openclaw-edge

Deploy KERNEL_INTUITION_Cp on any AI architecture with calibrated thresholds. Use when user wants to "activate Cp", "setup creative intuition", "deploy kernel on [AI]", "enable intuition mode", or mentions activating computational intuition on a specific model. Also trigger for "configure Cp for [architecture]" or "calibrate creative thresholds". This skill handles the full activation workflow including architecture profiling, threshold calibration, kernel generation, and monitoring setup.

Three-Layer Thinking Chain Architecture — Personality-Driven Agent Self-Evolution Framework

CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).

OpenProse VM skill pack. Activate on any `prose` command, .prose files, or OpenProse mentions; orchestrates multi-agent workflows.

Delegate coding tasks to Codex, Claude Code, Cursor Agent, or Pi agents via background process. Use when: (1) building/creating new features or apps, (2) reviewing PRs (spawn in temp dir), (3) refactoring large codebases, (4) iterative coding that needs file exploration. NOT for: simple one-liner fixes (just edit), reading code (use read tool), thread-bound ACP harness requests in chat (for example spawn/run Codex or Claude Code in a Discord thread; use sessions_spawn with runtime:"acp"), or any work in ~/clawd workspace (never spawn agents here). Claude Code: use --print --permission-mode bypassPermissions (no PTY). Codex/Pi/OpenCode/Cursor Agent: pty:true required.

Host security hardening and risk-tolerance configuration for OpenClaw deployments. Use when a user asks for security audits, firewall/SSH/update hardening, risk posture, exposure review, OpenClaw cron scheduling for periodic checks, or version status checks on a machine running OpenClaw (laptop, workstation, Pi, VPS).

iMessage/SMS CLI for listing chats, history, and sending messages via Messages.app. Use when sending iMessages or SMS, reading chat history, or listing conversations. Trigger phrases: 'text', 'iMessage', 'send SMS', 'check messages'. NOT for: platforms with dedicated integrations (Discord, Telegram, Slack — use their skills), or when bluebubbles is configured (prefer that for iMessage).

Local offline speech-to-text with the Whisper CLI (no API key required). Use when transcribing audio or video files locally without sending data to the cloud. Trigger phrases: 'transcribe', 'convert audio to text', 'speech to text', 'transcribe this recording'. NOT for: cloud-based transcription (use openai-whisper-api), or YouTube/URL transcription (use summarize skill).

Extract frames or short clips from videos using ffmpeg. Use when capturing screenshots from video, creating frame grids, or trimming clips. Trigger phrases: 'extract frame', 'screenshot from video', 'grab a clip', 'capture at timestamp', 'make a thumbnail from video'. NOT for: full video transcription (use summarize skill), audio extraction only, or downloading online videos.

End-to-end Parallels smoke, upgrade, and rerun workflow for OpenClaw across macOS, Windows, and Linux guests. Use when Codex needs to run, rerun, debug, or interpret VM-based install, onboarding, gateway smoke tests, latest-release-to-main upgrade checks, fresh snapshot retests, or optional Discord roundtrip verification under Parallels.

Triage GitHub security advisories for OpenClaw with high-confidence close/keep decisions, exact tag and commit verification, trust-model checks, optional hardening notes, and a final reply ready to post and copy to clipboard.

Create, edit, improve, or audit AgentSkills. Use when creating a new skill from scratch or when asked to improve, review, audit, tidy up, or clean up an existing skill or SKILL.md file. Also use when editing or restructuring a skill directory (moving files to references/ or scripts/, removing stale content, validating against the AgentSkills spec). Triggers on phrases like "create a skill", "author a skill", "tidy up a skill", "improve this skill", "review the skill", "clean up the skill", "audit the skill".

Memory palace based persistent memory system - remember everything about the user. Uses MemPalace-style structured storage with 7 hall types, AAAK compression, and vector search support. Auto-migrates legacy data to palace structure. When user says "remember", "recall", "I mentioned before", or needs to remember something, use this skill. Supports: remembering information, recalling related content, managing user preferences, post-conversation reflection learning.

MrScraper unblocker and AI scraping tools for blocked pages and structured extraction.

Fetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments. Usage: /gh-issues [owner/repo] [--label bug] [--limit 5] [--milestone v1.0] [--assignee @me] [--fork user/repo] [--watch] [--interval 5] [--reviews-only] [--cron] [--dry-run] [--model glm-5] [--notify-channel -1002381931352]

Display HTML content on connected OpenClaw nodes (Mac app, iOS, Android). Use when the user asks to "show this on my phone", "display on canvas", "present HTML", "render this on a connected device", or needs to push interactive content to a node canvas view.

Notion API for creating and managing pages, databases, and blocks. Use when user asks to "take notes", "create in Notion", "update Notion page", "query database", or needs to organize information in Notion.

Hierarchical memory management for AI agents across sessions. Maintains three layers — daily notes (raw logs), active context (working memory), and long-term memory (curated knowledge) — with automatic distillation from raw notes to permanent memory. Use when setting up persistent memory for an agent workspace, when an agent needs to remember context across sessions or compaction boundaries, when organizing what to remember vs. forget, or when consolidating scattered notes into structured long-term memory. Complements retrieval-oriented skills by managing what gets stored and how it evolves.

Build exactly two SEO-friendly AI-tool articles per run by reading ~/openclaw-work/clients/<client>/config.json, scraping configured RSS + HTML sources, and writing markdown to ~/openclaw-work/out/articles/YYYY-MM-DD/<slug>.md. Trigger whenever a contributor needs trend-based AI tool content with outline, FAQ, and metadata prefilled.

