Skills

Platform-specific AI search optimization — audit and optimize for Google AI Overviews, ChatGPT, Perplexity, Gemini, and Bing Copilot individually

This skill should be used when the harness, scaffold, workflow, or optimizer itself is the optimization target: recursive self-improvement (RSI) loops, meta-harnesses, self-improving harnesses that mine their own failures and propose bounded edits, evolutionary or population-based search over agent scaffolds, acceptance gates for self-modifying systems, and agentic context evolution where the mechanism that produces context is versioned and evolved. Route governance of a single autonomous loop (locked surfaces, durable logs, rollback, novelty gates, approval boundaries) to harness-engineering, measurement and quality-gate design to evaluation, judge design to advanced-evaluation, and remote sandbox infrastructure to hosted-agents.

>-

Use the mcpc CLI to work with MCP (Model Context Protocol) servers from the shell - connect to a server as a persistent session, then list and call tools, read resources, get prompts, and run async tasks. Use --json for scripting and code mode. Reach for this whenever interacting with MCP servers, calling MCP tools, or accessing MCP resources programmatically.

Shellcode development reference for offensive security engagements. Use when writing custom x86/x64 shellcode, implementing position-independent code (PIC), building shellcode loaders, evading AV/EDR detection, or converting PE files to shellcode. Covers null byte avoidance, API hashing, encoder/decoder patterns, staged vs stageless payloads, Windows PEB traversal, and cross-platform shellcode techniques.

AWS DynamoDB single-table design, GSI patterns, SDK v3 TypeScript/Python

Example skill demonstrating Anthropic SKILL.md format. Load when learning to create skills or testing the OpenSkills loader.

Calculate A/B test statistical significance. Use when: determining if test results are significant; calculating required sample size; estimating test duration; analyzing conversion experiments; making data-driven decisions

Clarify intent before RIPER-5 phase delegation. Scores ambiguity (4 signals); generates structured multi-choice questions for Tier 2. Two-mode: SIMPLE and DEEP.

|

>

Upgrades existing websites and apps to premium quality. Audits current design, identifies generic AI patterns, and applies high-end design standards without breaking functionality. Works with any CSS framework or vanilla CSS.

Use trace-mcp tools for code navigation, impact analysis, and framework-aware queries instead of Read/Grep/Glob/Bash. Activate whenever the agent needs to explore, understand, or modify a codebase that has trace-mcp indexed.

|

Import/export textures crash-safely, query the Content Browser selection, and check if an asset is open (AssetDiscoveryService). Search, load, save, move, rename, duplicate, and delete assets are handled by Unreal's native AssetTools toolset or EditorAssetLibrary. Use when the user asks to import an image from disk, export a texture, query the Content Browser selection, or check whether an asset is open in an editor.

High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.

Create professional, dark-themed SVG diagrams of any type — architecture diagrams, flowcharts, sequence diagrams, structural diagrams, mind maps, timelines, illustrative/conceptual diagrams, and more. Use this skill whenever the user asks for any kind of technical or conceptual diagram, visualization of a system, process flow, data flow, component relationship, network topology, decision tree, org chart, state machine, or any visual representation of structure/logic/process. Also trigger when the user says "画个图" "画一个架构图" "diagram" "flowchart" "sequence diagram" "draw me a ..." or uploads content and asks to visualize it. Output is always a standalone .svg file.

Complete visual content system for Claude Code. Default aesthetic - light backgrounds, teal/burnt orange accents, hand-drawn sketch style.

>-

Consolidate IBRK trade CSV files from a directory into a summary report. Groups trades by symbol, underlying, date, strike, buy/sell, and open/close. Outputs both markdown and CSV.

钉钉电子表格。Use when 用户说 电子表格/工作表/单元格读写/单元格追加/查找/公式/超链接/插入图片/浮动图片/sheet。Distinct from dingtalk-aitable(AI表格/多维表/字段类型)、dingtalk-doc(普通文档)。命令前缀：dws sheet。

Word / PDF / PPT 文档解析与数据分析引擎。覆盖三类文件格式的全量提取、表格数值化、图表理解与跨文档汇总分析。**遇到以下任一情况就主动使用本 skill**：①用户上传或指定了 .docx / .doc / .pdf / .pptx / .ppt 文件并要求分析、提取或统计其中内容；②用户出现触发词：Word分析 / PDF解析 / PPT提取 / 文档分析 / 报告解析 / 幻灯片分析 / 发票提取 / 合同分析 / 文档统计 / 错别字 / 语病 / 字号检查 / 简历分析 / 多文档对比；③任务涉及从文档中提取表格、数值、图表、格式（颜色/高亮/字号）、组织架构、时间线等结构化信息。仅不用于：Excel/CSV 数据分析（使用 sn-da-excel-workflow）、纯图片分析（使用 sn-da-image-caption）。

Use when the user mentions in-app purchase review, IAP audit, StoreKit issues, purchase bugs, transaction problems, or subscription management.

E2E testing with Playwright - Page Objects, cross-browser, CI/CD

Full safety mode: destructive command warnings + directory-scoped edits. (gstack)

Events and attendees with optional polymorphic links to CRM records.

Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.

Audit and rewrite content to remove AI writing patterns ("AI-isms"). Use this skill when asked to "remove AI-isms," "clean up AI writing," "edit writing for AI patterns," "audit writing for AI tells," or "make this sound less like AI." Supports a detect-only mode, an edit-in-place mode for files, an optional voice profile (casual / professional / technical / warm / blunt), and an iterate-to-convergence pass.

