{"id":48380790,"url":"https://github.com/flonat/claude-research","last_synced_at":"2026-04-05T20:01:59.898Z","repository":{"id":339586250,"uuid":"1162504337","full_name":"flonat/claude-research","owner":"flonat","description":"Shareable Claude Code infrastructure for PhD researchers — skills, agents, hooks, and rules for academic workflows","archived":false,"fork":false,"pushed_at":"2026-03-23T21:19:36.000Z","size":1481,"stargazers_count":16,"open_issues_count":0,"forks_count":1,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-03-24T19:54:57.778Z","etag":null,"topics":["academic-research","ai-tools","claude","claude-code","latex","phd","research-workflow"],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/flonat.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":"docs/agents.md","dco":null,"cla":null}},"created_at":"2026-02-20T10:45:59.000Z","updated_at":"2026-03-23T21:19:40.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/flonat/claude-research","commit_stats":null,"previous_names":["flonat/claude-code-public","flonat/claude-code-flonat","flonat/claude-research"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/flonat/claude-research","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/flonat%2Fclaude-research","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/flonat%2Fclaude-research/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/flonat%2Fclaude-research/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/flonat%2Fclaude-research/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/flonat","download_url":"https://codeload.github.com/flonat/claude-research/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/flonat%2Fclaude-research/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31448216,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-05T15:22:31.103Z","status":"ssl_error","status_checked_at":"2026-04-05T15:22:00.205Z","response_time":75,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["academic-research","ai-tools","claude","claude-code","latex","phd","research-workflow"],"created_at":"2026-04-05T20:01:59.136Z","updated_at":"2026-04-05T20:01:59.892Z","avatar_url":"https://github.com/flonat.png","language":"Python","funding_links":[],"categories":["Skills, Workflow Packs, and Reusable Procedures"],"sub_categories":[],"readme":"\u003c!-- Governed by: skills/shared/project-documentation.md --\u003e\n\n# Claude Code for an Academic Researcher\n\nMade by a humble PhD student. A complete Claude Code infrastructure for researchers — skills, agents, hooks, and rules for academic workflows. Built for researchers who write papers in LaTeX, manage bibliographies, run experiments, and want AI assistance that understands academic conventions.\n\nWorks on **macOS, Linux, and Windows**. Use Claude Code from the [terminal CLI](https://docs.anthropic.com/en/docs/claude-code), [VS Code](https://marketplace.visualstudio.com/items?itemName=anthropics.claude-code), [JetBrains IDEs](https://plugins.jetbrains.com/plugin/27189-claude-code), [the web](https://claude.ai/code), or the [desktop app](https://claude.ai/download) — all share the same skills, agents, and rules.\n\n[![npm version](https://img.shields.io/npm/v/flonat-research)](https://www.npmjs.com/package/flonat-research)\n[![GitHub release](https://img.shields.io/github/v/release/flonat/claude-research)](https://github.com/flonat/claude-research/releases)\n\n## Installation\n\n### Quick Install (npm)\n\n```bash\nnpx flonat-research\n```\n\nThis downloads the package and runs the setup script, which symlinks skills, agents, hooks, and rules into `~/.claude/`.\n\n### Full Install (recommended for customisation)\n\n#### macOS / Linux\n\n```bash\ngit clone https://github.com/flonat/claude-research.git\ncd claude-research\n./scripts/setup.sh\n```\n\n#### Windows (PowerShell)\n\n```powershell\ngit clone https://github.com/flonat/claude-research.git\ncd claude-research\n.