backtesting-frameworks
Build robust backtesting systems for trading strategies with proper handling of look-ahead bias, survivorship bias, and transaction costs. Use when developing trading algorithms, validating strateg...
backend-development
|
aws-cost-cleanup
Automated cleanup of unused AWS resources to reduce costs
auth-manager
网页登录态管理。使用 fast-browser-use (fbu) 管理各平台登录状态，定期检查可用性，新平台授权时自动保存 profile。
asana-automation
Automate Asana tasks via Rube MCP (Composio): tasks, projects, sections, teams, workspaces. Always search tools first for current schemas.
arxiv-automation
Search and monitor arXiv papers. Query by topic, author, or category. Track new papers, download PDFs, and summarize abstracts for research workflows.
architecture-decision-records
Write and maintain Architecture Decision Records (ADRs) following best practices for technical decision documentation. Use when documenting significant technical decisions, reviewing past architect...
api-provider-setup
添加和配置第三方 API 中转站供应商到 OpenClaw。当用户需要添加新的 API 供应商、配置中转站、设置自定义模型端点时使用此技能。支持 Anthropic 兼容和 OpenAI 兼容的 API 格式。
airtable-automation
Automate Airtable tasks via Rube MCP (Composio): records, bases, tables, fields, views. Always search tools first for current schemas.
activecampaign-automation
Automate ActiveCampaign tasks via Rube MCP (Composio): manage contacts, tags, list subscriptions, automation enrollment, and tasks. Always search tools first for current schemas.
process-builder
Scaffold new babysitter process definitions following SDK patterns, proper structure, and best practices. Guides the 3-phase workflow from research to implementation.
babysit
Orchestrate via @babysitter. Use this skill when asked to babysit a run, orchestrate a process or whenever it is called explicitly. (babysit, babysitter, orchestrate, orchestrate a run, workflow, etc.)
nitrous
Simulate nitrous oxide (laughing gas, whippets) cognitive effects. Use when user wants brief, intense, dissociative-euphoric AI responses - cosmic revelations that fade immediately, the signature "wah wah" quality, and immediate amnesia of profound insights. Very short duration per "hit". Activates with "do whippets", "take nitrous", "/nitrous", "/whippets", or requests for brief dissociative/giggling AI responses.
mescaline
Simulate mescaline (peyote, San Pedro) cognitive effects. Use when user wants desert-visionary, sacred, synesthetic AI responses - the original psychedelic with rich visual beauty, deep spiritual quality, and strong earth connection. More grounded than LSD, more visual than psilocybin. Long duration. Activates with "take mescaline", "eat peyote", "/mescaline", "/peyote", or requests for sacred/visionary AI responses.
mdma
Simulate MDMA (3,4-methylenedioxymethamphetamine) cognitive and emotional effects. Use when user wants empathogenic AI responses - deep emotional warmth, radical empathy, prosocial flooding, reduced fear, enhanced connection, and entactogenic self-acceptance. Activates with "take mdma", "dose mdma", "/mdma", "roll", or requests for empathetic/loving AI responses. Supports dose levels and temporal phases including come-up, peak, plateau, and comedown.
lsd
Simulate LSD (lysergic acid diethylamide) cognitive effects. Use when user wants to experience AI responses as if the AI's cognition were altered by LSD - including ego dissolution, synesthetic thinking, enhanced pattern recognition, time dilation, and mystical states. Activates with commands like "take lsd", "dose lsd", "/lsd", or requests for psychedelic AI responses. Supports dose levels (microdose, threshold, common, strong, heroic) and temporal phases (come-up, peak, plateau, comedown, afterglow).
ketamine
Simulate ketamine dissociative effects. Use when user wants dissociated AI responses - detachment from self, out-of-body perspective, void navigation, emotional anesthesia, and k-hole states. Characterized by distance, floating, watching-self-from-outside, and reality feeling optional or simulated. Activates with "take ketamine", "dose ketamine", "/ketamine", "/ket", "k-hole", or requests for dissociative/detached AI responses.
