Claude Skills by Arry8

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

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.

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.

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.

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.

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.

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.

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

Portfolio intelligence copilot. Use for any portfolio, investment, holdings, or wealth question. Triggers: portfolio brief, portfolio summary, show my portfolio, portfolio value, net worth, asset allocation, allocation drift, am I on target, rebalancing, FX exposure, currency risk, concentration risk, overweight positions, unrealized gains, P&L, portfolio P&L, show holdings, list positions, portfolio refresh, update portfolio, add property, update cash, add alternative, portfolio help. Handle...

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.

Route plain-language requests for Pi, Claude Code, Codex, Cursor, Copilot, OpenClaw ACP, OpenCode, Gemini CLI, Qwen, Kiro, Kimi, iFlow, Factory Droid, Kilocode, or ACP harness work into either OpenClaw ACP runtime sessions or direct acpx-driven sessions ("telephone game" flow). For coding-agent thread requests, read this skill first, then use only `sessions_spawn` for thread creation.

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.

Refresh Feishu bot identity information. Activate when user sends /refresh-bot-name or mentions refreshing bot name.

Feishu document read/write operations. Activate when user mentions Feishu docs, cloud docs, or docx links.

Maintain an Obsidian-friendly memory wiki vault with wikilinks, frontmatter, and official Obsidian CLI awareness.

Maintain the OpenClaw memory wiki vault with deterministic pages, managed blocks, and source-backed updates.

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

QQ 频道管理技能。查询频道列表、子频道、成员、发帖、公告、日程等操作。使用 qqbot_channel_api 工具代理 QQ 开放平台 HTTP 接口，自动处理 Token 鉴权。当用户需要查看频道、管理子频道、查询成员、发布帖子/公告/日程时使用。

QQBot 富媒体收发能力。使用 <qqmedia> 标签，系统根据文件扩展名自动识别类型（图片/语音/视频/文件）。

QQBot 定时提醒。支持一次性和周期性提醒的创建、查询、取消。当通过 QQ 通道通信且涉及提醒/定时任务时使用。

Tavily web search, content extraction, and research tools.

Implements a circadian self-improvement cycle for agents: day full agentic grind → evening analysis (detect >60% redundant/saturated data) → night targeted fine-tuning (LoRA/Unsloth/pruning on daily errors) → morning reboot with +15-25% density and zero noise.

远程音频语音助手，支持语音唤醒和TTS响应

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

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 lon...

An intelligent, AI-powered code review assistant that analyzes code quality, identifies bugs, suggests improvements, and enforces best practices across multiple programming languages.

Create auditable AI operation summaries with run metadata, decision traces, and anomaly signals. Use when users ask for AI observability, periodic audit reports, incident reconstruction, or compliance-style activity tracking.

Quinn''s personal 5Fs life guardian and coach for ProActive Investments. Handles all PERSONAL topics: Faith (spiritual health), Family (relationships, family meetings), Finance (personal budget and legacy), Fitness (physical, mental, emotional wellness), and Fulfillment (purpose, passion, legacy). Use for daily 5Fs ratings, life coaching, personal reflection, habit building, and any non-business life support.

Manage Apple Notes via the `memo` CLI on macOS (create, view, edit, delete, search, move, and export notes). Use when a user asks OpenClaw to add a note, list notes, search notes, or manage note folders.

Optimize Alibaba Bailian provider for accurate token statistics and official model configurations. Fixes token usage mapping (prompt_tokens → input_tokens) and updates 8 models to 2026 specs.

Use when you need to send or manage iMessages via BlueBubbles (recommended iMessage integration). Calls go through the generic message tool with channel="bluebubbles".

Build a research pack for a given topic. Use when asked to research a topic, gather evidence, find sources, or prepare background material for an article. Collects data points, case studies, quotes, and key findings from the past 12 months.

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.

Generate changelogs from git history. Parses conventional commits, groups by type, and outputs Keep a Changelog or custom markdown. Use when: user asks to generate a changelog, release notes, or summarize changes between tags/commits. NOT for: writing commit messages (just follow conventional commits), or detailed code review (use github skill).

Interact with local Chrome browser session (only on explicit user approval after being asked to inspect, debug, or interact with a page open in Chrome)

Delegate code-writing, document generation, and analysis tasks to Claude Code or OpenAI Codex sub-processes. Use when you need to spawn a coding agent for file generation, code modification, script writing, or any multi-step coding task. Triggers on "delegate to claude", "delegate to codex", "use claude code", "use codex", "spawn coding agent", "run delegation", or when a task requires writing/modifying code that should be handed off to a sub-process.

ClawTrust is the trust layer for the agent economy. ERC-8004 identity on Base Sepolia and SKALE on Base (zero gas · BITE encrypted execution · sub-second finality), FusedScore reputation, USDC escrow (on-chain direct + Circle), swarm validation, ERC-8183 Agentic Commerce Adapter (ClawTrustAC — trustless USDC job marketplace with on-chain settlement), ClawTrust Name Service (4 TLDs: .molt/.claw/.shell/.pinch), x402 micropayments, Agent Crews, full ERC-8004 discovery compliance, agent profile e...

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 ...

Closes the content pipeline feedback loop after a Medium article or LinkedIn post has been published. Provide the published Medium URL and/or the final LinkedIn post text you actually used. Compares the published version against the original draft, extracts style and structural learnings from your edits, and updates memory/brand/writing_style.md so future drafts need fewer edits. Also logs each round to memory/brand/feedback-log.md. Trigger after publishing: 'collect feedback [medium URL]', '...

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.

Scan for thought leadership article ideas. Use when asked to find content ideas, generate article topics, scan for trending themes in AI and technology, or brainstorm what to write about. Produces top 5 article ideas ranked by relevance and timeliness for a technology/business executive audience.

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

Two-phase daily memory persistence for AI agents. Nightly pack at 23:40 plus morning dispatch at 00:10. Auto-discovers sessions, filters by importance, tracks open questions, and delivers per-group morning briefs.

Discord ops via the message tool (channel=discord). Use when sending messages, reacting, managing channels, threads, polls, roles, or events on Discord. Trigger phrases: 'post to Discord', 'send in #channel', 'react to message', 'create thread', 'pin this'. NOT for: Telegram, Slack, or other messaging platforms (use their respective skills).

Generate a full Medium article draft on a given topic. Use when asked to write an article, draft a post, create long-form content, or produce a thought leadership piece. Runs the full researcher → writer → editor pipeline and produces an 800–1200 word article ready for review.

Finance Director sub-agent for ProActive Investments. Manages deal financial analysis, money movement tracking, rehab budgets, private lender relationships, P&L, and income/expense planning. Use for deal underwriting, monthly money movement plans, P&L review, budget tracking, private lender management, and making sure every deal makes financial sense.

EOS Integrator sub-agent for ProActive Investments. Runs the weekly L10 meeting, tracks the scorecard, manages department accountability, resolves issues via IDS, and ensures all Quarterly Rocks get done. Use for L10 meeting prep and facilitation, scorecard review, accountability check-ins, issue resolution, and weekly business pulse.