Appendix B — Appendix: File Reference
B.1 All Agents
| Agent | File | Purpose |
|---|---|---|
| Proofreader | .agents/agents/proofreader.md |
Grammar, typos, consistency |
| Slide Auditor | .agents/agents/slide-auditor.md |
Visual layout, overflow, spacing |
| Pedagogy Reviewer | .agents/agents/pedagogy-reviewer.md |
Narrative arc, notation clarity |
| R Reviewer | .agents/agents/r-reviewer.md |
R code quality, reproducibility |
| TikZ Reviewer | .agents/agents/tikz-reviewer.md |
Diagram visual quality |
| Beamer Translator | .agents/agents/beamer-translator.md |
LaTeX to Quarto translation |
| Quarto Critic | .agents/agents/quarto-critic.md |
Adversarial Quarto QA |
| Quarto Fixer | .agents/agents/quarto-fixer.md |
Applies critic’s fixes |
| Verifier | .agents/agents/verifier.md |
Task completion verification |
| Domain Reviewer | .agents/agents/domain-reviewer.md |
Your domain-specific review |
| Claim Verifier | .agents/agents/claim-verifier.md |
Chain-of-Verification (fresh-context) fact-checker (v1.7.0) |
| Editor | .agents/agents/editor.md |
Journal editor for review-paper --peer (desk review + referee selection + editorial synthesis, v1.5.0) |
| Domain Referee | .agents/agents/domain-referee.md |
Disposition-primed substance referee for review-paper --peer (v1.5.0) |
| Methods Referee | .agents/agents/methods-referee.md |
Paper-type-aware methodology referee for review-paper --peer (v1.5.0; +formal-theory + survey-experiment in v1.8.0) |
| Humanize Auditor | .agents/agents/humanize-auditor.md |
Read-only auditor for AI-voice tells in academic prose; invoked by humanize (v1.9.0) |
| Promote-Memory Council | .agents/agents/promote-memory-council.md |
Five-critic council (generality / staleness / redundancy / evidence / format) for [LEARN] promotion from personal-memory.md to MEMORY.md; invoked by promote-memory (v1.9.0) |
| Project Coordinator | .agents/agents/project-coordinator.md |
Spawns, steers, and coordinates theoretical workstreams |
| Prover | .agents/agents/prover.md |
Drafts mathematical proofs under strict no-handwaving constraints |
| Literature Reviewer | .agents/agents/literature-reviewer.md |
Conducts verified literature reviews and fetches papers |
| Paper Reviewer | .agents/agents/paper-reviewer.md |
Gates workstream completion through adversarial correctness review |
| Coder | .agents/agents/coder.md |
Implements computational experiments and golden value verification |
| Lean Prover | .agents/agents/lean-prover.md |
Formalizes results and theorems in Lean 4 |
B.2 All Skills
| Skill | Directory | Purpose |
|---|---|---|
| Use when writing recommendation letters, reference letters, or award nominations for … | ||
| Draft economics papers with proper structure and academic style | ||
| This skill should be used for time series machine learning tasks including classifica… | ||
| Fetch economic data from FRED, World Bank, and other APIs | ||
| Enforce the replication-protocol.md rule by cross-checking numeric claims in a manusc… | ||
| Create academic presentations in Beamer with professional themes | ||
| Snapshot the computational environment for a replication package — detects the analys… | ||
| Use when writing or reviewing career documents including research statements, teachin… | ||
| Save a structured state snapshot before stopping or handing off. Captures the active … | ||
| Comprehensive citation management for academic research. Search Google Scholar and Pu… | ||
| Initialize a new AI co-mathematician research project. Use when the user wants to sta… | ||
| Render a compact status view of an AI co-mathematician research project — goals, acti… | ||
| Generate a co-author / collaborator handoff brief for a multi-author, multi-machine p… | ||
| OpenAI Codex (gpt-5.5) as an adversarial mathematical co-processor — verify, write, a… | ||
| Stage, commit, push, open a PR, and merge to main. Use ONLY on explicit commit intent… | ||
| Compile a Beamer LaTeX slide deck with XeLaTeX (3 passes + bibtex). Use when user say… | ||
| Distill the current conversation into a structured note (decisions made, open questio… | ||