\\scripts\\setup.ps1\n```\n\nThe git clone gives you a local copy you can fully customise — edit `.context/profile.md`, `CLAUDE.md`, and workflows to match your research.\n\n### Update\n\n```bash\n# macOS/Linux: pull latest, then re-link without overwriting settings\ngit pull \u0026\u0026 ./scripts/setup.sh --update\n\n# Windows (PowerShell):\ngit pull; .\\scripts\\setup.ps1 -Update\n```\n\nThen customise `.context/profile.md`, `.context/current-focus.md`, and `CLAUDE.md` with your details. See [`docs/getting-started.md`](docs/getting-started.md) for the full guide (includes Windows-specific setup, Python install, and troubleshooting).\n\n### Related Packages\n\n| Package | Install | Description |\n|---------|---------|-------------|\n| [`llm-council`](https://github.com/flonat/llm-council) | `pip install llm-council` | Multi-model council via OpenRouter API |\n| [`cli-council`](https://github.com/flonat/cli-council) | `pip install cli-council` | Multi-model council via local CLI tools |\n\n## What's Included\n\n\u003c!-- COMPONENT-TABLE:START --\u003e\n\u003c!-- auto-generated by generate-public-docs.py — do not edit manually --\u003e\n| Component | Count | Description |\n|-----------|-------|-------------|\n| **Skills** | 38 | Slash commands for common tasks (`/proofread`, `/latex-autofix`, `/literature`, etc.) |\n| **Agents** | 6 | Specialised reviewers (peer review, referee 2, paper critic, domain review, fixer) |\n| **Hooks** | 8 | Automated guardrails (destructive git protection, context monitoring, etc.) |\n| **Rules** | 9 | Always-on policies (plan before implementing, scope discipline, etc.) |\n| **Context library** | — | Structured files that give Claude persistent memory across sessions |\n| **Research Vault** | — | Obsidian-style markdown vault for tasks, pipeline, submissions, venues, people |\n| **Bibliography MCP** | — | Multi-source scholarly search (OpenAlex + Scopus + WoS) — [setup guide](docs/biblio-setup.md) |\n| **Council mode** | — | Multi-model deliberation (3 reviewers + synthesis) — [setup guide](docs/council-mode.md) |\n| **CLI tools** | — | Vault task management from the terminal — [docs](docs/scripts.md) |\n\u003c!-- COMPONENT-TABLE:END --\u003e\n\n## Architecture\n\n\u003c!-- ARCHITECTURE:START --\u003e\n\u003c!-- synced from private README — do not edit manually --\u003e\n```\n┌──────────────────────────────────────────────────────────────┐\n│  Claude Code (Terminal)              Claude Desktop (GUI)     │\n│         │                                   │                │\n│    CLAUDE.md + Rules              MCP Server (load-context)   │\n│         │                                   │                │\n│    ┌────┴──────────────┬──────────────┐     │                │\n│    │                   │              │     │                │\n│  Context ◄─────────  Skills    ◄──────┼─────┘                │\n│  Library               │              │                      │\n│                   CLI Scripts    Research Vault               │\n│                                                              │\n│  MEMORY.md ◄───────  Hooks \u0026                                 │\n│  + Logs            Permissions                               │\n└──────────────────────────────────────────────────────────────┘\n```\n\nThe MCP server's `load-context` tool gives Claude Desktop access to the context library and MEMORY.md — the same files Claude Code reads automatically.\n\u003c!-- ARCHITECTURE:END --\u003e\n\n## Components\n\n**Context Library** (`.context/`) — Markdown files that give Claude persistent memory about you, your projects, and your workflows. Instead of re-explaining your research every session, Claude reads these files automatically.\n\n**Skills** (`skills/`) — Slash commands invoked with `/\u003cskill-name\u003e` or natural language.\n\u003c!-- SKILLS-SUMMARY:START --\u003e\n\u003c!