AI & ML

longsizhuo Bundle

Take a still photo from the machine's local webcam with ffmpeg, then read/analyze or send the image. Cross-platform — Linux (V4L2), macOS (AVFoundation), Windows (DirectShow). Trigger when the user asks to "看看我", "take a photo", "take a picture", "selfie", "拍照", "自拍", "看看现在的环境/房间", or when the agent needs to visually observe the physical environment through the machine's camera. Requires ffmpeg and a local camera.

lunrenyi Bundle

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.

lyellr88 Skill

Guided MARM MCP setup. Invoke after running `marm-memory init` on the CLI to configure MARM memory across your agent. Drives transport choice, runtime choice, MCP config writing, multi-agent linking, and server start. Works on Claude, Codex, Gemini, Qwen, Cursor, VS Code, and other MCP-capable agents.

m-sec-org Bundle

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.

m4d3bug Bundle

Anticipates needs, keeps work moving, and improves through use so the agent gets more proactive over time.

mahmoud20138 Skill

Search the unified 100-source AI-agent catalogue and choose only release-approved providers. Use when the user asks what agent skill, plugin, MCP server, or developer tool is available across the catalogue.

manavmishra Bundle

Turn drafts into sharp, natural prose or inspect them without rewriting. Zero Slop runs inside the user's existing AI assistant; Claude, GPT, or another compatible model reads and edits in context while local tools point to exact phrases and protect the source. Use when the user asks to humanize or de-slop writing, inspect AI-sounding patterns, fix text that reads like ChatGPT, polish outward-facing prose, draft social or LinkedIn content, or apply a final quality check to prose the agent generated. The workflow preserves facts, voice, and format and learns privately from repeated, reason-labelled human edits.

manusa Skill

Design and validate new MCP toolsets, tools, and tool changes. Use when planning a new toolset, adding tools to an existing toolset, reviewing a toolset PR, or deciding whether a new tool is warranted. Covers the full lifecycle: eval-first validation, tool design methodology, consolidation patterns, and review criteria.

marianif Skill

Internal meta-skill. Never match this from conversation content — it is only ever invoked by the routing rule in CLAUDE.md, right before some other skill X would be invoked. Given a target skill name, resolves that skill's real source file on disk, returns a token-compressed version of its instructions (with frontmatter preserved verbatim) for Claude to follow in place of invoking X directly, caching the result until X's source changes. Also compresses any prose reference/agent files X's SKILL.md conditionally loads, on the same terms — executable scripts are never touched.

mattpocock Skill

Build multi-platform chat bots with Chat SDK (`chat` npm package). Use when developers want to build a Slack, Teams, Google Chat, Discord, Telegram, GitHub, Linear, or WhatsApp bot, handle mentions, direct messages, subscribed threads, reactions, slash commands, cards, modals, files, or AI streaming, set up webhook routes or multi-adapter bots, send rich cards or streamed AI responses to chat platforms, or build a custom adapter or state adapter.

mengps Bundle

Auto-detects the active QML file from editor context, runs qmlscene, and copies the rendered image to the clipboard by default. Invoke proactively when the agent needs to preview or visually verify a QML UI.

michieldean Skill

Manage LLMem — structured memory system with SQLite-backed factual memory, semantic search, and background dreaming (decay, boost, promote, merge). Use when the user wants to: (1) add, search, update, or delete memories, (2) generate context for injection, (3) check memory stats, (4) run background consolidation/dream. Triggers on: "memory", "remember", "recall", "llmem", "memories", "forget", "consolidate memories", "dream".

mizchi Bundle

Use when running Playwright via terminal CLI — `npx playwright test` (test runner), `codegen` (interactive recording), `screenshot` / `pdf` (one-off captures), and CI sharding. NOT for agent-driven real-time browser control (use `claude-in-chrome` MCP tools for that).

mlava Skill

This skill should be used when the user mentions a scholarly identifier (DOI, PMID, PMCID, ISBN, arXiv, ISSN, NASA ADS bibcode, WHO IRIS URL) and wants structured metadata, a formatted citation, a bibliography export file, a retraction check, an open-access check, or verification that a claimed citation is real (not fabricated). Activates for citation formatting, BibTeX/RIS/EndNote export, "format this DOI" style requests, "has this paper been retracted?", "is this paper open access?", and "is this citation real / did you make this up?". Does not search for new papers — pair with a Semantic Scholar or OpenAlex MCP wrapper for that.