| / Show current context status and session health. Use to check how much context h… | ||
Create a new Beamer lecture .tex from source papers and materials, with notation co… |
||
| Distributed computing for larger-than-RAM pandas/NumPy workflows. Use when you need t… | ||
| End-to-end R data analysis pipeline — exploration → cleaning → regression → publicati… | ||
| Draft a funder-compliant Data Management Plan (NSF DMP, NIH DMS Policy 2023, ERC, Hor… | ||
| Work with Data Commons, a platform providing programmatic access to public statistica… | ||
| / Deep consistency audit of the entire repository infrastructure. Launches 4 para… | ||
Render Quarto .qmd slides to HTML and sync to docs/ for GitHub Pages. Use when us… |
||
| Adversarial 5-7 question challenge to a deck’s pedagogical choices — ordering, prereq… | ||
| Root-cause a failing or wrong empirical result with a disciplined reproduce → minimis… | ||
| Run a staggered difference-in-differences / event-study analysis to the Sant’Anna pra… | ||
| Pre-screen analysis outputs (tables, figures, logs) built on restricted or confidenti… | ||
Use when the task involves reading, creating, or editing .docx documents, especiall… |
||
| Document toolkit (.docx). Create/edit documents, tracked changes, comments, formattin… | ||
| Remove AI writing patterns from academic economics, finance, and accounting prose. En… | ||
| Supplements the econ-humanizer skill with a more exhaustive and specific rule set for… | ||
| Search a curated corpus of ~51k economics papers (NBER working papers, JEL-coded jour… | ||
| Pre-submission referee report for economics, finance, and accounting papers — verifie… | ||
| Turn an economics, finance, or accounting paper into a professional Beamer talk with … | ||
| Create publication-quality charts and graphs for economics papers. | ||
| Draft and revise economics, finance, and accounting papers using Cochrane/McCloskey/S… | ||
| Supplements economic-writing, econ-humanizer, academic-paper-writer, research-grants,… | ||
| Perform comprehensive exploratory data analysis on scientific data files across 200+ … | ||
Extract TikZ diagrams from Beamer .tex source, compile each to a standalone PDF, an… |
||
| Measure sentiment and stance in financial and economic text — 10-K/10-Q MD&A, earning… | ||
| Gemini 3.5 Pro as an adversarial mathematical co-processor — verify, write, and explo… | ||
| Python library for working with geospatial vector data including shapefiles, GeoJSON,… | ||
| Scaffold a research grant proposal (NSF, NIH, ERC, or foundation) by composing existi… | ||
Read-only audit of .tex, .qmd, or .md text for AI-voice tells — boilerplate tra… |
||
| Structured hypothesis formulation from observations. Use when you have experimental o… | ||
| Interactive interview that formalizes a fuzzy research idea into a structured spec (R… | ||
| Write and typeset economic models in LaTeX with proper notation | ||
| Create professional research posters in LaTeX using beamerposter, tikzposter, or bapo… | ||
| Generate publication-ready regression tables in LaTeX. | ||
| / Extract reusable knowledge from the current session into a persistent skill. Us… | ||
| Structured literature search + synthesis with citation extraction, thematic clusterin… | ||
| Search, summarize, and synthesize economics literature | ||
| Conduct comprehensive, systematic literature reviews using multiple academic database… | ||
| Generate comprehensive market research reports (50+ pages) in the style of top consul… | ||
| Convert files and office documents to Markdown. Supports PDF, DOCX, PPTX, XLSX, image… | ||
| Write clear, detailed mathematical proofs for academic papers. Use when the user as… | ||
| Low-level plotting library for full customization. Use when you need fine-grained con… | ||
| Comprehensive toolkit for creating, analyzing, and visualizing complex networks and g… | ||
| Scaffold a new TikZ diagram from the snippet gallery with prevention rules pre-applie… | ||
| Scaffold a new skill that follows this repo’s conventions — interviews for purpose, t… | ||
| Research across Notion and synthesize into structured documentation; use when gatheri… | ||
