dawsonblock

Summary of the [REPLACE: CHANNEL_PLATFORM] channel [REPLACE: CHANNEL_NAME] — top [REPLACE: TOP_N_THREADS] threads + open questions

Price and volume tracker for [REPLACE: TOKEN_SYMBOL] with anomaly alerts above [REPLACE: ALERT_THRESHOLD_PCT]% movement

Watch Vercel deploys for [REPLACE: VERCEL_PROJECT] — alert on [REPLACE: ALERT_ON] in the last [REPLACE: LOOKBACK_HOURS] hours

Digest of the most interesting new posts on [REPLACE: TOPIC] from RSS feeds and the open web

Mention/keyword sweep on social platforms for [REPLACE: KEYWORDS] — trends, sentiment, top posts

5 concrete real-life actions, leverage-scored against open loops with specificity and anti-fluff gates

Curated AI-agent tweets, clustered into narratives with insight summaries

Tracker of AI agent substitution signals — which roles, companies, and industries show real headcount displacement. Named roles + real deployments only.

Convert local PDF text streams into Markdown bullet points.

Clean CSV files by trimming whitespace and exporting normalized JSON output.

Create, refactor, and package high-quality agent skills with strong trigger metadata, concise SKILL.md instructions, and reusable scripts/references/assets. Use when users ask to build a new skill, improve an existing skill, fix trigger behavior, or prepare a distributable package.

Draft high-clarity internal communication for announcements, incident updates, org changes, all-hands notes, policy rollouts, and leadership messages. Use when users request internal copy for teams or company-wide audiences. Trigger phrases include "internal announcement", "team update", "all-hands", "incident update", "staff update", "org change", and "leadership message".

Design and render visual assets using HTML5 Canvas or node-canvas. Use when users request banners, posters, social graphics, composited images, or canvas-based visuals with explicit dimensions and export formats. Trigger phrases include "canvas design", "html canvas", "draw on canvas", "create banner", "generate graphic", "social image", and "canvas animation".

Extract, normalize, and apply a brand system across UI, docs, and assets. Use when users ask for a brand kit, style guide, design tokens, tone rules, or brand-consistent output. Trigger phrases include "brand guidelines", "brand identity", "brand kit", "style guide", "brand colors", "brand fonts", "design tokens", and "make this on-brand".

Design and implement distinctive, production-grade frontend interfaces for web pages, components, and apps. Use when users ask for UI design, layout polish, landing pages, dashboards, React components, HTML/CSS styling, or visual redesign. Trigger phrases include "design this UI", "build a landing page", "make this look better", "frontend component", "dashboard UI", and "polish the interface".

Generate production-ready UI themes and token systems for CSS, Tailwind, and shadcn/ui. Use when users ask to apply a theme, theme an existing app, change colors and fonts, map dark/light mode tokens, or turn a palette into semantic variables. Trigger phrases include "apply a theme", "theme this app", "change the colors", and "re-theme this UI". Do not use for brand identity extraction, logo work, or full UI redesigns; use brand-guidelines or frontend-design instead.

Instrument C/C++ with -finstrument-functions for execution tracing and Perfetto visualization

Add gcov code coverage instrumentation to C/C++ projects

Check if specific lines were executed using gcov data

Deterministic debugging with rr record-replay. Use when debugging crashes, ASAN faults, or when reverse execution is needed. Provides reverse-next, reverse-step, reverse-continue commands and crash trace extraction.

Investigate GitHub security incidents using tamper-proof GitHub Archive data via BigQuery. Use when verifying repository activity claims, recovering deleted PRs/branches/tags/repos, attributing actions to actors, or reconstructing attack timelines. Provides immutable forensic evidence of all public GitHub events since 2011.

Recover deleted commits from GitHub using REST API, web interface, and git fetch. Use when you have commit SHAs and need to retrieve actual commit content, diffs, or patches. Includes techniques for accessing "deleted" commits that remain on GitHub servers.

Generate, export, load, and verify forensic evidence from GitHub sources. Use when creating verifiable evidence objects from GitHub API, GH Archive, Wayback Machine, local git repositories, or security vendor reports. Handles evidence storage, querying, and re-verification against original sources.

Recover deleted GitHub content using the Wayback Machine and Archive.org APIs. Use when repositories, files, issues, PRs, or wiki pages have been deleted from GitHub but may persist in web archives. Covers CDX API queries, URL patterns, and systematic recovery workflows.

Stateful LLDB debugging via LLDB Python API

Stateful LLDB debugging via LLDB Python API

Command-line interface for Obsidian — Knowledge management and note-taking via Obsidian Local REST API. Designed for AI agents and power users who need to manage notes, search the vault, and execute commands without the GUI.

Capture Unreal Engine traces to .utrace files and export Unreal Insights timing/counter data in headless mode.

Long-term memory engine for OpenClaw agents using M-flow knowledge graphs. Stores conversations as structured episodic memories and retrieves via graph-routed search. Use when the agent needs to remember past conversations, recall user preferences, or maintain context across sessions. Requires Docker.

Long-term memory engine for OpenClaw agents using M-flow knowledge graphs. Stores conversations as structured episodic memories and retrieves via graph-routed search. Use when the agent needs to remember past conversations, recall user preferences, or maintain context across sessions. Requires Docker.

**WORKFLOW SKILL** — Create, update, review, fix, or debug VS Code agent customization files (.instructions.md, .prompt.md, .agent.md, SKILL.md, copilot-instructions.md, AGENTS.md). USE FOR: saving coding preferences; troubleshooting why instructions/skills/agents are ignored or not invoked; configuring applyTo patterns; defining tool restrictions; creating custom agent modes or specialized workflows; packaging domain knowledge; fixing YAML frontmatter syntax. DO NOT USE FOR: general coding questions (use default agent); runtime debugging or error diagnosis; MCP server configuration (use MCP docs directly); VS Code extension development. INVOKES: file system tools (read/write customization files), ask-questions tool (interview user for requirements), subagents for codebase exploration. FOR SINGLE OPERATIONS: For quick YAML frontmatter fixes or creating a single file from a known pattern, edit the file directly — no skill needed.

Generate or update workspace instructions file for AI coding agents

Autonomous engineering team runtime — one API call spins up coordinated AI agents to scope, build, and ship software.

Karpathy-inspired behavioral guidelines for coding agents: clarify assumptions, keep changes simple, edit surgically, and verify before claiming completion.

Cube Sandbox 安全沙箱执行技能。当需要安全执行 Python 代码、Shell 命令，或需要隔离环境运行不受信任的代码时使用。 适用场景： (1) 用户要求"在沙箱中执行代码"、"跑一段 Python"、"安全执行"、"隔离环境运行"； (2) 需要执行可能有副作用的代码（文件操作、网络请求、安装包等），希望通过沙箱隔离风险； (3) 需要读写沙箱内文件、挂载宿主机目录到沙箱； (4) 需要控制沙箱网络策略（完全断网、白名单、黑名单）； (5) 需要暂停/恢复沙箱（保留内存快照以实现快速复用）。 Cube Sandbox 兼容 E2B SDK，通过环境变量 E2B_API_URL 指向 Cube 部署地址即可使用。

Search for places (restaurants, cafes, etc.) via Google Places API proxy on localhost.