Spec-driven development workflow. Interactive phase-by-phase confirmation from proposal to implementation. Trigger: 'spec-flow', 'spec mode', 'need a plan', 'structured development', 'write a spec', 'feature spec', 'technical spec', '需求文档', '技术方案', '任务拆解', '规格驱动', '写个方案', '做个规划', '结构化开发', 'plan this feature', 'break this down', 'design doc'. Creates .spec-flow/ directory with proposal, requirements, design, and tasks.

>

Advanced Hive Mind collective intelligence system for queen-led multi-agent coordination with consensus mechanisms and persistent memory

Comprehensive quality verification: spec compliance, lint, type-check, tests, cross-layer data flow, code reuse, and consistency checks. Use when code is written and needs quality verification, before committing changes, or to catch context drift during long sessions.

|

Run and ship this repo: make targets, artifacts, release runbook. Use when testing, linting, or releasing. Do not use for setup; use night-market-build-and-env.

Use when the user says: 'ijfw status', 'show me the system state', 'what is ijfw doing', or to see the at-a-glance routing / memory / activity banner.

Fetch comprehensive, login-free data for any Bilibili (B站) video — title, UP name and follower count, publish date, partition, tags, per-part cids, live stats (view, like, coin, favorite, share, reply, danmaku), and full danmaku (bullet-comment) text. Use this skill whenever working with a Bilibili video and needing real, citable numbers or metadata — ingesting a Bilibili source into a knowledge base, analyzing why a video performed, verifying a creator's claimed metrics, building a case study, or any time a Bilibili view/like/favorite count is about to be written into a document — fetch it, never hand-type or estimate it. Accepts BVID, av numbers, b23.tv short links, or full URLs. Subtitles are also covered but require the user's Bilibili login.

Practical offensive fuzzing methodology covering target identification, fuzzer selection (AFL++, libFuzzer, Honggfuzz, Boofuzz, syzkaller), harness writing, corpus curation, mutation strategies, coverage measurement, and crash triage. Use when setting up or running fuzz campaigns against any target: file parsers, network protocols, kernel drivers, EDR engines, embedded firmware, or language runtimes.

Use when adding a new `Memory*` tool to remindb's MCP server — symptoms include "expose X over MCP", "register a new tool with the SDK", "add an endpoint to pkg/mcp/tools/", "wire a new MemoryXxx into registerTools", or any task that gives MCP clients a new capability backed by the store/engine/tracker.

Scan stocks for bullish trends using technical indicators (SMA, RSI, MACD, ADX). Use when user asks to scan for bullish stocks, find trending stocks, or rank symbols by momentum.

AI-native, open-source backend-as-a-service with a built-in Model Context Protocol server. Postgres, auth, storage, functions, AI gateway.

Transform podcast transcripts into multiple content assets—blog posts, social snippets, newsletters, and SEO-optimized landing pages—using systematic repurposing workflows. Use when: Maximizing ROI from podcast episodes; Creating blog content from audio/video; Generating social media posts from long-form content; Building newsletter content from transcripts; Extracting quotes and highlights for promotion

Fetch any URL and convert to markdown using baoyu-fetch CLI (Chrome CDP with site-specific adapters). Built-in adapters for X/Twitter, YouTube transcripts, Hacker News threads, and generic pages via Defuddle. Handles login/CAPTCHA via interaction wait modes. Use when user wants to save a webpage as markdown.

|

Detect and fix AI-generated writing patterns (slop). Comprehensive detection with 45+ patterns across 3 severity tiers, scoring system, and editor mode that directly fixes problems. Use when scanning any content for AI tells, auditing drafts before publishing, checking if writing "sounds like AI", humanizing AI-generated text, or verifying content authenticity. Trigger on "check for slop", "does this sound like AI", "humanize this", "AI audit", "slop check", "clean up AI writing", or any request to detect/remove artificial-sounding patterns. Also use proactively before publishing any AI-assisted content.

Create polished dark-themed architecture diagrams as self-contained HTML+SVG files. Use when the user asks for system, infrastructure, cloud, security, or network topology diagrams.

Diagnoses Kirby rendering/runtime issues using MCP runtime rendering, dump traces, and template/snippet/controller indexes. Use when outputs are wrong, errors occur, or tracing execution paths is required.

Transform learning content (like YouTube transcripts, articles, tutorials) into actionable implementation plans using the Ship-Learn-Next framework. Use when user wants to turn advice, lessons, or educational content into concrete action steps, reps, or a learning quest.

Guides users through professional filmmaking workflows in Higgsfield Cinema Studio, including creating multi-shot sequences, configuring optical stacks, applying color grading, managing Soul Cast AI actors, and structuring per-scene prompts with Director Panel camera movements. Use when the user mentions Cinema Studio, Cinema Studio 2.5, Cinema Studio 3.0, Soul Cast, color grading, multi-shot video, shot sequences, storyboard workflow, Hero Frame, optical stack, keyframe interpolation, Elements system (@Characters/@Locations/@Props), Speed Ramp, Director Panel, Higgsfield Popcorn, Single Shot / Multi-Shot Auto / Multi-Shot Manual modes, Reference Anchor, Smart shot control, or any professional filmmaking workflow inside Higgsfield.