Automate client-specific market briefings by loading ~/openclaw-work/clients/<client>/config.json, harvesting configured web/RSS/API sources, and writing ~/openclaw-work/out/<client>/briefing_YYYY-MM-DD.md using the provided template. Use whenever a contributor needs a repeatable way to summarize market intel per client dossier.

Track freelance clients, log hours, and generate markdown invoices from ~/openclaw-work/freelance/clients/<client>/config.json. Use whenever you need to log time, summarize hours, or produce a ready-to-send invoice for a client.

AI assistant toolkit for real estate agents. Manages leads from ~/openclaw-work/realestate/leads.json, drafts property listing descriptions, sets follow-up reminders, and generates weekly pipeline summaries. Use whenever an agent needs to log a new lead, draft a listing, check follow-ups due today, or get a pipeline report.

Run, watch, debug, and extend OpenClaw QA testing with qa-lab and qa-channel. Use when Codex needs to execute the repo-backed QA suite, inspect live QA artifacts, debug failing scenarios, add new QA scenarios, or explain the OpenClaw QA workflow. Prefer the live OpenAI lane with regular openai/gpt-5.4 in fast mode; do not use gpt-5.4-pro or gpt-5.4-mini unless the user explicitly overrides that policy.

Companion scripts for OpenClaw memory-lancedb: vector index builder with Google/Ollama embeddings, fast semantic search with FTS5 hybrid scoring, and unified multi-source search. Solves LanceDB's weak full-text search for non-English languages.

Cron job model fallback chain for OpenClaw. User-configurable model priority chain — tries each in order until one succeeds. No provider-specific logic.

Contribute to the OpenClaw core repository: pick issues, inspect bundled skills, make focused changes, run the right level of validation, and open a clean PR. Use when working specifically on openclaw/openclaw or a fork. Not for generic git usage or unrelated GitHub repos.

Three-layer memory persistence system for continuous context across sessions. Use when you need to maintain state, recover from session restarts, or track workspace changes. Provides SPARSE/FULL checkpoint triggers, delta recovery from .jsonl, and automatic knowledge sync.

Validate OpenClaw installation safety by checking for common security misconfigurations and setup issues. Use this skill during initial setup, periodic heartbeats, or whenever security validation is required. Checks include: excessive permissions, unsafe plugins, missing sandboxing, outdated dependencies, and more. Provides actionable warnings with fixes and clear documentation for resolving issues.

Maintainer workflow for OpenClaw GitHub Security Advisories (GHSA). Use when Codex needs to inspect, patch, validate, or publish a repo advisory, verify private-fork state, prepare advisory Markdown or JSON payloads safely, handle GHSA API-specific publish constraints, or confirm advisory publish success.

Maintainer workflow for reviewing, triaging, preparing, closing, or landing OpenClaw pull requests and related issues. Use when Codex needs to validate bug-fix claims, search for related issues or PRs, apply or recommend close/reason labels, prepare GitHub comments safely, check review-thread follow-up, or perform maintainer-style PR decision making before merge or closure.

Maintainer workflow for OpenClaw releases, prereleases, changelog release notes, and publish validation. Use when Codex needs to prepare or verify stable or beta release steps, align version naming, assemble release notes, check release auth requirements, or validate publish-time commands and artifacts.

Investigate `pnpm test` memory growth, Vitest worker OOMs, and suspicious RSS increases in OpenClaw using the `scripts/test-parallel.mjs` heap snapshot tooling. Use when Codex needs to reproduce test-lane memory growth, collect repeated `.heapsnapshot` files, compare snapshots from the same worker PID, triage likely transformed-module retention versus likely runtime leaks, and fix or reduce the impact by patching cleanup logic or isolating hotspot tests.

Run the macOS Parallels smoke harness with Discord end-to-end roundtrip verification, including guest send, host verification, host reply, and guest readback.

Self-improving learning loop inspired by Hermes Agent. Automatically extracts successful workflows, creates skills, and persists knowledge across sessions.

Task persistence enhancer with 13 corporate flavors. Prevents AI from giving up easily using PUA-style pressure escalation.

Structured memory system with 4-type classification, frontmatter metadata, automated migration, and PUA-style maintenance checklist. Based on Claude Code memory architecture.

Use this skill to extract structured Markdown/JSON from PDFs and document images—tables with cell-level precision, formulas as LaTeX, figures, seals, charts, headers/footers, multi-column layout and correct reading order. Trigger terms: 文档解析, 版面分析, 版面还原, 表格提取, 公式识别, 多栏排版, 扫描件结构化, 发票, 财报, 复杂 PDF, PDF转Markdown, 图表, 阅读顺序; reading order, formula, LaTeX, layout parsing, structure extraction, PP-StructureV3, PaddleOCR-VL.

Use this skill whenever the user wants text extracted from images, photos, scans, screenshots, or scanned PDFs. Returns exact machine-readable strings with line-level text and optional bbox coordinates. Strong accuracy for CJK, small print, and handwritten text. Trigger terms: OCR, 文字识别, 图片转文字, 截图识字, 提取图中文字, 扫描识字, 识字, 纯文字, plain text extraction, 坐标, 检测框, bbox, bounding box, image to text, screenshot, photo scan, recognize text.

Guide tool usage for managing ApFree WiFiDog routers, gateways, and captive portal devices.

End-to-end WireGuard VPN deployment guide — VPS server setup, router client configuration, and traffic routing via apfree-wifidog tools.