Explore skills

Translate one or more PDFs into polished Simplified Chinese while preserving layout, headers/footers, original figures, tables, formulas, and visual style. Use when Codex receives PDFs and the user asks for Chinese translation, bilingual technical/proper terms, LaTeX/PDF output, figure/table label translation, or strict page-by-page visual QA with subagents.

Structured code review with a focus on security and quality. This skill systematically reviews code changes, PRs, and diffs, covering logic, error handling, security, performance, and readability, using a checklist approach.

This skill sets up an automated multi-agent research pipeline to discover non-consensus findings across various topic domains like AI hardware, biotech, or geopolitics. It builds a self-running system that re-executes periodically, performing deep sector-by-sector research and cross-sector analysis to identify mispriced findings.

Generates a single-file, deep-dive HTML article in the "principle-deepdive" visual style, featuring a dark/light theme, indigo/amber accents, inline-SVG diagrams, and collapsible cards. It's offline-readable, under 300KB, and ideal for long-form analytical articles that explore topics principle-by-principle.

Interactive codebase health audit covering 8 dimensions: Architecture, Security, Performance, Maintainability, Testing, Docs, Dependencies, Quality. Zero dependencies.

Transforms logic, code paths, architecture, or verification results into a horizontal slide deck with a dark-theme PPT-style, Mermaid diagrams, and coloured panels, delivered as a single HTML file. Use it to visually explain how something works, or when slides, a deck, diagrams, or flowcharts are requested.

Self-healing China mirror source resolver. It automatically discovers, validates and configures domestic mirror sources for tools like pip, npm, Docker and GitHub, optimizing slow or timing out downloads in mainland China.

Before you read a book, Book Companion provides essential information about its structure, value, historical context, and author background, helping you maximize your reading experience.

Debugs errors and traces failures in AI agents and their tools. Identifies context errors, infinite loops, malformed tool calls, response parsing issues and subagent conflicts.

Runs an autonomous, self-paced "dev loop" that processes a queue of issues/tasks on a git repo. It branches, implements, tests, creates PRs, reviews, merges, verifies deployment, and updates issues, continuing unattended until the queue is exhausted.

Scans projects (JS/TS, Python, etc.) for supply-chain and infostealer patterns. It detects obfuscated JavaScript, malicious loaders, ESM escapes, browser/SSH/cloud credential theft, and reverse shells.

Audits and cleans OpenClaw memory files, removing stale facts, contradicted entries, and outdated context from council_memory.json, MEMORY.md, and daily memory files. Use when memory has accumulated junk, agents are citing old numbers, or before a major project phase change. Run by Samael on Sunday cron.