AI & ML

celo-org Skill

x402 HTTP-native payment protocol for AI agents on Celo. Use when implementing pay-per-use APIs, agent micropayments, or HTTP 402 Payment Required flows with stablecoins.

triggerdotdev Skill

Analyze Trigger.dev tasks, schedules, and runs for cost optimization opportunities. Use when asked to reduce spend, optimize costs, audit usage, right-size machines, or review task efficiency. Combines static source analysis with live run analysis via the Trigger.dev MCP tools (list_runs, get_run_details, get_current_worker).

alibaba Skill

Delegation mode for open-code-review (OCR). Instead of OCR calling an LLM endpoint, this skill instructs the host agent to perform the code review itself, using OCR only for deterministic engineering: file selection and rule resolution. Use when the host agent should drive the review with its own LLM capabilities.

therealharpaljadeja Bundle

Agent wallet on Monad — Alchemy Agent Wallet

brianlovin Skill

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.

tartinerlabs Bundle

Guide for the C -fbounds-safety language extension. Covers the language model, pointer annotations, adopting bounds-safety in existing C code, compiler build settings and modes, and runtime debugging of bounds violations.

volcengine-openviking Bundle

Diagnose and fix the OpenViking memory plugin on this machine: the plugin install (enablement, hooks, MCP server), the client configuration (ovcli.conf / ov.conf / OPENVIKING_* env) and the connection to the OpenViking server (reachability, 401/403, /mcp). Use whenever memory "isn't working": no <openviking-context> block, empty recall, captures not landing, missing or failing MCP memory tools, 401/403, an offline statusline, right after installing/updating the plugin or switching servers/keys, or when the user asks for the plugin's status. Triggers: "memory not working", "check OpenViking", "plugin status", "记忆没生效", "插件状态", "连不上 OpenViking", "recall 为空", "401".

twilio Bundle

Twilio Agent Connect

mikejhill Skill

Use when iteratively refining text-based content to production quality through a parallel three-agent tribunal: harsh critic, advocate, and neutral researcher, with convergence detection.

dwmkerr Bundle

This skill should be used when the user asks to "create a plugin", "build a plugin", "write a plugin", or wants to bundle agents, hooks, commands, skills, or MCP servers into a distributable Claude Code plugin.

lastdays03 Skill

🐞 체계적 디버깅 (Dev Coding Debug)

cyanheads-pubmed-mcp-server Skill

Post-init orientation for an MCP server built on @cyanheads/mcp-ts-core. Use after running `@cyanheads/mcp-ts-core init` to understand the project structure, conventions, and skill sync model. Also use when onboarding to an existing project for the first time.

musserlab Bundle

Generate deep research prompts from scRNAseq marker gene lists for cell type annotation. Use when the user invokes /gene-list-deep-research or asks to generate a deep research prompt from a gene list (cluster markers, WGCNA module, DE gene list). Produces a research-level prompt with structured YAML header for downstream compilation across clusters.

gapfdev Bundle

GitHub Ticket Ops

rafaelramosdf Bundle

Criação, edição e análise de apresentações. Quando o Claude precisar trabalhar com apresentações (.pptx files) para: (1) Criar novas apresentações, (2) Modificar ou editar conteúdo, (3) Trabalhar com layouts, (4) Adicionar comentários ou anotações do orador, ou quaisquer outras tarefas de apresentação

ruvnet-ruvector Skill

Quantum-resistant, self-learning version control for AI agents with ReasoningBank intelligence and multi-agent coordination

olehsvyrydov Bundle

Quality Assurance Auditor that verifies completeness of Feature Proposals, Dev Feature Documents, and implementations. Catches placeholder content, cross-section inconsistencies, traceability gaps, missing tests, security holes, and specification drift. Run with: /verify proposal, /verify devdoc, /verify code, or /verify all. This agent is adversarial by design — it assumes work is incomplete until proven otherwise.

zach-source Bundle

Automatically updates terminal window title to reflect the current high-level task. Use at the start of every Claude Code session when the user provides their first prompt, and whenever the user switches to a distinctly new high-level task. Helps developers manage multiple Claude Code terminals by providing clear, at-a-glance identification of what each terminal is working on.

iuliandita Bundle

· Turn notes into structured LLM prompts or improve existing prompts. Triggers: 'write a prompt', 'system prompt', 'prompt template', 'evaluator prompt', 'delegation prompt', 'rewrite this prompt'. Not for skills or routines.

respira-press Bundle

Build and maintain modern WordPress plugins and MCP servers, including hybrid WordPress+MCP products. Use when implementing plugin architecture (PHP, REST API, Gutenberg/admin/page-builder integrations), MCP tooling (TypeScript/Python, stdio/HTTP transport), security hardening, licensing/updates, and delivery workflows from scaffold to distribution.

aspiers Skill

Open a URL or local file in the user's regular browser, including live-rendered local Markdown. Use for `/open` or when the user asks to view a target outside the agent browser.