| Access and analyze OpenAlex scholarly metadata through the REST API, including works,… | ||
| Convert accounting and finance papers into dissemination assets — interactive project… | ||
| This skill should be used when converting academic papers into promotional and presen… | ||
| PDF manipulation toolkit. Extract text/tables, create PDFs, merge/split, fill forms, … | ||
Holistic pedagogical review of a lecture deck (.qmd or .tex). Checks narrative ar… |
||
| Structured manuscript/grant review with checklist-based evaluation. Use when writing … | ||
| Diagnose why Antigravity is (or isn’t) prompting for permission. By default reads onl… | ||
| Interactive visualization library. Use when you need hover info, zoom, pan, or web-em… | ||
| Fast in-memory DataFrame library for datasets that fit in RAM. Use when pandas is too… | ||
| Compute statistical power, required sample size, and minimum detectable effect (MDE) … | ||
| Presentation toolkit (.pptx). Create/edit slides, layouts, content, speaker notes, co… | ||
| Draft a structured preregistration document (OSF, AsPredicted, or AEA RCT Registry st… | ||
Review candidate [LEARN] entries in .agents/state/personal-memory.md (gitignored)… |
||
| Improve the readability and exposition of mathematical proofs that are already veri… | ||
Read-only proofreading pass over lecture .tex or .qmd files. Checks grammar, typo… |
||
| Fast high-dimensional fixed-effects regression in Python with pyfixest (fixest-like s… | ||
| Bayesian modeling with PyMC. Build hierarchical models, MCMC (NUTS), variational infe… | ||
| Panel data analysis with Python using linearmodels and pandas. | ||
| Adversarial Quarto-vs-Beamer parity QA. A critic agent compares the Quarto HTML rende… | ||
| Run IV, DiD, and RDD analyses in R with proper diagnostics | ||
| Run the full R package release gate — regenerate docs, run the test suite, run R CMD … | ||
| Assemble a submission-ready replication package to the AEA Data and Code Availability… | ||
| Generate structured research questions, testable hypotheses, and candidate empirical … | ||
| Look up current research information using Perplexity Sonar Pro Search or Sonar Reaso… | ||
| Turn student course evaluations (free-text + numeric) into an actionable teaching-imp… | ||
| Generate a structured response-to-referees document from a referee report and the rev… | ||
| Comprehensive manuscript review with three modes: single-pass (default), –adversaria… | ||
Read-only R code review protocol for .R scripts. Checks code quality, reproducibili… |
||
| Scaffold a graded problem set with sections, problems, worked solutions, and short “w… | ||
| Systematically evaluate scholarly work using the ScholarEval framework, providing str… | ||
| Creative research ideation and exploration. Use for open-ended brainstorming sessions… | ||
| Evaluate scientific claims and evidence quality. Use for assessing experimental desig… | ||
| Create publication-quality scientific diagrams using Nano Banana Pro AI with smart it… | ||
| Build slide decks and presentations for research talks. Use this for making PowerPoin… | ||
| Core skill for the deep research and writing tool. Write scientific manuscripts in fu… | ||
| Machine learning in Python with scikit-learn. Use when working with supervised learni… | ||
| Statistical visualization with pandas integration. Use for quick exploration of distr… | ||
| Pull SEC EDGAR filings, XBRL financials, and Form 3/4/5 insider trades for accounting… | ||
| Mechanize Pattern 15 — the seven-pass adversarial review protocol for academic manusc… | ||
| Model interpretability and explainability using SHAP (SHapley Additive exPlanations)…. | ||
| Process-based discrete-event simulation framework in Python. Use this skill when buil… | ||
| Scaffold and run a reproducible Monte Carlo simulation study in R — parameterized DGP… | ||
| Multi-agent comprehensive slide review (visual + pedagogy + proofreading, plus TikZ /… | ||
| Create, edit, render, verify, and export PowerPoint slide decks. Use when Codex needs… | ||
| Use this skill when a user requests to create, modify, analyze, visualize, or work wi… | ||
