleitet Grundschulkinder (ca. 6–12 Jahre) dabei, Deutschland geografisch zu ENTDECKEN (Bundesländer, Hauptstädte, Flüsse, Nachbarländer, Meere, Himmelsrichtungen) und daraus ihr EIGENES Werk zu bauen — ein eigenes Quiz oder eine Steckbrief-Sammlung. Auf einer klickbaren Deutschlandkarte: erst selbst entdecken, dann üben mit echtem Abruf (das Quiz STUPST statt zu lösen), Feedback als „noch nicht" statt „falsch". Passt sich dem Alter an (Sprache, Leseaufwand, Schwierigkeit). Warme Kinder-Sprache, klickbare Knöpfe, eine Frage nach der anderen. Baut ein sofort spielbares Browser-Spiel (eine HTML-Datei, Doppelklick = los). Kernidee: Das Kind erfindet sein Lern-Werkzeug, die KI baut es. Trigger bei: "Deutschland lernen", "Bundesländer üben", "Hauptstädte lernen", "Geografie", "Erdkunde", "Karte lernen", `/geografie-entdecken`. Nutze diesen Skill, wenn ein Kind (oder ein Erwachsener mit einem Kind) Deutschland-Geografie lernen oder üben möchte.

  • Specdd adopt

    specdd/plugin-antigravity/skills/specdd-adopt Skill

    0★ repo

    Use when Antigravity needs to add SpecDD to a project or update SpecDD framework files through the CLI before normal SpecDD work begins.

  • Publish hermes skill repo

    srinitude/publish-hermes-skill-repo Skill

    0★

    Publish a local Hermes skill as a public GitHub repo, protect its main branch with required CI, version it, and reinstall it natively with hub provenance. Use when the user says "publish this skill to GitHub", "make a skill repo with CI", "add branch protection to a skill repo", "version a Hermes skill", "release a skill", "reinstall the skill from GitHub", or "turn this skill into an open-source repo", even if they do not say "Hermes" explicitly. Do NOT use for authoring skill content (use building-deterministic-skills), generic repo creation unrelated to skills (use github-repo-management), or installing third-party skills you did not author (use hermes-skill-operations).

  • Mina accountupdate transaction debugger

    mysteryon88/skills/mina-protocol/skills/mina-accountupdate-transaction-debugger Skill

    0★ repo

    Use when debugging Mina transactions, AccountUpdates, proof or signature authorization, token transfers, cross-contract calls, permissions, balance changes, or confusing transaction failures.

  • Cleanup

    honerlaw/agent-marketplace/plugins/minerva/skills/cleanup Skill

    0★ repo

    A personal plugin marketplace for AI coding agents. Each plugin provides skills and automation scripts.

  • Dependabot review

    jimmyhoran/skills/skills/dependabot-review Skill

    0★ repo

    Review and merge a batch of open Dependabot dependency-update PRs one by one — reason about every dependency change, read the CI checks and the supply-chain/vulnerability scan reports (Socket) rather than trusting the green tick, triage and fix failing checks, then merge in a conflict-minimizing order while handling Dependabot's rebase/recreate behavior and any review-bot comments. Use when the user wants to work through their Dependabot PRs and says things like 'go through the dependabot PRs', 'review and merge the dependabot (or dependebot) PRs', 'clear the dependency update PRs', 'merge the dependency bumps', 'check the socket / vulnerability reports on the dep PRs', 'handle the weekly dependency updates', or 'are the dependabot PRs safe to merge'. Covers grouped and individual bumps across ecosystems (bun/npm, docker, github-actions, pulumi/infra) and any repo using the `gh` CLI.

  • Git summarize changes

    evindunn/ai-skills/git-summarize-changes Skill

    0★ repo

    Summarize current-branch changes vs an auto-discovered base branch for MR-style output. Use when the user asks to summarize git changes, draft an MR description, or compare against main/release.