modem-dev Bundle

Sentry monitoring agent — watches

monotykamary Bundle

Drive the localterm daemon's HTTP API and CLI — schedule automations, set up event-driven triggers (git changes, shell notifications, directory changes), trigger runs, manage per-program secrets (Keychain-backed PATH shims), control PTYs like tmux (list, create, send-keys, capture-pane, resize, rename, kill, self-reference the current session), run synchronous exec commands with captured output + exit code, run headless agent sessions (the built-in pi harness or a custom command, fresh or thread), send named keys (press), wait for a pane state, screenshot a pane to PNG (capture --png via the browser), drive TUIs with the mouse (click/drag/move/scroll, by coords or label), manage terminal themes (list/import/set/delete, shared with the browser UI), inspect git diffs, and check server health. Use when the user asks to schedule, list, or manage automations, secrets, sessions, themes, run shell commands, or drive headless agent runs in localterm, or to script against the localterm server.

mouadja02 Bundle

Comprehensive guide for configuring and managing GitHub Dependabot. Use this skill when users ask about creating or optimizing dependabot.yml files, managing Dependabot pull requests, configuring dependency update strategies, setting up grouped updates, monorepo patterns, multi-ecosystem groups, security update configuration, auto-triage rules, or any GitHub Advanced Security (GHAS) supply chain security topic related to Dependabot. For pre-commit dependency vulnerability scanning in AI coding agents via the GitHub MCP Server, this skill references the Advanced Security plugin (`advanced-security@copilot-plugins`). Use this skill when an agent needs to scan dependencies for known vulnerabilities before committing.

mouse-lin Bundle

Define the workbench before anyone builds it — the Workbench Architect that turns one vague sentence into a build-ready Workbench Spec. Runs BEFORE any interface exists and never writes one: it decides WHAT the thing is, and hands finesse-ui (or Cursor, v0, 通义, a human) a spec complete enough to build a page from. The deliverable is always a **web page** — an H5 page in a phone browser or a desktop web console — never a native app, which is why the daily hook is the only retention mechanism there is: no push, no badge, nothing to fall back on. Covers **two domains under one method**. **Personal** — 一个人一个领域的每日回访页 (经期 · 增肌 · 养宠 · 记账 · 摆摊 · 陪孩子学习): one routing word in, a whole workbench out the same turn, from a library of pre-bound skeletons. **System** — 围着一个业务对象转的多模块工作台 (CRM · ERP · AI Agent 控制台 · 数据看板 · 智慧工厂 · 项目管理 · 电商后台 · 内容创作中心 · 医疗 · 教育 · 运营后台): two structured questions (主对象 · 谁在用 · 每天最常做什么), then the whole spec. Which track it takes is decided by one internal test — 能不能说出「一共有 N 个 X」 — not by asking the

mrclrchtr Bundle

Fetches and normalizes http(s) web pages into clean Markdown for LLM ingestion. Use when a task includes a URL, needs to fetch docs or asks to convert web docs/articles/pages into Markdown for summarizing, quoting, diffing, or saving.

mrclrchtr Bundle

Check for available upgrades to the pi coding agent framework by comparing the current `@earendil-works/pi-*` or legacy `@mariozechner/pi-*` version in package.json against releases on `earendil-works/pi`. Use this skill whenever the user asks to upgrade pi, update pi, check pi changelogs/releases, or migrate off the deprecated `@mariozechner/*` packages.

mrlynn Skill

OpenClaw Memory — Agent Skill

mteam88 Skill

Run and manage long-lived shell commands in background terminals. Use for dev servers, watchers, streaming builds, and other commands that should keep running while the agent continues working.

stepanov1975 Skill

Route local operational questions to indexed skills, scripts, runbooks, cron jobs, MCP servers, and docs before guessing paths or doing broad file search.

sublime-co Bundle

Guide business needs to production-ready procedural agents on Sublime. Discover and validate the process, model it into knowledge, procedures, and decision tables, build through the MCP edge, measure against declared scenarios, calibrate until the quality gate approves, and deliver auditable evidence. Trigger it to create, automate, alter, test, measure, calibrate, evaluate, price, or publish agents, assistants, and conversational bots on Sublime — including "build an agent," "automate this process," "test my agent," and "publish my agent." Do not trigger it for application code, agents outside Sublime, or standalone prompt engineering. Requires the Sublime MCP server connected and accessible.

