flonat-research

Use when you need to compare a project .bib against a Paperpile project/topic folder to find uncited papers or unfiled entries.

Use when you need to extract citations from a PDF and generate a validated .bib file. Reads the PDF, identifies all referenced works, constructs BibTeX entries with metadata verification, then runs bib-validate.

Use when you need to check a LaTeX submission against a PDF assessment brief.

Use when you need to replicate a quantitative analysis in a second language (R↔Python↔Stata↔Julia) to verify correctness. Level 1 of the verification hierarchy.

Use when you need to challenge research assumptions or stress-test arguments.

Review user-facing documentation for accuracy, consistency, and completeness across private, public, nested repos, and the user manual. Use when docs feel stale, after major changes, or before sharing. (Replaces `repo-doc-audit`)

Use when you need to compile all LaTeX projects and check cross-project consistency.

Use when you need to compile a LaTeX document — includes autonomous error resolution, citation audit, and quality scoring.

Use when you need to compare a project's LaTeX preamble against the working paper template.

Use when you need to explore a research question from multiple independent perspectives.

Use when you need all quality checks run before submission, producing a single dated report.

Use when you need academic proofreading of a LaTeX paper (11 check categories).

Use when you need Python environment management with uv (install, create venv, manage deps).

Use when you need to audit which findings in a literature have been replicated or failed.

Use when you need to assemble, anonymize, or audit a replication package.

Use when you need a mid-draft adversarial review of a paper — runs paper-critic + domain-reviewer + claim-verify + blindspot in parallel, then auto-synthesises into a prioritised revision plan. Distinct from pre-submission-report (final-gate kitchen sink, 13 sub-agents) — this is the active-drafting feedback loop. Triggers: 'review my draft', 'adversarial review', 'cluster review', 'mid-draft critique', 'feedback before pre-submission'.

Use when you need to download, split, and deeply read an academic PDF that is NOT in Paperpile (for Paperpile items, prefer paperpile get-pdf-text directly).

Use when mosh hangs / fails to connect to a headless Mac mini after a Tailscale update or restart, OR when a remote-access tool (RustDesk, VNC, AnyDesk) fails to reach its public relay from an MDM-managed client. Layers — Tailscale daemon health (dual-install conflict, headless GUI-app limitation, Homebrew launchd takeover), downstream mosh-server cleanup (stale UDP bindings to old Tailscale IP), macOS resolver stuck state, and Tailscale direct-IP as relay-bypass fallback. Symptoms include `could not get canonical name for <host>`, `failed to connect to local Tailscale service`, `Tailscale.CLIError error 1`, `Connection closed by UNKNOWN port 65535`, `Failed to connect to rs-ny.rustdesk.com:21116: Please try later`.

Fork an existing conference/journal paper into a second-venue submission variant: verify both CFPs' concurrent-submission policies, create a separate Overleaf project, convert the document class (LIPIcs/LNCS/acmart → target format), refit to the new page budget by relocating content to appendices (never cutting prose), run compile + anonymity + render-level QA, and write back vault submission + atlas output with concurrency/withdrawal clauses. Use for: 'submit this paper also to X', 'concurrent submission', 'make the WINE/EC/conference version', 'reformat for another venue'. NOT for preprints/arXiv (use preprint), NOT for moving a paper to a new target (use retarget-journal), NOT post-acceptance (use camera-ready).

Use when you need to interact with or test a local web application using Playwright.

Use when you need to bootstrap a university course or module folder.

Use when you need to bootstrap a lightweight project with minimal structure.

Use for daily planning, weekly reviews, meeting actions, or read/write queries over the Research Vault and research portfolio: tasks, topics, papers, outputs, submissions, venues, people, institutions, and deadlines. Triggers include 'do I have any topics for this venue?', 'which institution-X projects target venue Y?', and 'what is recorded for this paper?'. For venue suitability or recommendations rather than recorded state, query the portfolio first, then use the installed venue-recommendation workflow.

Use when you need to create an academic Beamer presentation with original theme and multi-agent review.

Use when you need to filter a .bib file to only entries actually cited in a .tex project.

Convert an accepted anonymous-submission LaTeX paper (AAAI/AIES/ACM-style) to camera-ready and implement the accepted reviews. Use when a paper is accepted with no rebuttal and you need to de-anonymize, add copyright, turn on section numbering, implement each reviewer's minor revisions, optionally move proofs to a non-counted appendix, and QA. Not for R&R/revise-and-resubmit (use strategic-revision) or for preprints (use preprint).

Use when you need to design or audit an identification strategy for an observational study.

Use when you need to save session state to survive context compaction or handoff between sessions.

Use when you need to compile raw inputs (literature, meeting notes, session logs, code findings) into a per-project knowledge wiki. Supports --autonomous / -y for end-to-end runs without prompts (used by the Saturday wiki-grow cron).

Use when you need to scaffold, run, or publish computational research experiments.

Use when you need an end-to-end analysis pipeline: EDA, estimation, or publication output.

Use when you need power analysis, pre-analysis plans, QSF parsing, or survey design.

Use when you want to be interrogated ONE question at a time — either to (a) defend your own research (viva, job talk, seminar Q&A, hostile-referee prep) or (b) study a class / subject you're learning (exam revision, active recall). An interactive adversarial/Socratic oral drill grounded in your actual material, escalating on weak answers, then a study sheet of what you fumbled with model answers. Triggers: 'grill me', 'grill me on X', 'viva prep', 'defend my paper', 'quiz me on this class', 'test me on <topic>', 'exam revision', 'help me study X'. Distinct from devils-advocate (stress-tests arguments in prose) and referee2-reviewer / paper-critic (produce a WRITTEN critique) — here YOU answer aloud.

Create, receive, or update a persistent project handoff between AI sessions. Supports Claude-to-Claude, Codex-to-Codex, Claude-to-Codex, and Codex-to-Claude through the same `.context/ai-handoff.md` protocol. Use for 'handoff', 'continue in a new session', 'hand this to Claude', 'hand this to Codex', or cross-machine continuation.

Use when you need to capture or integrate improvement ideas for Claude Code infrastructure.

Create or migrate project-level agents, repeatable project workflows, and planning state from one client-neutral contract, then render repository-scoped adapters for both Claude Code and Codex. Use when a research project needs role separation, project commands, formal phase tracking, or conversion from an existing Claude-only .claude/agents and .claude/commands setup.

Bootstrap a new research project. Interview for details, scaffold directory structure, create Overleaf symlink, initialise git, and create project context files.

Use when you need to archive an exported Claude Code insights HTML report and create a timestamped Beamer presentation. The deck-building workflow works from Claude Code or Codex; the Claude insights export is an input artifact.

Use when you need to conduct a structured interview to extract knowledge or preferences.

Use when you need to check compiled knowledge for contradictions, uncited claims, missing connections, stale articles, and orphaned concepts.