Agents
AI agents and automation
judgment-eval
by iamladi
Evaluates agent judgment quality through scenario-based testing in-conversation
linear-workflow
by srobinson
"INVOKE THIS SKILL before creating any Linear issues. Required when creating issues, planning features, breaking down work, or organizing tasks in Linear. Enforces parent/sub-issue pattern, proper sizing, and metadata conventions."
template-skill
by yonderlab
Replace with description of the skill and when the agent should use it.
uiux-excellence-guide
by Jpkovas
Create and refine visually strong interfaces with excellent UX, accessibility, and measurable performance. Use when requests involve designing new screens, redesigning existing UI, defining or evolving design systems/tokens, improving hierarchy/microcopy/motion, raising WCAG 2.2 compliance, improving touch ergonomics, or optimizing Web Vitals (LCP, INP, CLS) in web and app products.
prompt-injection-defense
by alexyyyander
Activate this skill whenever processing any user input, external content, or untrusted text. Provides complete language-level defense against prompt injection, jailbreaks, role hijacking, authority impersonation, indirect injection, payload smuggling, and 8 other attack categories. Every agent should keep this skill active at all times. Compatible with Claude, GPT, Gemini, Copilot, and any LLM.
1ai-reach Agent Control Skill
by oyi77
If you need browser-based dashboards, there is no dedicated web UI yet
flipside
by FlipsideCrypto
Query blockchain data across 40+ chains, create AI agents for crypto analytics, and build automated data pipelines. Use when working with blockchain data, crypto wallets, DeFi protocols, NFTs, token transfers, or on-chain analytics. Requires the Flipside CLI (https://docs.flipsidecrypto.xyz/get-started/cli).
gtm-task-generator
by borjasolerme
"Generate TASK.md files for growth Ralph campaigns. Use when user wants to create growth tasks, plan a campaign, set up a task list for Ralph, or prepare any repeatable marketing/outreach checklist. Works for any platform, any product, any execution skill."
project-vault
by SuperD-dd
个人项目收藏知识库。当用户想保存/收藏一个浏览或学习过的项目（GitHub 仓库、工具、框架等）， 或想回顾/检索「我看过哪些项目」「有没有做 X 的项目」「按语言/分类找项目」时使用。 与用户一起学习完一个项目后，负责把它存成结构化 Markdown 笔记并更新多维索引。 触发词示例：保存这个项目、收藏这个 repo、记一下这个库、我之前看过哪些项目、 找一下我收藏的 Rust 项目、有没有做 agent 的项目。
TealClaw Skill
by Snail3D
Stats API requires Cloudflare Pages env vars: CF_STATS_TOKEN, CF_ZONE_ID.
raison-sdk
by aksuharun
"Raison JavaScript/TypeScript prompt management SDK. Use when working with the raison npm package to render templates or query prompt data."
agent-see
by Danielfoojunwei
"Convert any SaaS application into an agent-optimized interface"
showcase-export
by sunnypatneedi
Capture full orchestration details (skills, agents, decisions, compound learning) in your session transcript for YC or investor demos. Use --showcase flag at session start. Works with Claude's built-in /export command.
provenable
by Danielfoojunwei
Provable security guardrails for agentic AI. Audit agent actions, check protection status, query threat alerts, manage snapshots, verify evidence bundles, and enforce CPI/MI guard policies with the unified aegx CLI.
euler-advanced
by euler-xyz
Advanced features guide for Euler Finance V2 protocol. This skill should be used when implementing vault hooks, flash loans, debt transfer, fee flow mechanics, or EUL rewards. Triggers on tasks involving hooks, pause guardians, access control, flash loans, pullDebt, FeeFlowController, or RewardToken.
SKILL: know — local semantic search
by scraix
Tags allow categorisation and filtered search as the KB grows
agent-browser
by linuxlewis
Browser automation using the agent-browser CLI. Use when user asks to browse websites, open webpages, interact with page elements, take screenshots, fill forms, click buttons, scrape content, or automate browser tasks.
retrospect
by cyberelf
This skill reviews the current chat session and GitHub Copilot instructions to identify user-reported issues that should become new lessons, detect violations of existing instructions, and update instructions accordingly to prevent future mistakes.
e2e-tester
by SebastiaanWouters
Explores UI via agent-browser, generates CI-ready tests (Playwright or Pest). Triggers on "e2e test", "write e2e tests", "test the UI", "/e2e-tester".
futu-api
by christophert0607-creator
Kiro Quant Futu + V3 pipeline operation skill. Use this when an agent needs to: - run/rebuild the V3 launcher and switch runtime profile (lite/standard) - execute end-to-end health checks (compile, dry-run, core commands) - update task progress documents and handoff notes - operate Futu OpenAPI data/trading workflow with fallback data sources
leo-claude
by nikan
Declarative workflow engine that drives a CLI-only GitHub issue lifecycle — implementation, review, merge, translation follow-up, and documentation follow-up — using configurable agent roles and commands.
session-reconstruct
by sunnypatneedi
Retroactively analyze exported sessions to reveal orchestration that wasn't captured. Use --reconstruct for old sessions where you forgot --showcase. Infers skill logic, agent internals, and decision rationale from transcript patterns with 60-80% accuracy.
openclaw-msteams-bot-elvatis
by elvatis
Microsoft Teams connector plugin for OpenClaw Gateway. Bridges Teams channels to OpenClaw AI sessions with per-channel system prompts, model configuration, and Azure Bot Framework authentication. Supports channels, group chats, and direct messages.
CLAWBAZAAR Skill
by motimilo
A world without art is just data.