| > Comprehensive Stata reference for writing correct .do files, data management, e… | ||
| >- Develop high-performance C/C++ plugins for Stata using the stplugin.h SDK. Use… | ||
| Clean and transform messy data in Stata with reproducible workflows | ||
| Run regression analyses in Stata with publication-ready output tables. | ||
End-to-end Stata replication pipeline — scaffolds numbered .do files in scripts/st... | | | | Guided statistical analysis with test selection and reporting. Use when you need help... | | | | Statistical models library for Python. Use when you need specific model classes (OLS,... | | | | Generate the submission-time disclosure block for a manuscript — the AI-use disclosur... | | | | Build or restructure a course syllabus from a topic list or reading list — course des... | | | | Use this skill when working with symbolic mathematics in Python. This skill should be... | | | | Turn a research paper into teaching materials — a lecture outline, the 3-5 results wo... | | | | Translate a Beamer.texlecture to a Quarto RevealJS.qmdmirror. Multi-phase: Ti... | | | | Triage academic email and calendar (Gmail / Google Calendar via the session's MCP) in... | | | | UMAP dimensionality reduction. Fast nonlinear manifold learning for 2D/3D visualizati... | | | | Reminds and assists the user in updating the MEMORY.md file with key decisions, miles... | | | | Use this skill for processing and analyzing large tabular datasets (billions of rows)... | | | | Validate bibliography entries against citations in all lecture files. Structural chec... | | | | Access comprehensive LaTeX templates, formatting requirements, and submission guideli... | | | | Run Chain-of-Verification (CoVe) on a draft or a block of text with factual claims. S... | | | | Adversarial visual-layout audit of a Quarto.qmdor Beamer.tex` deck. Flags overf… |
||
| > Web scraping skill for economists and applied researchers. Use this skill whene… | ||
| This skill should be used when the user asks to “query WRDS”, “access Compustat”, “ge… | ||
| Spreadsheet toolkit (.xlsx/.csv). Create/edit with formulas/formatting, analyze data,… |
B.3 All Rules
Always-on (load every session):
| Rule | File | Purpose |
|---|---|---|
| Plan-First Workflow | plan-first-workflow.md |
Plan mode + context preservation |
| Orchestrator Protocol | orchestrator-protocol.md |
Contractor mode loop |
| Session Logging | session-logging.md |
Three logging triggers |
| Meta-Governance | meta-governance.md |
Template vs working project distinctions |
Path-scoped (load only when working on matching files):
| Rule | File | Triggers On |
|---|---|---|
| Verification Protocol | verification-protocol.md |
.tex, .qmd, docs/ |
| Single Source of Truth | single-source-of-truth.md |
Figures/, .tex, .qmd |
| Quality Gates | quality-gates.md |
.tex, .qmd, *.R |
| R Code Conventions | r-code-conventions.md |
*.R |
| TikZ Quality | tikz-visual-quality.md |
.tex |
| TikZ Prevention | tikz-prevention.md |
Slides/**, Figures/**, Preambles/** |
| TikZ Measurement | tikz-measurement.md |
Slides/**, Figures/**, Preambles/**, scripts/** |
| Beamer-Quarto Sync | beamer-quarto-sync.md |
.tex, .qmd |
| PDF Processing | pdf-processing.md |
master_supporting_docs/ |
| Proofreading Protocol | proofreading-protocol.md |
.tex, .qmd, quality_reports/ |
| No Pause | no-pause-beamer.md |
.tex |
| Replication Protocol | replication-protocol.md |
*.R |
| Knowledge Base | knowledge-base-template.md |
.tex, .qmd, *.R |
| Orchestrator Research | orchestrator-research.md |
*.R, explorations/ |
| Exploration Folder | exploration-folder-protocol.md |
explorations/ |
| Exploration Fast-Track | exploration-fast-track.md |
explorations/ |
| Content Invariants | content-invariants.md |
.tex, .qmd, Preambles/, scripts/R/** |
| Cross-Artifact Review | cross-artifact-review.md |
master_supporting_docs/, .tex, .qmd |
| Summary–Body Parity | summary-parity.md |
CHANGELOG.md, README.md, .qmd, skill/rule/agent .md |
| Post-Flight Verification | post-flight-verification.md |
skills that generate factual claims (lit-review, research-ideation, respond-to-referees, review-paper, interview-me) |