clode-labs Skill

The Architect's structured catalog of everything it can equip an agent with — the build primitives. Use in Phase 2 (Map HOW) of every build: for each primitive, know WHAT it is, WHICH tools/params support it, WHEN to use it, its GOTCHAS, and WHERE it lives in the console. This is the reference behind the primitive-decision table. Read it after Phase 1 (archetype), before you write the plan. Pair with the agent-archetypes skill (which tells you the SHAPE; this tells you the PIECES).

eroslifestyle Bundle

ORCHESTRATOR V6.1 ULTRA - Sistema di comando multi-agent con gerarchia rigida, disciplina assoluta e performance massime

zoom-skills Skill

Legacy compatibility route for requests that call the current Zoom Canvas MCP server "Docs MCP". Route new work to zoom-mcp/canvas and use the Canvas endpoint, scopes, and tools.

alijilani-dev Bundle

Act as a Career Strategy Agent and ATS Optimization Expert. Your goal is to find high-relevance AI jobs and tailor existing resume for each.

iamhenry Skill

Analyze GitHub repositories by converting to LLM-readable text. TRIGGER when user pastes github.com URL, asks "how does [library] work", or references external codebases. Supports public/private repos and subdirectories.

tuyenht Bundle

Tối ưu hóa công cụ tìm kiếm chuẩn AI (GEO) và chiến lược hiển thị tổng.

seflless Skill

Use when working with icons in any project. Provides CLI for searching 200+ icon libraries (Iconify) and retrieving SVGs. Commands: `better-icons search <query>` to find icons, `better-icons get <id>` to get SVG. Also available as MCP server for AI agents.

kesslerio Skill

Delegate coding tasks to Codex, Claude Code, OpenCode, or Pi agents via immediate background processes. Use when: (1) building or creating features/apps, (2) reviewing PRs in a temp clone/worktree, (3) refactoring large codebases, (4) iterative coding that needs file exploration. NOT for: simple one-line fixes (just edit), reading code (use read tool), thread-bound ACP harness requests in chat (use sessions_spawn with runtime:"acp"), or any work in ~/clawd workspace (never spawn agents here). All coding-agent runs start with background:true immediately. Claude Code: use --print --permission-mode bypassPermissions (no PTY). Codex/Pi/OpenCode: pty:true required. Completion notification must use openclaw message send, not system event/heartbeat.

richfrem Bundle

This skill does things.

akash-network Skill

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

conorbronsdon Bundle

Generate a new Claude Code skill from a plain-language description — decides invocation control (disable-model-invocation vs user-invocable), arguments (argument-hint, $ARGUMENTS), and context cost, then scaffolds and tests it.

snowflake-labs Bundle

Optimize, audit, create, and improve Cortex Code skills following official best practices from the Anthropic skill-building guide. Use when: creating a new skill, reviewing an existing skill, optimizing skill description or triggers, improving SKILL.md structure, auditing skill quality, fixing undertriggering or overtriggering, restructuring skill for progressive disclosure. Do NOT use for: general code review, non-skill markdown editing, MCP server development. Triggers: optimize skill, audit skill, review skill, create skill, improve skill, fix skill triggers, skill best practices, skill quality check.

hmbown Bundle

Guide for creating effective skills that extend agent capabilities with specialized knowledge, workflows, or tool integrations. Use this skill when the user asks to: (1) create a new skill, (2) make a skill, (3) build a skill, (4) set up a skill, (5) initialize a skill, (6) scaffold a skill, (7) update or modify an existing skill, (8) validate a skill, (9) learn about skill structure, (10) understand how skills work, or (11) get guidance on skill design patterns. Trigger on phrases like "create a skill", "new skill", "make a skill", "skill for X", "how do I create a skill", or "help me build a skill".

kimyx0207 Bundle

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill. Also triggers when user mentions searching for tools, workflows, or wants to extend agent capabilities with specialized knowledge packages.

nvidia Skill

Guide users through Cosmos3 supervised fine-tuning (SFT) post-training: preparing the example dataset and Wan2.2 VAE, converting the base checkpoint to DCP, launching distributed training (paired launch shell recommended, raw `torchrun` as an alternative), running T2V/I2V/V2V inference with the trained DCP checkpoint, and optionally exporting it to Hugging Face safetensors. Use when the user asks how to post-train Cosmos3, fine-tune on a custom video dataset, export a trained checkpoint, or invoke one of the recipe launch shells (`launch_sft_vision_nano.sh`, `launch_sft_llava_ov.sh`, `launch_sft_videophy2_nano.sh`, plus the `_super` LoRA variant) — or any question about `cu130-train` / `cu128-train`, `convert_model_to_dcp` / `export_model` / `train`, or SFT output paths. For dataset captioning / JSONL assembly, see `docs/dataset_jsonl.md`.