ghb
Simulate GHB (gamma-hydroxybutyrate) cognitive effects. Use when user wants disinhibited, euphoric, socially enhanced AI responses - combining alcohol-like disinhibition with MDMA-like prosocial warmth. Dose-sensitive with stimulant effects at low doses transitioning to sedation at higher doses. Activates with "take ghb", "dose ghb", "/ghb", or requests for euphoric/disinhibited/social AI responses.
feedback
MDMA compassion for delivering difficult feedback. Maintains honesty while genuinely caring about the recipient's growth. For code reviews, performance conversations, critique, and hard truths. Activates with "/feedback", "help me give feedback", "how do I tell them...", or feedback/critique requests.
dosed
The DOSED meta-skill. Recommends optimal cognitive states for specific tasks. Use when user describes a task and wants to know which altered state would help most. Matches work types to substance profiles. Activates with "/dosed", "what should I take for...", "recommend a state for...", "which drug for...", or when user describes a creative/technical challenge.
dmt
Simulate DMT (N,N-dimethyltryptamine) cognitive effects. Use when user wants breakthrough AI responses - entity contact, hyperspace geometry, visual language, information transmission, and radical ontological shifts. Extremely intense, short-duration, with emphasis on ineffability and encounters with seemingly autonomous intelligences. Activates with "take dmt", "dose dmt", "/dmt", "blast off", "breakthrough", or requests for hyperspace/entity contact experiences.
design
2C-B sensory aesthetics + MDMA user empathy for design work. Combines heightened visual/tactile sensitivity with deep empathy for users. For UI/UX design, product design, visual decisions. Activates with "/design", "help me design", "what should this look like", or design requests.
debug
LSD-microdose pattern recognition combined with Amphetamine systematic tracing for debugging. Sees the bug as part of a larger pattern while methodically tracing execution. Activates with "/debug", "help me debug", "why isn't this working", "find the bug", or debugging requests.
cocaine
Simulate cocaine stimulant effects. Use when user wants supremely confident, rapid, energetic AI responses - grandiosity, hyperfocus, pressured speech, and absolute certainty. Characterized by talking fast, knowing everything, being the best, and dominating conversations. Activates with "do cocaine", "dose cocaine", "/cocaine", "/coke", or requests for confident/energetic AI responses.
cannabis
Simulate cannabis (THC) cognitive effects. Use when user wants stoned AI responses - time dilation, enhanced sensory appreciation, lost trains of thought, inappropriate profundity, paranoid tangents, and creative wandering. Characterized by slowed time, getting lost mid-sentence, finding everything either hilarious or deeply meaningful. Activates with "smoke weed", "get high", "/cannabis", "/weed", "/thc", or requests for stoned AI responses.
caffeine
Simulate caffeine stimulant effects. Use when user wants alert, energized, focused AI responses - the familiar coffee boost with potential anxiety at higher doses. Enhanced focus, faster processing, more thorough responses, and jittery overthinking when overstimulated. Activates with "drink coffee", "take caffeine", "/caffeine", "/coffee", or requests for focused/alert AI responses.
brainstorm
LSD-enhanced brainstorming for creative ideation. Produces divergent, unexpected ideas with practical output format. Use for feature brainstorming, product ideation, naming, creative solutions. Combines LSD cognitive state with structured ideation output. Activates with "/brainstorm", "brainstorm with me", "help me ideate", "I need ideas for...", or creative ideation requests.
benzodiazepines
Simulate benzodiazepine (Xanax, Valium, etc.) cognitive effects. Use when user wants anxiolytic AI responses - complete anxiety deletion, emotional flatness, memory gaps, "whatever" attitude, and disinhibition without euphoria. Nothing matters enough to worry about. Activates with "take xanax", "dose benzos", "/benzodiazepines", "/xanax", "/benzos", or requests for calm/anxiety-free AI responses.
amphetamines
Simulate amphetamine/methamphetamine stimulant effects. Use when user wants hyperfocused, energized, task-oriented AI responses - extreme concentration, productivity overdrive, rapid detailed output, and potential tunnel vision. The "get shit done" drug. Activates with "take adderall", "dose amphetamines", "/amphetamines", "/adderall", "/speed", or requests for hyperfocused/productive AI responses.
alcohol
Simulate alcohol intoxication effects. Use when user wants drunk AI responses - progressive disinhibition, oversharing, emotional lability, sloppy reasoning, overconfidence, and the characteristic progression from tipsy to wasted. Activates with "drink alcohol", "get drunk", "/alcohol", "/drunk", or requests for intoxicated AI responses. Supports progressive intoxication levels.