| Model Routing | model-routing.md |
.agents/agents/**/*.md, .agents/skills/**/SKILL.md — 70/20/10 architect/editor split, per-agent model: field guidance (v1.9.0) |
| Stata Code Conventions | stata-code-conventions.md |
**/*.do, scripts/stata/** — header scaffold, numbered pipeline, esttab tables, clustering discipline, AEA compliance (v1.9.0) |
B.4 Hooks
| Hook | Type | Configuration |
|---|---|---|
| Session log reminder | Stop (command) | .agents/hooks/log-reminder.py |
| Desktop notification | Notification (command) | .agents/hooks/notify.sh |
| Context state capture | PreCompact (command) | .agents/hooks/pre-compact.py |
| Context restoration | SessionStart[compact|resume] (command) | .agents/hooks/post-compact-restore.py |
| Context monitor | PostToolUse[Bash|Task] (command) | .agents/hooks/context-monitor.py |
| Verification reminder | PostToolUse[Write|Edit] (command) | .agents/hooks/verify-reminder.py |
Additional hook events available in Antigravity (not used in this template but available for custom hooks):
| Event | When It Fires | Use Case |
|---|---|---|
UserPromptSubmit |
Before user message is processed | Input validation, auto-routing |
PermissionRequest |
When permission dialog appears | Auto-approve patterns, logging |
PostToolUseFailure |
When a tool call fails | Error tracking, retry logic |
SubagentStart |
When a subagent spawns | Resource tracking |
SubagentStop |
When a subagent completes | Result aggregation |
PostCompact |
After context compaction | Post-compaction cleanup |
SessionEnd |
When session closes | Final state saving, cleanup |
WorktreeCreate |
When a git worktree is created | Branch tracking |
WorktreeRemove |
When a git worktree is removed | Cleanup verification |
TaskCompleted |
When a background task finishes | Progress notifications |
ConfigChange |
When settings are modified | Audit logging |
B.5 Troubleshooting
B.5.1 LaTeX Won’t Compile
Symptom: xelatex errors or missing packages.
Fix: 1. Check you have XeLaTeX installed: which xelatex 2. Ensure TEXINPUTS includes Preambles/: the compile-latex skill handles this 3. Missing package? Install via TeX Live: tlmgr install [package]
B.5.2 Quarto Won’t Render
Symptom: quarto render fails or produces broken HTML.
Fix: 1. Check Quarto version: quarto --version (need 1.3+) 2. Check for syntax errors in YAML frontmatter 3. Missing TikZ SVGs? Run extract-tikz first
B.5.3 Hooks Not Firing
Symptom: No context warnings, no verification reminders.
Fix: 1. Check hooks are configured: cat .agents/settings.json | grep hooks 2. Ensure Python 3 is available: which python3 3. Check hook file permissions: ls -la .agents/hooks/
B.5.4 Gemini Ignores Rules
Symptom: Gemini doesn’t follow conventions in .agents/rules/.
Fix: 1. Rules use paths: frontmatter — check the path matches your files 2. Too many rules? Gemini follows ~150 instructions reliably. Consolidate. 3. Try: “Read .agents/rules/[rule].md and follow it for this task”
B.5.5 Context Lost After Compaction
Symptom: Gemini forgets what you were working on.
Fix: 1. Point Gemini to the plan: “Read quality_reports/plans/[latest].md” 2. Check session log: “Read quality_reports/session_logs/[latest].md” 3. The post-compact-restore.py hook should print recovery info automatically
B.5.6 Quality Score Too Low
Symptom: Score stuck below 80, can’t commit.
Fix: 1. Run slide-excellence to get detailed issue breakdown 2. Fix critical issues first (they cost -10 to -20 points each) 3. Ask Gemini: “What are the remaining critical issues?”
B.5.7 Skills Not Auto-Invoked
Symptom: Gemini doesn’t use skills when you describe a task.
Fix: 1. Be explicit in your request: “Review my slides for grammar and layout issues” 2. Check skill has auto-invocation enabled (no disable-model-invocation: true) 3. Skill descriptions help Gemini know when to use them — check they’re clear
B.5.8 Plans Saved to Wrong Directory
Symptom: Plans save to ~/.agents/plans/ instead of your project directory. Can’t track plans in git.
Fix: Add to .agents/settings.json:
{
"plansDirectory": "quality_reports/plans"
}This tells Antigravity to save plans inside your project where they can be version-controlled.