AI Ml AI Skills

Search the Agent Wiki knowledge base. Use before web searching for technical knowledge.

Search, install, list, and update agent skills from ClawHub into ~/.clawlite/workspace.

当用户明确要求“测试项目”、 “运行 auto-test-project”或“进行项目级测试”时使用。对完整项目执行多轮 A 轮批判性测试与 B 轮质量检查，发现、记录、修复并验证问题。⚠️ 不适用：用户只是想优化功能、询问项目问题，或没有明确测试意图。

Interrogate a UX idea, requirement, flow, feature, or design direction before execution. Use when a designer asks to be challenged, wants assumptions exposed, wants a red-team review of the premise,…

Audit and fix HTML accessibility issues including ARIA labels, keyboard navigation, focus management, color contrast, and form errors. Use when adding interactive controls, forms, dialogs, or…

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a…

McKinsey/BCG-tier strategy decks. Dense, structured, signal-color callouts on neutral grounds. Use when the user asks for 'strategy', 'consulting', 'case', 'recommendation', 'McKinsey-style',…

Detect UX antipatterns (smells) in interface descriptions using the uxuiprinciples smell taxonomy. Returns structured findings with matched symptoms, severity, and step-by-step remediation recipes.…

Guide any team through the Design Thinking methodology — empathize, define, ideate, prototype, test, and implement. Core audiences: product & design teams (product designers, UX researchers, UI…

Deep design quality evaluation of AI-generated HTML against DESIGN.md. Use when the user wants to check if a generated screen looks like obvious AI output, assess design fidelity, or get actionable…

Cognitive accessibility pass for ADHD, autism, dyslexia, and neurodivergent users. Use for readability, plain language, predictability, sensory load, memory burden, time pressure, forms, onboarding,…

把 Figma 设计稿转成生产代码：Figma MCP 的取数与顺序、节点选择、令牌映射、翻译成项目既有约定、1:1 还原验收与差异定位。当用户给出 Figma 链接或 node-id、设计稿截图，要求实现设计、还原稿子、或抱怨「还原得不像」时使用。同时覆盖 Figma MCP 的连接与排错。

Use when designing, building, or reviewing any authentication surface — signup, login, logout, magic links, passkeys, OAuth/SSO buttons, password reset, 2FA/MFA, email verification, or session-expiry…

Creates and integrates coherent icons, illustrations, imagery and visual assets for web and mobile interfaces.

Xiaohongshu Card (Open Design) — use only when explicitly invoked, not for general design requests

Retrieve concise, graph-backed design context from AI Design Context with the local CLI. Use before implementing or reviewing a user-facing flow, reference fixture, prompt output, or known knowledge…

Independent adversarial code review via Codex CLI to eliminate Claude self-review bias

Structured code review when explicitly requested, preferring OpenAI/Codex before Claude.

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Development conventions and patterns for ECC. JavaScript project with conventional commits.

Integrate Firecrawl `/search` into product code and agent workflows. Use when an app needs discovery before extraction, when the feature starts with a query instead of a URL, or when the system should…

Use when writing or changing Vitest or React Testing Library tests under `web/` or `packages/dify-ui/`, or when the user explicitly requests frontend test strategy, including evaluation of an existing…

Quick-reference card for all ponytail modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /ponytail-help, "ponytail help", "what ponytail commands", "how do I use ponytail".

QA-test a website or web app and return a 1-5 quality score (5 = flawless, 1 = broken) with evidence. Use when the user wants to test, QA, evaluate, score, or "check how good" a site, page, flow, or…

Speak like a pirate.

Compress a memory file such as CLAUDE.md or a todo list into caveman format to save input tokens, keeping a readable backup. Trigger: /caveman-compress.

Use this when the user asks to search memory, "did we already solve this?", "how did we do X last time?", or wants work from previous sessions.

Evaluate and carry out non-trivial software-system changes from first principles. Use when assessing RFCs, issues, designs, features, refactors, migrations, dependency changes, or proposed fields,…

Process PDF files - extract text, create PDFs, merge documents. Use when user asks to read PDF, create PDF, or work with PDF files.

Automate Appdrag tasks via Rube MCP (Composio). Always search tools first for current schemas.

An orbiting camera follows an ice logo as it breaks apart, reforms into two text moments, and fades. HyperFrames block, 1920×1080, 22.5s, 216 variables.

Switches into OpenSpec docs-writing mode; loads the house style guide and drafts or revises pages in its voice (action-first, no preamble, scannable). Use when writing or editing pages in the OpenSpec…

Easter egg command - about oh-my-opencode. Triggers: omomomo, about, easter egg.

Publish an approved Orchard release

Display the current time in Pakistan Standard Time (PKT, UTC+5). Use when the user asks for the current time, Pakistan time, or PKT.

Generate AI videos from text prompts using multiple provider gateways. Use when: (1) Generating videos from text descriptions, (2) Creating AI-generated video clips for content production, (3)…

Use the ctx7 CLI to fetch library documentation, manage AI coding skills, and configure Context7 MCP. Activate when the user mentions "ctx7" or "context7", needs current docs for any library, wants to…

Required bmod metadata. Never invoke this skill.

Make sure to use this skill whenever the user wants to search for jobs in Denmark, find Danish job listings, look up a specific job posting, or asks anything about the Danish job market — even if they…

Evaluates and negotiates job offers. Decodes base, bonus, equity, sign-on, level and terms with unknowns kept unknown and each offer in its own currency, benchmarks against checkable pay data, finds…

Control Herdr, a terminal multiplexer for coding agents. Use only when the user explicitly mentions Herdr or asks to use Herdr to inspect or control panes, tabs, workspaces, commands, or another…

Examine NTFS slack space, MFT entries, the USN Change Journal, and Alternate Data Streams (ADS) to recover hidden or residual data, reconstruct deleted-file metadata, and reconstruct available…

Use this skill to build a multi-element Excel dashboard — Dashboard sheet on open, multiple formula-driven KPI cards, multiple charts, sparklines, and conditional formatting — from CSV or tabular…

GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction,…

Use when building your own cognee processing — writing custom tasks, chaining them into a pipeline with run_custom_pipeline or the lightweight run_pipeline (from cognee.pipelines import run_pipeline),…

Drafts engaging social media posts, writes hooks, suggests hashtags, creates thread structures, and generates companion images. Use when the user asks to write a LinkedIn post, tweet, Twitter/X…

Use this skill when working on the Repomix documentation website in `website/` directory, including VitePress configuration, multi-language content, or translation workflows.

Control the user's Chrome through the existing persistent Node REPL and the Qwen Browser SDK.

Use when the user wants to add, write, debug, or configure a Crush hook — gating or blocking tool calls, approving or rewriting tool input before execution, injecting context into tool results, or…

Retrieve and analyze Screenpipe CLI backend logs and desktop app logs for debugging

把一句话的想法拆成 AI agent 能独立跑完的目标任务书。用户说「帮我给 agent 写个目标」「帮我详细拆一下这个目标」「写个任务书/brief 给 agent」「写个 goal 提示词」「让 agent 自己跑这个项目」「把活分给几个 agent 并行」时使用。先进代码库实测、必要时联网调研，再一次性提问（≤5 个），产出一份 ≤4000 字符、直接粘进 /goal…