-- auto-generated — do not edit manually --\u003e\n38 skills available. Key examples: `/proofread`, `/latex-autofix`, `/literature`, `/bib-validate`, `/code-review`, `/session-recap`, and more.\n\u003c!-- SKILLS-SUMMARY:END --\u003e\nSee [`docs/skills.md`](docs/skills.md) for the full catalogue.\n\n**Agents** (`.claude/agents/`) — Specialised personas for complex review tasks, spawning sub-agents for parallel work.\n\n\u003c!-- AGENTS-TABLE:START --\u003e\n| Agent | Use case |\n|-------|----------|\n| `domain-reviewer` | Research-focused substantive correctness agent |\n| `fixer` | Generic fix implementer for any critic report |\n| `paper-critic` | Read-only adversarial auditor for LaTeX papers |\n| `peer-reviewer` | Use this agent when you need to review someone else's paper — as a peer reviewer, discussant, or for reading group preparation |\n| `proposal-reviewer` | Use this agent when you need to review a research proposal, extended abstract, conference submission outline, or pre-paper plan — either his own or someone else's |\n| `referee2-reviewer` | Use this agent when the user wants a rigorous, adversarial academic review of their work — including papers, manuscripts, research designs, code, or arguments |\n\n\u003c!-- AGENTS-TABLE:END --\u003e\n\nSee [`docs/agents.md`](docs/agents.md) for detailed descriptions.\n\n**Hooks** (`hooks/`) — Automated guardrails that run at specific points in a session.\n\n\u003c!-- HOOKS-TABLE:START --\u003e\n| Hook | Trigger | What it does |\n|------|---------|-------------|\n| `block-destructive-git.sh` | Before Bash | catches dangerous git/shell commands |\n| `context-monitor.py` | After tool use | tracks tool call count as a heuristic for context usage |\n| `postcompact-restore.py` | After compact | restores state after context compression |\n| `precompact-autosave.py` | Before compact | saves state before context compression |\n| `promise-checker.sh` | Session stop | catches \"performative compliance\": Claude says it remembered/noted/saved |\n| `protect-source-files.sh` | Before edit/write | prompts confirmation for files outside |\n| `resume-context-loader.sh` | Session resume | surfaces current focus and latest session log |\n| `startup-context-loader.sh` | Session start | auto-detects and surfaces project documentation |\n\n\u003c!-- HOOKS-TABLE:END --\u003e\n\nSee [`docs/hooks.md`](docs/hooks.md) for full documentation.\n\n**Rules** (`.claude/rules/`) — Always-on policies enforcing good research practices. See [`docs/rules.md`](docs/rules.md).\n\n**Research Vault** — Obsidian-style markdown vault (`~/Research-Vault`) for tasks, pipeline, submissions, venues, people, and themes. Accessed via the `taskflow` MCP server.\n\n**Biblio MCP** — Multi-source scholarly search server (OpenAlex + optional Scopus \u0026 Web of Science). See [`docs/bibliography-setup.md`](docs/bibliography-setup.md).\n\n**Flonat-Papers MCP** — Zotero library management server (search, PDF extraction, semantic retrieval, BibTeX export). Lives in `packages/flonat-papers/` with bundled `bib-validate` and `bib-parse` skills.\n\n**Council Mode** — Multi-model deliberation with 3 LLM providers, anonymised cross-review, and chairman synthesis. See [`docs/council-mode.md`](docs/council-mode.md).\n\n## Workflows\n\n\u003c!-- WORKFLOWS:START --\u003e\n\u003c!-- synced from private README — do not edit manually --\u003e\n| Command | What happens |\n|---------|-------------|\n| \"Plan my day\" | Reads context, queries vault, asks questions, creates Must Do / Should Do / Could Do plan |\n| \"Extract actions from my meeting with [name]\" | Finds transcript, extracts tasks with full context, creates in vault |\n| \"Weekly review\" | 4-part reflection: clear the decks, review, plan, project check |\n| \"What's overdue?\" | Queries vault and summarises |\n| \"Proofread my paper\" | 7-category academic check (report only) |\n| \"Validate my bibliography\" | Cross-references `\\cite{}` keys against `.bib` |\n\u003c!