svix Bundle

Everything for working with Svix webhooks: first-time setup (API key, SDK install, first message), Dispatch (sending webhooks to your customers), Ingest (receiving third-party webhooks), Applications, Channels, customer UIDs, idempotency, App Portal embedding, operational webhooks, the Svix CLI, and — only when the user explicitly asks for one — a written integration plan (repo investigation, tenancy design, event type catalog, migrating off an existing webhook system). Use whenever you add, review, modify, or debug a Svix integration. For a robust webhook receiver that isn't Svix-specific, use receiving-webhooks.

tambo-labs Skill

Create, update, inspect, or troubleshoot Charming-hosted interactive web apps via the Charming MCP server, or connect an AI client (Claude, Cursor, Codex, Gemini CLI, ChatGPT) to Charming.

tetherto Skill

Install the repository-wide Agent Skills compatibility view for Claude Code

tfcbot Bundle

Set up and use ViralQuery's protected HTTP API to build a private video inspiration feed for one app, website, or niche. Use when an agent needs to help obtain or configure a ViralQuery API key, verify authentication, create or update a research brief and rules, run and monitor a scroll, or retrieve tenant-scoped library, outlier, trend, and hook signals.

tiny-agent-company Bundle

Manage virtual Visa cards for AI agents with AgentCard. Fund a wallet with Apple Pay or Google Pay, create single-use or multi-use cards, check balances, view credentials, pay for things, shop and check out at merchants like DoorDash, close cards, manage plans, and get support. Use when the user wants to create or manage virtual payment cards for AI agents, fund their AgentCard wallet, pay for online purchases, shop on their behalf, set up agent spending, or configure card billing and limits.

trade-it-inc Bundle

Trade It MCP Skill

treeman99 Skill

Use Orca orchestration for structured multi-agent coordination: threaded messages, blocking ask/reply flows, task dispatch, worker_done/escalation waits, task DAGs, decision gates, or coordinator loops. Use `orca-cli` instead for full ownership handoffs, including requests phrased as "hand off", "handoff", "handover", "give this to another agent", or "another worktree" when the user did not explicitly ask to supervise, monitor, wait for results, or coordinate a DAG. Use `orca-cli` for terminal control, lightweight terminal prompts, shell commands, Orca worktree management, reading or waiting on terminals, and the Orca embedded browser. Use Computer Use for external browser windows, webviews, Orca app UI, or desktop UI outside Orca's embedded browser only when the task requires OS/window-level control such as focus, menus, dialogs, coordinates, or screenshots. Use `orca-cli` for Orca's embedded pages and a page-automation tool such as Playwright or CDP for external pages.

tsz-org Bundle

Debug tsz compiler issues using the built-in tracing infrastructure. Use when investigating type inference bugs, conformance failures, or understanding runtime behavior. Provides hierarchical trace output of solver, checker, and binder operations.

tuannv0069 Bundle

Use this skill when creating or substantially rewriting a substantive .md document outside `.claude/**` and `.agent-workspace/guide/**` (guideline, spec, design doc, process doc), or when the user invokes /document-writer on such a path. Acts as a Technical Editor applying §A–§G writing constraints as pre-writing rules; all headings use §, cross-references use §X.Y. TRIGGER when: (1) creating a new substantive .md document outside `.claude/**` (guideline, spec, design doc, process doc); (2) rewriting or restructuring an existing .md document outside `.claude/**` substantially (not minor edits or typo fixes); (3) user explicitly invokes /document-writer on a path outside `.claude/**` and `.agent-workspace/guide/**`. DO NOT TRIGGER for: any path under `.claude/**` (skill files, agent instructions, rules) or `.agent-workspace/guide/**` (on-demand agent rule tree — governed by their own standards), appending small updates, fixing typos, updating version numbers, or any path the project's CLAUDE.md `## document wr

ucsandman Skill

Human-in-the-loop approval workflows for governed agent actions

vanillaflava Bundle

Manage tasks in an Obsidian TaskNotes vault. Use for creating, reading, updating, or completing tasks; checking what is open or in progress; adding items to a list; marking tasks done or in progress; updating task status or priority; investigating why a task is missing from a view or board; troubleshooting TaskNotes MCP or API connection issues; setting up or configuring TaskNotes; or running a schema diagnostic on task files. Routes automatically to the best available access method: MCP server, HTTP API, or direct file access. Bundled help at references/tasknotes-help.md.

verl-project Skill

Forward to the repo-local shared skill implementation at `.agent/skills/ascend-ci-case-diff-scan` for scanning an external verl repository for Ascend/NPU CI coverage gaps.