AI Ml AI Skills

A skill shipped by a composer-shaped local directory donor.

Guides the agent through creating and maintaining Capacitor plugins from scratch. Covers scaffolding a new plugin project, designing the TypeScript API, implementing native iOS (Swift) and Android…

Review VC term sheets for pre-seed, seed, and Series A rounds. Analyzes each clause from investor or startup perspective, identifies investor-friendly vs. founder-friendly terms, flags deviations from…

Deep-dive research using Codex, double-checked by a fresh verifier subagent. Use when asked "codex research", "deep dive with codex", "investigate this topic". Not for code review or plan…

从宋·陈言（陈无择）《三因极一病证方论》卷之五「五运时气民病证治」「六气时行民病证治」蒸馏出的运气用方「方源」层框架——十六方（五运十方 + 六气六岁方）的药物组成、炮制分量、主治、煎服法与随气加减，逐字照宋本底本。用于「按年干支回查运气用方」与「运气方源研读」，非临床处方指南。

Backward-compatible alias for ClawHub skill discovery and installation into the ClawLite workspace.

文档专家。专注于技术文档编写、API 文档生成、README 优化和文档维护。提供清晰的文档结构、规范的格式和用户友好的内容。

Trace what else a UX, flow, component, content, or design-system change could affect. Use when a designer asks "if we change this, what else moves?", "what else could this affect?", or wants to…

Flutter-specific implementation skill for polished web and mobile application UI.

Glitch Title Frame (Open Design) — use only when explicitly invoked, not for general design requests

Design or review touch-first mobile product behavior. Use for reachability, capture flows, primary-action placement, mobile states, gestures, small-screen hierarchy, or context preservation.

Add Google Assistant App Actions and Slices for Android (equivalent of iOS Siri Shortcuts). Use when the user says 'app actions android', 'google assistant integration', 'slices android'.

Implement UI that matches the existing product style without a Figma file

Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions

Bun as runtime, package manager, bundler, and test runner. When to choose Bun vs Node, migration notes, and Vercel support.

1-3-1 decision briefs: problem, three options, one pick.

Act on a Caveman learn report - review the ranked token sinks, apply cost-lowering fixes with per-edit consent, and report what those fixes returned. Use when asked to lower an agent's token cost,…

Audit a design against Dieter Rams' ten "Good design is..." principles, then hand off a /make-plan prompt for one of three outcomes — new design, refine design, or redesign. Use when the user says…

Use this skill instead of WebSearch for ANY question requiring web research. Trigger on queries like "what is X", "explain X", "compare X and Y", "research X", or before content generation tasks.…

Get or make any media for a HyperFrames video - music, sound effects, images, icons, logos, voiceover, avatar and generated video, transcripts, cutouts, colour grades and looks - with HeyGen or free…

Guided onboarding for OpenSpec - walk through a complete workflow cycle with narration and real codebase work. Also use when the user says "openspec onboard" or "opsx onboard".

Full PR lifecycle in a fresh task-owned git worktree: implement via the ulw-loop skill with mandatory evidence-bound manual QA → reviewer-readable English PR → verification loop (CI + Cubic, where…

Use when working with ComfyUI workflows in OpenMontage, including comfyui_image/comfyui_video/comfyui_music, custom workflow_json/workflow_path inputs, output_node selection, missing model setup,…

Review a skill-requested filesystem, command, network, secret, or destructive action against an explicit sandbox policy without executing it.

Facilitate a brainstorming session using diverse creative techniques. Use when the user says 'help me brainstorm' or 'help me ideate'

Expert-level browser automation, debugging, and performance analysis using Chrome DevTools MCP. Use for interacting with web pages, capturing screenshots, analyzing network traffic, and profiling…

Analyzes UEFI bootkit persistence (SPI flash implants, ESP modifications, Secure Boot bypass, UEFI variable manipulation) using chipsec for firmware integrity verification, detecting known families…

Use when cognee is slow, expensive, or hitting rate limits — speeding up or throttling ingestion (remember/cognify batching, chunk size, LLM and embedding rate limits, per-stage models), cutting read…

Use for GPU-accelerated data analysis on datasets, CSVs, or tabular data using NVIDIA cuDF. Triggers when tasks involve groupby aggregations, statistical summaries, anomaly detection, or large-scale…

Turn a fuzzy intention into a /goal objective the Goal verifier can actually judge - one outcome, numbered binary "Done when" checks that leave evidence in the transcript, guardrails, a budget, and a…

Convert a recorded or starred procedure into a reusable guide with verified steps and explicit gaps.

Generates code and provides documentation for the Genkit Dart SDK. Use when the user asks to build AI agents in Dart, use Genkit flows, or integrate LLMs into Dart/Flutter applications.

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations.…

Use when working with iii SDK APIs across Node.js, browser, Python, or Rust: package installation, worker initialization, function/trigger registration, invocation, channels, logging, OpenTelemetry,…

DEFAULT poster pipeline — build an academic conference poster (ICML/NeurIPS/ICLR/CVPR/...) as a single HTML/CSS file with measurement-driven hard gates, real paper figures, a two-hue design-token…

Expert knowledge for AI video clipping — yt-dlp downloading, whisper transcription, SRT generation, and ffmpeg processing

Backlink profile analysis: referring domains, anchor text distribution, toxic link detection, competitor gap analysis. Works with free APIs (Moz, Bing Webmaster, Common Crawl) and DataForSEO…

KubeSphere extension management Skill. Use when user requests to install, configure, upgrade, uninstall extensions, or query extension info/troubleshoot issues. Includes extension discovery,…

Codex-only writing and layout overlay for AI Berkshire investment research reports. Use whenever Codex creates, rewrites, revises, or critiques company/industry/fund research reports, especially…

Hunter mindset, recon setup, and target scoring for Web3 bug bounty. Use at the START of any new protocol hunt - scoring targets, setting up environment, understanding architecture.

Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-source…

Take an open pull request to green — wait for CI, triage failing checks, and answer review-bot comments — using one backgrounded observation per cycle. Use when monitoring or babysitting a PR, waiting…

Build a reporting or executive presentation where every slide title states a conclusion and the deck follows a pyramid, answer-first structure. Use when the user asks for a management update, board…

导入已有小说、逆向重建设定与续写工程，并区分母本参考。Use for importing manuscripts or attaching external canon safely.

Optimize Core Web Vitals (LCP, INP, CLS) for better page experience and search ranking. Use when asked to "improve Core Web Vitals", "fix LCP", "reduce CLS", "optimize INP", "page experience…

Query the per-turn DecisionEntry log for skill co-occurrence patterns, meta-skill usage stats, and the router fixture corpus. Returns a JSON summary suitable for downstream LLM consumption. Used by…

Create the SDD technical design and architecture approach. Trigger: orchestrator launches design for a change.

CyberStrikeAI 项目黑板：跨会话 Fact 图（SQLite）+ upsert_project_fact/record_vulnerability 边渗透边记录节奏、关系边 links、confidence、与多代理协调落库。Use when managing project facts, blackboard index, writing evidence, or avoiding…

更新飞书云文档。支持 7 种更新模式：追加、覆盖、定位替换、全文替换、前/后插入、删除。

Detect data leakage, missing boundaries, or privilege mismatch in inter-agent communication.

DeepChat app settings modification (DeepChat 设置/偏好) skill. Activate ONLY when the user explicitly asks to change DeepChat's own settings/preferences (e.g., theme, language, font size...). Do NOT…