Loading...
Loading...
Found 8,857 Skills
Initialize a new workspace by copying the standard artifact template (STATUS.md, CHECKPOINTS.md, UNITS.csv, DECISIONS.md + folders). **Trigger**: workspace init, initialize workspace, workspace template, 初始化 workspace. **Use when**: 启动任何 pipeline run（必须先有 workspace 工件与目录骨架）。 **Skip if**: workspace 已初始化且不希望覆盖既有文件（除非显式 `--overwrite`）。 **Network**: none. **Guardrail**: 不要修改 `.codex/skills/workspace-init/assets/` 模板；默认不覆盖已有文件。
Use before claiming work is done, fixed, or passing — requires running verification commands and confirming output before any success claim. Prevents false completion claims, unverified assertions, and "should work" statements.
Generate high-quality images for WeChat Official Account articles. Support cover images (2.35:1), body illustrations (16:9/4:3), and infographics. Two paths are provided: AI Generation (visual creative type) and HTML Rendering (text precise type). Use this skill when users mention "WeChat Official Account images", "WeChat Official Account covers", "article images", "body illustrations", or "WeChat Official Account pictures".
Research topics with web search. Use when: researching a topic or concept, finding current information, answering factual questions, comparing options or technologies. Triggers: research [topic], find out about, what are the best practices for, research the latest on.
Collaborative planning using abstract roles (designer + inspiration + reviewer).
Review contracts against your organization's negotiation playbook, flagging deviations and generating redline suggestions. Use when reviewing vendor contracts, customer agreements, or any commercial agreement where you need clause-by-clause analysis against standard positions.
Autonomous goal execution — give a goal, get a plan, confirm, execute, report. You steer, Claude drives.
Manages Atlassian Jira and Confluence via the Rovo MCP Server. Handles MCP setup, OAuth authentication, and troubleshooting. Runs agentic project management: Confluence plans, Jira Epics with child tickets, agent team coordination, and resuming interrupted work from Jira state. Supports uploading images/attachments to Confluence pages via REST API. Reads and writes Confluence page comments (footer, inline, reply threads). Creates git branches linked to Jira tickets (GitHub and Bitbucket). Use this skill whenever the user mentions Jira, Confluence, Atlassian, tickets, epics, sprints, project boards, wiki pages, or Confluence spaces. Also trigger when the user wants to plan a project, break work into tasks, track progress, resume interrupted work, upload images to wiki pages, manage comments on Confluence pages, or create git branches linked to tickets — even if they don't mention Atlassian by name.
Front-end development expert for this project. Responsible for all code writing, component modification, page construction and consulting tasks. **Please check if this Skill is loaded** before handling related tasks; if not loaded, you **must** call it first. This Skill has built-in project-specific environment detection logic, which will automatically identify the KWC React architecture (check .kd directory, etc.) and apply mandatory development specifications (i.e., rule.md under this Skill directory). Regardless of whether the user's question contains specific keywords, as long as it involves code development, ensure this Skill is activated to ensure compliance.
Expert guidelines for Ethereum smart contract development with Solidity, OpenZeppelin, and Hardhat
Two-way integration channel between Feishu (Lark/Feishu) and OpenClaw. It implements message receiving and sending through Feishu bot, supporting private chat, group chat, @mention detection, card messages, and file transfer. This skill is used when you need to interact with AI assistants via Feishu, receive Feishu messages to trigger AI responses, or send messages from OpenClaw to Feishu. Difference from feishu-automation: this skill focuses on message channel integration, while feishu-automation focuses on automated operations of Feishu platform (such as multidimensional tables, documents, etc.)
Iteratively improve any output until measurable criteria are met. Use when the user wants to refine existing work against specific standards — whether it's code, prose, data, config, or any other artifact. Triggers on phrases like "improve this", "make it better", "iterate", "refine", "keep improving", "not good enough yet", "optimize this", "polish this", "tighten this up", or when the user provides criteria and wants repeated improvement until they're satisfied. Also use when the user gives feedback on output and expects you to keep refining, even if they don't say "improve" explicitly.