Agent building

判断、扫描、拆解并归档抖音视频、小红书图文或小红书视频。实时读取用户同平台粉丝数并划分主对标池/跨级灵感池，用已登录浏览器读取目标作品和作者主页公开指标，再用确定性代码判定普通、小爆、爆款、现象级并扫描作者近 20 条候选；只对用户选中的爆款和现象级先构建可追溯证据包，再调用子 Agent…

Convert an Agent Skill into a formatted document (PDF, DOCX, or HTML).

Audit, score, and compare repositories containing portable Agent Plugins against the official Agent Plugins specification.

用于处理涉及检查、读取、创建、编辑、导出或代码映射的 Figma 内容任务，也用于将 HTML/React/Vue 等网页复制到 Figma，尤其适用于当前选区、设计系统、Figma MCP、Drafito、Figwright 或需要避免 MCP 工具污染上下文的场景。当用户需要可批注 Figma…

Codex/OpenClaw skill audit: live budget, usage, duplicates, compact descriptions.

Create a session retrospective with an AI diary and reusable lessons.

Automate low-impact web vulnerability verification through Burp MCP.

Claude Code adapter for the auto-capture skill.

Use when the user asks how to build with OpenAI products or APIs, asks about Codex itself or choosing Codex surfaces, needs up-to-date official documentation…

Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path.

OpenAI Images API: batches, prompt sampler, gallery.

Find, evaluate, and download common purchasable CAD parts from step.parts, including named off-the-shelf actuators, servos, motors, electronics boards…

Run bounded, evidence-driven training research through W&B Launch: assess project readiness, establish launchable code and queue capacity, smoke-test real…

Convert W&B Table artifacts into non-destructive EvalTable previews with scan-first planning, typed input/output/score columns, bounded batches, verification…

Retrospective on a coding session that proposes changes to the agent's environment (checks, pointers, steering, tooling) so the next run goes better.

Validates all interactive skills in this repo against the Agent Skills spec, project conventions, and structural requirements.

This skill should be used when long-running agent sessions need context compression, structured summarization, compaction, token-per-task optimization, or…

This skill should be used when agent work needs file-backed context: durable scratchpads, tool-output offloading, just-in-time discovery, cross-agent handoff…

Use when adding or auditing Yao copyright comment headers for an agent skill package, especially SKILL.md, README.md, references, prompts, templates…

Audit local and OpenClaw skill libraries for privacy theft, credential theft, stealthy exfiltration, unsafe execution chains, deceptive instructions, and…

Analyze local Agent Skill folders, SKILL.md files, or safe zip archives as untrusted input; explain purpose, trigger contract, structure, usage readiness…

Drafts copy-paste-ready /goal commands for goal mode in Claude Code and Codex.

[Beta] Session-start scan that surfaces relevant learnings, recent errors, and eval status before work begins.

Create, synthesize, and iteratively improve agent skills following the Agent Skills specification.