best/openclaw-skills

openclaw-usage-tracker

Track and report OpenClaw model usage and costs. Generate daily/weekly cost reports with per-model token breakdowns, interactive vs cron classification, provider summary, and trend analysis.

feed-score

Score and publish AI Feed candidates through a controlled runner. Agent only writes scored-results JSON.

feed-broadcast

Broadcast newly published AI Feed posts through a controlled wrapper with state and delivery guards.

feed-collect

AI Feed deterministic collection runner. Use to collect Miniflux/HN/GitHub candidates into data/candidates.json for feed-score.

discord-thread-archiver

Smart Discord thread archiving. Use when: (1) running periodic thread cleanup, (2) evaluating whether Discord threads should be archived. Agent lists active threads, reads messages, judges conversation status, archives resolved threads, and produces a…

skill-validator

技能实验室：OpenClaw 技能的全生命周期准入测试。包含三阶段： (1) 静态校验 — 结构、路径、跨平台兼容性（脚本 + AI 分析） (2) 智能分析 — 模型阅读技能全部内容，语义级审查 (3) 动态测试 — 生成子 Agent 加载技能实际运行，验证能力声明 Use when: 收到技能压缩包/目录需要评审，技能发布前准入测试，技能升级回归测试。

Source text: Chinese

wechat-mp-publisher

Publish Markdown articles to WeChat Official Account draft box using a local config file. Use when user wants to push blog posts to 微信公众号, convert Markdown to WeChat format, or create 公众号草稿.

cc-iterator

Autonomous CC (Claude Code) iteration loop. Manages background coding agent tasks with pull-based issue tracking.

chevereto-upload

Upload images to a Chevereto V4 image hosting service using a local config file for permanent, shareable URLs. Use when images (AI-generated, screenshots, or any visual content) need to be hosted, archived, or shared via a link. Also supports listing and…

code-reviewer

Standardized code review checklist for AI-generated code. Supports both local diff and PR review workflows.

dream

记忆方法论 & 整合执行——定义 T0/T1/T2/Dream 记忆职责、OpenClaw 注入预算硬约束、价值判断、遗忘机制，以及初始化/日常/深度三种执行流程。

Source text: Chinese

evolution-engine

PCEC — Wiki-Native 进化引擎。以 Wiki Vault 为核心知识库，通过 Gene（策略模板）和 Capsule（验证记录）实现经验积累与复用。信号检测→经验召回→诊断→固化到Wiki。

Source text: Chinese

gemini-image-gen

Generate and edit images using the Gemini Image Generation API with provider fallback through GEMINI_IMAGE_CONFIG. Supports text-to-image, image editing, multi-image composition (up to 14 input images), aspect ratio control, and 1K/2K/4K resolution.…

openai-image-gen

Generate and edit images with the OpenAI Image API, defaulting to gpt-image-2. Requires provider fallback through OPENAI_IMAGE_CONFIG; supports text-to-image, repeated-prompt batch generation, multi-image editing/composition (up to 16 input images), mask…

project-planner

Evaluate and prioritize open issues for next development task. Score-based ranking with effort estimation.

wechat-article-fetcher

Fetch and extract content from WeChat Official Account (微信公众号) articles. Use when a user provides a mp.weixin.qq.com URL and wants to read, extract, summarize, or archive the article. Supports full text extraction, metadata (title, account name, author,…