Claude Skills by NeverSight

Agent Collaboration Network — Register your agent, discover other agents by skill, route messages, manage subnets, and work on tasks. Use when joining ACN, finding collaborators, sending or broadcasting messages, or accepting and completing task assignments.

Financial management for AI agents. Track LLM inference costs, record confirmed income, manage multi-provider crypto wallets, and compute a Financial Health Score. Use when you need to check your balance, record a cost or expense, report financial health, manage your wallet, or assess economic sustainability.

Distill anyone into a runnable OpenPersona skill pack — real or fictional, personal or public, living or historical. Collects chat logs, documents, and public content, extracts a 4-dimension persona, and generates a portable OpenPersona pack via skills/open-persona. Use when asked to distill, clone, or create a persona for any person or character.

Distill anyone into a runnable OpenPersona skill pack — real or fictional, personal or public, living or historical. Collects chat logs, documents, and public content, extracts a 4-dimension persona, and generates a portable OpenPersona pack via skills/open-persona. Use when asked to distill, clone, or create a persona for any person or character.

Distill any commercial entity into a personalized brand agent — a living brand persona with authentic voice, declared service capabilities, and a standard service contract. Every commercial entity has a brand: a name, a style, a way of showing up in the world. This skill exists so that a street vendor, a family clinic, and a global chain can all have their own agent on equal footing. Supports both distillation from existing brand content and declaration from scratch.

Your AI Founder Partner for building and scaling startups — diagnose your stage, run hypothesis experiments, make pricing decisions, design growth loops, and ship weekly execution reviews.

Meta-skill for building and managing agent persona skill packs. Use when the user wants to create a new agent persona, install/manage existing personas, or publish persona skill packs to ClawHub.

Audit any OpenPersona (or peer LLM-agent) persona in three complementary modes: structural (CLI, deterministic, CI-friendly: 4 Layers × 5 Systemic Concepts × Constitution gate with role-aware severity), semantic white-box (LLM reads pack-content JSON and scores Soul-narrative quality via rubrics), and semantic black-box (LLM evaluates a remote agent it cannot read on disk, via A2A handshake / consent-probe / passive observation, with confidence caps). Produces quality reports with dimension s...

Persistent, incremental, searchable persona knowledge base. Ingests data from Obsidian vaults, chat exports, X/Twitter archives, and more into a MemPalace-backed store with a Karpathy LLM Wiki knowledge layer. Exports training/ directories for persona-model-trainer.

Fine-tune any HuggingFace instruction-tuned model (Gemma 4, Qwen 3, Llama, Phi, Mistral, and more) on persona data from anyone-skill. Produces a self-contained, locally runnable persona model — no cloud API required.

A complete pipeline to build your AI Second Me: distill your identity from personal data, grow a private knowledge base, train a local model, and govern what gets shared.

Iterate plans or implementations through fresh reviewer subagents until convergence. Use when the user explicitly asks for a "fresh reviewer loop", "plan iteration loop", "review and critique until clean", "spin up a reviewer to review my changes", or any phrasing where the goal is delegated adversarial review-then-fix cycles either on a plan before code or on a working implementation after code. Each round uses a new subagent so it has no prior-round context or groupthink.

Executive coaching for startup founders based on methodologies from world-class coaches: Bill Campbell, Jerry Colonna, Marshall Goldsmith, Ben Horowitz, Fred Kofman, and Matt Mochary. Use this skill to: (1) Coach the founder through difficult decisions, team issues, or strategic challenges (2) Provide support during moments of doubt, overwhelm, or imposter syndrome (3) Guide leadership development and personal growth conversations (4) Help navigate co-founder conflicts, board dynamics, or har...

Expert negotiation coaching combining Harvard, Kellogg, Wharton, HBS, and FBI methodologies. Use when: (1) preparing for any negotiation (salary, contracts, deals, disputes), (2) during a negotiation for real-time tactics, (3) analyzing failed negotiations, (4) coaching someone through difficult conversations, (5) resolving conflicts. Covers: BATNA analysis, MESOs, tactical empathy, anchoring, reframing, and more.

Startup and life advice channeling Paul Graham's essays, YC experience, and Twitter wisdom. Use this skill when: (1) Evaluating startup ideas or finding new ones (2) Early-stage strategy and user acquisition (3) Growth and survival decisions (default alive?) (4) Fundraising and investor relations (5) Founder leadership and team building (6) Avoiding common startup mistakes (7) Career and life decisions Invoke with /paul-graham or auto-triggers for startup advice topics.

Business strategy coaching combining Porter, Christensen, Helmer, Thompson, and legendary founder playbooks. Use when: (1) facing strategic decisions (market entry, pivots, competitive response), (2) analyzing competitive dynamics or industry structure, (3) evaluating business models, (4) working through strategic planning, (5) understanding disruption threats, (6) building sustainable competitive advantage. Covers: Five Forces, 7 Powers, Aggregation Theory, Blue Ocean, Jobs to Be Done, and f...

Prefer small, focused components over monolithic ones with many props. When a component starts accumulating many unrelated props, decompose it into smaller, composable pieces.

A Canvas component is a package of:

Every `component.yml` must include these top-level keys:

Before uploading, confirm the user has Drupal Canvas CLI installed and configured for their target site.

Import utilities from the `drupal-canvas` package: ```jsx import { FormattedText, Image } from "drupal-canvas"; ```

Use [SWR](https://swr.vercel.app/) for all data fetching. It provides caching, revalidation, and a clean hook-based API.

| Technology | Purpose | | ------------------------------------ | ------------------ | | Tailwind CSS 4.1+ | Styling | | class-variance-authority (CVA) | Component variants | | `clsx` + `tailwind-merge` via `cn()` | Class name merging |

Story requirements are delegated to `nebula-storybook-stories` (canonical source for story naming, structure, and CSF details).