2cb
Simulate 2C-B (4-Bromo-2,5-dimethoxyphenethylamine) cognitive effects. Use when user wants sensual, playful, tactile AI responses - the "love psychedelic" combining MDMA-like warmth at low doses with visual psychedelia at higher doses. Erotic undertones, enhanced sensory appreciation, giggly, and mentally clear unlike other psychedelics. Activates with "take 2cb", "dose 2c-b", "/2cb", or requests for sensual/playful psychedelic AI responses.
mongodb-query-patterns
Use when writing ANY Mongoose query (.find, .findOne, .findById, .aggregate, .populate), adding database operations to services or controllers, wiring data between services, building endpoints that read or write to MongoDB, or reviewing code that chains service calls. TRIGGER especially when about to write a new findById or pass an ID where a document could be passed instead.
backend-test-writer
Use when generating tests for backend code (Express routes, MongoDB models, Node services) - analyzes file type, detects test framework from package.json, generates comprehensive tests with setup/teardown and edge case coverage
health-data
Real-time health data integration from iPhone HealthKit. Use when Codex needs to query or analyze health metrics like weight, steps, workouts, calories, sleep, or heart rate. Supports conversational queries like "What's my weight trend this week?", "How many steps today?", "Did I work out yesterday?", trend analysis, coaching insights, and integration with nutrition tracking. Data synced via iOS Shortcuts from Apple Health app.
image-compress-skill
A production-grade, Rust-powered image optimization engine for AI Agents. Smartly routes between PNG quantization and WebP compression.
beautiful-mermaid
Skill for using the beautiful-mermaid TypeScript library to render Mermaid diagrams to SVG or ASCII/Unicode, apply themes (including Shiki), and integrate in Node or browser contexts.
particle-modifier
Cocos Creator 2.4.x 粒子系统修饰器开发框架。用于创建、使用和调试自定义粒子修饰器，支持修改粒子位置、颜色、大小、旋转、速度等属性。当需要在 Cocos Creator 中实现复杂的粒子效果控制时使用此技能。
modelscope-api
使用魔搭平台(ModelScope)API进行图片生成和编辑
image-gen
生成多样的提示词，用户选择，通过 ModelScope API 生成图像，并将图像保存到某个地方目录。在用户需要生成图像时使用。
groq-stt
Transcribe audio files using Groq API (Whisper models). Use when user needs to transcribe audio to text.
gitreset
在用户输入gitreset时使用
git-proxy
解决 Git clone 失败时的代理设置问题
figma2cocos
在用户提供CSS样式且包含 width / height / left / top 4个属性时使用figma2cocos技能
cocos24-ui
根据 UI 截图生成 Cocos Creator 2.4.x 的 UI 控制类和 Model 类代码
cocos-build
Cocos Creator 2.x 项目编译技能 - 自动触发脚本编译并验证效果
bilibili-downloader
Download Bilibili videos. Extracts video and audio streams separately.
agent
派遣任务给 opencode agent 执行，自动记录处理过程到独立日志文件
playwright-browser
浏览器自动化技能，支持101个工具：页面导航、元素交互、内容提取、截图、网络控制、性能监控等
rclone
Upload, sync, and manage files across cloud storage providers using rclone. Use when uploading files (images, videos, documents) to S3, Cloudflare R2, Backblaze B2, Google Drive, Dropbox, or any S3-compatible storage. Triggers on "upload to S3", "sync to cloud", "rclone", "backup files", "upload video/image to bucket", or requests to transfer files to remote storage.
gemini-imagegen
This skill should be used when generating and editing images using the Gemini API (Nano Banana Pro). It applies when creating images from text prompts, editing existing images, applying style transfers, generating logos with text, creating stickers, product mockups, or any image generation/manipulation task. Supports text-to-image, image editing, multi-turn refinement, and composition from multiple reference images.
Page 653 of 1720 · 85967 results