-- WORKFLOWS:END --\u003e\n\n## Session Continuity\n\n\u003c!-- SESSION-CONTINUITY:START --\u003e\n\u003c!-- synced from private README — do not edit manually --\u003e\nEach session builds on previous ones:\n\n- `current-focus.md` — updated at session end with progress and next steps\n- `log/` — timestamped session logs\n- `log/plans/` — saved implementation plans\n- `MEMORY.md` — accumulated `[LEARN]` tags (notation, citation, code, method, domain corrections)\n\nThe recovery protocol reads the latest plan, session log, and current focus to resume seamlessly.\n\u003c!-- SESSION-CONTINUITY:END --\u003e\n\n## Project Structure\n\n\u003c!-- FILE-TREE:START --\u003e\n```\nclaude-research/\n├── CLAUDE.md                    # Main instruction file (customise this)\n├── README.md                    # This file\n├── MEMORY.md                    # Accumulated knowledge (auto-populated)\n├── .claude/\n│   ├── agents/                  # 6 specialised review agents\n│   ├── rules/                   # 9 auto-loaded policy rules\n│   └── settings.json            # Permissions, hooks, model config\n├── skills/                      # 38 slash commands\n│   ├── shared/                  # Shared utilities (palettes, scoring, rhetoric)\n│   ├── proofread/               # Academic proofreading\n│   ├── latex-autofix/           # LaTeX compilation + auto-fix\n│   ├── literature/              # Literature search + synthesis\n│   └── ...                      # See docs/skills.md for full list\n├── hooks/                       # 8 automated guardrails\n├── .context/                    # AI context library\n│   ├── profile.md               # Your identity and background\n│   ├── current-focus.md         # What you're working on NOW\n│   ├── projects/                # Project metadata\n│   ├── preferences/             # Workflow preferences\n│   ├── workflows/               # Process guides (daily review, etc.)\n│   └── resources/               # Reference data (journal rankings, etc.)\n├── .scripts/                    # CLI tools for vault task management\n├── mcp-bibliography/            # Multi-source scholarly search (OpenAlex + Scopus + WoS)\n├── packages/\n│   ├── cli-council/             # Multi-model council via local CLI tools\n│   ├── llm-council/             # Multi-model council via OpenRouter API\n│   └── mcp-bibliography/             # mcp-bibliography\n├── docs/                        # Component documentation\n├── log/                         # Session logs (auto-created)\n└── scripts/\n    └── setup.sh                 # Initial setup script\n```\n\u003c!-- FILE-TREE:END --\u003e\n\n## Design Principles\n\n\u003c!-- DESIGN-PRINCIPLES:START --\u003e\n\u003c!-- synced from private README — do not edit manually --\u003e\n1. **Lazy prompting** — Context files eliminate repetitive explanations\n2. **Hybrid local + cloud** — Markdown (versioned) + Research Vault (dynamic)\n3. **Question-driven** — AI asks questions before dumping lists\n4. **Read-only audits** — Proofread, validate, review — never auto-edit source\n5. **Session continuity** — Every session makes the next one better\n6. **Permission governance** — Global settings propagate automatically\n\u003c!-- DESIGN-PRINCIPLES:END --\u003e\n\n## Requirements\n\n| Tool | Why you need it | macOS | Linux | Windows |\n|------|----------------|-------|-------|---------|\n| [Claude Code](https://docs.anthropic.com/en/docs/claude-code) | The AI engine — runs skills, agents, hooks | `curl -fsSL https://claude.ai/install.sh \\| bash` | same | `winget install Anthropic.ClaudeCode` |\n| [Python 3.11+](https://www.python.org/) | Hooks and MCP servers | `brew install python@3.12` | `apt install python3.12` | `winget install Python.Python.3.12` |\n| [uv](https://docs.astral.sh/uv/) | Fast Python package manager — isolates dependencies, replaces `pip` | `brew install uv` | `curl -LsSf https://astral.sh/uv/install.sh \\| sh` | `winget install astral-sh.uv` |\n| [Git](https://git-scm.com/) | Version control | Included | `apt install git` | `winget install Git.Git` |\n| [TeX Live](https://tug.org/texlive/) | LaTeX compilation (`/proofread`, `/latex-autofix`) | `brew install --cask mactex` | `apt install texlive-full` | [install guide](https://tug.org/texlive/windows.html) |\n\nAlso available as a [VS Code extension](https://marketplace.visualstudio.com/items?itemName=anthropics.claude-code), [JetBrains plugin](https://plugins.jetbrains.com/plugin/27189-claude-code), [web app](https://claude.ai/code), or [desktop app](https://claude.ai/download).\n\nSee [`docs/getting-started.md`](docs/getting-started.md) for Fedora/Arch commands, Windows-specific setup, Python version guidance, and troubleshooting.\n\n## Credits\n\n\u003c!-- CREDITS:START --\u003e\n\u003c!-- synced from private README — do not edit manually --\u003e\nThis infrastructure draws on design patterns from several open-source workflows.\n\n### Academic Researchers\n\n- **[Scott Cunningham](https://github.com/scunning1975/MixtapeTools)** (MixtapeTools) — session logs, rhetoric-driven presentations, \"health inspector\" model for code audits, cross-language replication, author/reviewer separation\n- **[Pedro Sant'Anna](https://github.com/pedrohcgs/claude-code-my-workflow)** — specialist agents, plan-first protocol, quality gates, critic-fixer loops, [LEARN] tags\n- **[Jared Black](https://github.com/Black-JL/Research-Project-Flow)** — \"break the glass\" protocol for infrastructure changes, data sensitivity rules, reproducible project templates\n- **[Antonio Mele](https://github.com/meleantonio/awesome-econ-ai-stuff)** — curated AI-for-economists resources, programmatic Claude Code controller, scientific skills reference\n- **[Hugo Sant'Anna](https://github.com/hsantanna88/clo-author)** (CLO-Author) — open-source Claude Code workflow for applied econometrics, agents, 29 slash commands\n- **[Chris Blattman](https://github.com/chrisblattman/claudeblattman)** — academic AI workflows guide, non-developer-friendly skill and agent patterns\n\n### General Resources\n\n- **[Andrej Karpathy](https://github.com/karpathy/llm-council)** — multi-model council with peer review and synthesis (our fork: [llm-council](https://github.com/user/llm-council), [cli-council](https://github.com/user/cli-council))\n- **[rtk-ai](https://github.com/rtk-ai/rtk)** — RTK rewrite hook for 60–90% token savings on CLI output\n- **[NPC Worldwide](https://github.com/npc-worldwide/npcsh)** (npcsh) — knowledge graph sleep/dream cycles, inspiring the memory consolidation skill\n- **[Boris Cherny](https://github.com/AugmendTech/ChernyCode)** (ChernyCode) — AI coding assistant configuration patterns\n- **[Jim Christian](https://github.com/aplaceforallmystuff)** (aplaceforallmystuff) — creation-guard pre-flight checks, lessons-learned retrospective, ecosystem health diagnostics\n- **[blader](https://github.com/blader/Claudeception)** (Claudeception) — skill description optimization, post-match action table, solution pattern for skill creation, learning nudge hook\n- **[Anthropic](https://github.com/anthropics/claude-code)** — Claude Code platform, 8 adopted skill patterns (docx, xlsx, pptx, pdf, frontend-design, mcp-builder, webapp-testing, skill-creator)\n\nSystem created January 2026.\n\u003c!-- CREDITS:END --\u003e\n\n## Star History\n\n[![Star History Chart](https://api.star-history.com/svg?repos=flonat/claude-research\u0026type=Date)](https://star-history.com/#flonat/claude-research\u0026Date)\n\n## License\n\nMIT\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fflonat%2Fclaude-research","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fflonat%2Fclaude-research","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fflonat%2Fclaude-research/lists"}