Skill rating

Two-thread adversarial review: a fresh reviewer constructs the strongest 200-word rejection memo, then a second fresh reviewer defends the paper point-by-point and surfaces still-unresolved critical i

DEFAULT poster pipeline — build an academic conference poster (ICML/NeurIPS/ICLR/CVPR/...) as a single HTML/CSS file with measurement-driven hard gates, real paper figures, a two-hue design-token syst

Get a deep critical review of research from a selected reviewer (Codex by default, Gemini, Grok, Claude Code, or manual). Use when user says "review my research", "help me review", "get external revie

Use when experiments complete to judge what claims the results support, what they don't, and what evidence is still missing. Codex MCP evaluates results against intended claims and routes to next acti

Periodically check WandB metrics during training to catch problems early (NaN, loss divergence, idle GPUs). Avoids wasting GPU hours on broken runs. Use when training is running and you want automated

Zero-context verification that every bibliographic entry in the paper is real, correctly attributed, and used in a context the cited paper actually supports — catching hallucinated authors, wrong year

Develop and verify a mathematical proof in Lean, continue an incomplete Lean project, or audit whether it proves the original statement. Connect actual inputs to intermediate lemmas, assemble the targ

Workflow 3: Full paper writing pipeline that goes from a narrative report to a polished, submission-ready PDF. Use when user says "写论文全流程", "write paper pipeline", "从报告到PDF", "paper writing", or wants

Double-blind bibliographic cross-check: one agent extracts each cited entry verbatim from the local .bib, a second independently re-fetches the same paper's record from the web while blind to the .bib

Generate publication-quality academic illustrations through a local Codex app-server bridge that uses Codex native image generation. This is a separate experimental alternative to `paper-illustration`

Workflow 5: orchestrate a text-only resubmit of a polished paper to a different venue under hard constraints (no new experiments, no bib edits, no framework changes, never overwrite prior submissions)

Rigorous mathematical proof verification and fixing workflow. Reads a LaTeX proof, identifies gaps via fresh-agent Codex GPT-6-Astra ultra review, fixes each gap with full derivations, re-reviews, and

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 derivat

Conditionally double-blind bibliographic cross-check (double-blind only when the host can isolate the web agent; a flag-only heuristic when isolation can't be attested): one agent extracts each cited

Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.

Build a working artifact from a plain "implement X for me" request: a running end-to-end spine first, then one feature per rung, with every under-determined decision written to an assumption ledger BE

Build a working artifact from a plain "implement X for me" request: a running end-to-end spine first, then one feature per rung, with every under-determined decision written to an assumption ledger BE

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 externa