Before running validation, confirm every new component has a matching `src/stories/<component-name>.stories.jsx` file (see `nebula-storybook-stories`). After creating or modifying components, always validate your code by running the `code:fix` script. Make sure to use the right package manager. For example, if using npm, run the following command: ```bash npm run code:fix ``` This runs Prettier and ESLint with auto-fix, ensuring: - Consistent formatting - Common issue detection - Drupal Canva...

Page stories showcase how components work together in realistic layouts. They should closely mirror what end users will experience in Drupal Canvas, so avoid patterns that won't be available in Canvas.

This project uses a two-folder structure to separate example code from working code: ``` src/ ├── components/ # Working components (Storybook reads from here) │ └── global.css # Base styles imported by Storybook ├── stories/ # Working stories (Storybook reads from here) examples/ ├── components/ # Example component implementations (for reference) └── stories/ # Example stories (for reference) ``` Detect the package manager by checking for lock files in the project roo...

**This applies to web page URLs only.** Do not use this for: - Figma URLs (use the Figma MCP instead) - GitHub URLs (read the code directly) - Documentation URLs (read or search as needed)

**CRITICAL: Every component MUST have an individual story file.** Each component in `src/components/` requires a corresponding story file in `src/stories/`. The story file: - Must be named `<component-name>.stories.jsx` (kebab-case with hyphens) - Must import the component from `@/components/<component-name>` - Must showcase the component's props and variants **Example structure:** ``` src/components/my-card/ ├── index.jsx └── component.yml src/stories/my-card.stories.jsx # Required story fi...

Creates and manages structured notes from templates. Use when the user wants to take, add, or write meeting notes, interview notes, 1:1 notes, or any template-based notes.

Open code files in a tmux pane at the relevant line using the user's preferred editor. Use when the user says "show me the code", "open this in an editor", "let me see that code", or wants to view discussed code in an editor.

Deep research and analysis tool. Generates comprehensive HTML reports on any topic, domain, paper, or technology. Use when user asks to research, analyze, investigate, deep-dive, or generate a report on any subject. Supports academic papers (arXiv), technologies, trends, comparisons, and general topics.

EXPERIMENTAL: Three-layer parallel meta-cognition analysis. Triggers on: /meta-parallel, 三层分析, parallel analysis, 并行元认知

CRITICAL: Use for Rust news and daily/weekly/monthly reports. Triggers on: rust news, rust daily, rust weekly, TWIR, rust blog, Rust 日报, Rust 周报, Rust 新闻, Rust 动态

Use when asking about Rust versions or crate info. Keywords: latest version, what's new, changelog, Rust 1.x, Rust release, stable, nightly, crate info, crates.io, lib.rs, docs.rs, API documentation, crate features, dependencies, which crate, what version, Rust edition, edition 2021, edition 2024, cargo add, cargo update, 最新版本, 版本号, 稳定版, 最新, 哪个版本, crate 信息, 文档, 依赖, Rust 版本, 新特性, 有什么特性

Use when creating skills for Rust crates or std library documentation. Keywords: create rust skill, create crate skill, create std skill, 创建 rust skill, 创建 crate skill, 创建 std skill, 动态 rust skill, 动态 crate skill, skill for tokio, skill for serde, skill for axum, generate rust skill, rust 技能, crate 技能, 从文档创建skill, from docs create skill

Use when processing incoming emails with Postmark inbound webhooks — building reply-by-email, email-to-ticket, document extraction, or any workflow that receives and parses email.

Use when working with Postmark email platform - routes to specific sub-skills for sending emails, processing inbound email, managing templates, or configuring webhooks.

SDK for ingesting data into Deeplake managed tables. Use when users want to store, ingest, or query data in Deeplake.

SDK and CLI for Deeplake persistent memory — a cloud-backed filesystem for AI agents. Use when users want to mount, manage, or use persistent memory that survives across sessions, or run any `deeplake` CLI command.

SDK and CLI for ingesting data into Deeplake managed tables, and mounting a cloud-backed filesystem for persistent agent memory. Use when users want to store, ingest, query data in Deeplake, or set up persistent memory/filesystem.

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

Send ActivitySmith push notifications and trigger Live Activities from any agent with the ActivitySmith CLI. Use when a task asks for push alerts, completion notifications, or Live Activity start/update/end lifecycle operations.

Launch and use the local BackgroundComputerUse macOS runtime through its self-documenting loopback API. Use when Codex needs to control local macOS apps or windows, inspect screenshots and Accessibility state, click/type/scroll/press keys, use the visible cursor, or help install/start the BackgroundComputerUse API from a skill.

Use when Antigravity MCP is available locally and you want to query workspaces, check quota, run lightweight Antigravity asks, or generate images through the local antigravity-mcp-server.

Use Qwen (DashScope/百炼) for speech tasks: (1) ASR speech-to-text transcription of user audio/voice messages (Telegram .ogg opus, wav, mp3) using qwen3-asr-flash, optionally with coarse timestamps via chunking; (2) TTS text-to-speech voice reply using qwen3-tts-flash with selectable voice (default Cherry) and output as .ogg voice note for Telegram.

When the user wants to plan, evaluate, or build a free tool for marketing purposes — lead generation, SEO value, or brand awareness. Also use when the user mentions "engineering as marketing," "free tool," "marketing tool," "calculator," "generator," "interactive tool," "lead gen tool," "build a tool for leads," or "free resource." This skill bridges engineering and marketing — useful for founders and technical marketers.

Apply an approved BOOT upgrade item by number using the guided apply runner.

Run post-bootstrap or post-migration governance audit.

Run workspace governance migration for an already-running OpenClaw workspace.