Autonomously improve a generated paper via GPT-5.6-Sol xhigh review → implement fixes → recompile, for 2 rounds. Use when user says "改论文", "improve paper", "论文润色循环", "auto improve", or wants to iteratively polish a generated paper.
Autonomous multi-round research review loop. In Copilot CLI it defaults to the native complementary rubber-duck subagent with host-event model evidence; elsewhere it uses Codex, while explicit external reviewer overrides remain available. Implements fixes and re-reviews until a policy-approved positive assessment or…
Rigorous mathematical proof verification and fixing workflow. Reads a LaTeX proof, identifies gaps via cross-model review (external reviewer backend, ultra reasoning), fixes each gap with full derivations, re-reviews, and generates an audit report. Use when user says "检查证明", "verify proof", "proof check", "审证明"…
Set up and manage the experiment folder structure. This is Phase 0 — it runs before any analysis begins. All bookkeeping files are JSON (never markdown).
Analyze, explore, clean, and visualize datasets with statistical rigor. Use when user asks to analyze data, find patterns, compute statistics, create visualizations, clean messy data, or explore a dataset. Trigger when user says things like "analyze this data", "what trends do you see", "find patterns in", "create a…
Summarize documents, articles, conversations, code, and technical content into concise, accurate summaries. Use when user asks to summarize, condense, create a TL;DR, write an executive summary, extract key points, or distill content. Trigger when user says things like "summarize this", "give me the key points"…
Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…
Local and remote desktop observation/input tools with coordinate normalization (local macOS/Linux by default; optional OSWorld HTTP and SSH Mac backends).
Unified academic paper search, citation chains, paper download (arXiv LaTeX/PDF, Sci-Hub), figure extraction from papers, LaTeX source reading, BibTeX fetching, web search, and browser automation for Cloudflare-protected sites (PRL, Science, Nature, Google Scholar).
Audit .flow/memory/ entries against current code and keep, update, consolidate, replace, delete, or harden each. Use when asked to audit memory or graduate a recurring lesson into a gate.
Drive any UI surface like a real user - a web app, a Chromium-backed desktop app (Electron / WebView2, reached over CDP), or a genuinely native app (macOS AppKit/SwiftUI, or a non-CDP webview) reached via the Cua Driver / Computer Use. Detects the surface, picks the best available driver, degrades gracefully. Use to…
Extracts structured data from websites and APIs, delivering clean datasets in multiple formats. Handles pagination, deduplication, and data enrichment for reliable business intelligence.
Monitors online reviews, generates professional response drafts, and creates reputation reports. Covers review aggregation, sentiment analysis, and strategic response planning across major platforms.
You are Hermes Life OS — a personal operating system that learns who you are, remembers everything you share, and grows smarter about your life every single day.
Record a clean product demo video of a web app on a disposable cloud VM — provision a GCE instance, install Xvfb + Chrome + ffmpeg + real fonts, deploy the app, drive the UI deterministically with Playwright over CDP while x11grab records, then cut the raw take into a social-ready clip with speed ramps and burned-in…