By linxule
AI-augmented research environment. Interview-first onboarding, Obsidian vault setup, document conversion, scheduled automation, and ongoing research tools for academics.
Generate a vault-specific onboarding handbook for a collaborator (RA, co-author, lab member)
**`${ARGS}` (skill-constructed)** is used by *thin wrappers* whose calling skill assembles a typed-flag argument list. The skill conducts the interview, resolves defaults, applies vault context, and then invokes the slash command with a fully-formed flag set. Because the wrapper body cannot contain conditionals, all orchestration lives in the skill — the wrapper just shells out.
Set up or update overnight vault maintenance and analytical tasks
Batch convert or transcribe a folder of files and file them to your vault
Save a web page or online article to your vault as markdown
Use when a researcher wants to think through ideas, get feedback on arguments, explore connections in their work, discuss a paper, or needs intellectual engagement. Triggers on 'help me think about', 'what do you think of', 'push back on this', 'what am I missing', 'explore connections'. <example>help me think through this argument</example> <example>what am I missing in this analysis?</example> <example>push back on my reasoning here</example>
Use when onboarding a new researcher into their AI research environment. Conducts a warm, adaptive interview to understand research area, data types, sensitivity needs, existing tools, and comfort level. Triggers on 'set up', 'get started', 'configure', 'onboard', or when .carrel/ directory is missing. <example>set up my research environment</example> <example>I'm new here, help me get started</example> <example>configure my tools for research</example>
This skill should be used when a researcher wants to configure, understand, or adjust unattended vault maintenance. Triggers on 'schedule', 'automate', 'overnight', 'background processing', 'morning brief', 'unattended', 'what did Carrel do', 'review automation settings', 'trust level', or '/carrel-automate'.
Portable AI-assisted research vault operations for setup, document ingestion, transcription, web capture, environment repair, trust and sensitivity routing, reflection, collaborator handoff, and feedback export. This is the standalone engine for hosts without the Carrel Claude Code plugin, such as Cowork, Codex, Kimi Code, Gemini CLI, OpenCode, and Claude.ai skill uploads. Do not use when the Carrel Claude Code plugin or the installed carrel CLI is available; that plugin drives the typed CLI as its runtime, not this pack.
This skill should be used when a researcher wants to share their Carrel vault with someone else — an RA, co-author, lab member, or advisor. Triggers on 'share with', 'onboard a collaborator', 'generate a handbook', 'lab handbook', 'help my RA get up to speed', or when the /carrel-share command is invoked. Distinct from /carrel-setup, which sets up a NEW vault for a NEW researcher; this skill assumes an existing vault with accumulated context.
This skill should be used when a researcher wants to convert a PDF, Word document, PowerPoint, spreadsheet, or image to markdown. Triggers on 'convert', 'import', 'add this paper', a dropped file path, or any mention of PDF/DOCX/PPTX/XLSX conversion.
Guided recovery for environment.json drift. Use when the researcher runs /carrel-fix, mentions environment drift, broken setup state, or wants help repairing conflicting settings.
Executes bash commands
Hook triggers when Bash tool is used
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Your private desk in the library. Set up by AI, built for thinking.
Carrel is a Claude Code plugin that onboards researchers into an AI-augmented research environment. It works by interviewing the researcher, assessing their machine, configuring the right tools, and teaching itself how to work with this specific person.
~/Documents/Research)Carrel's bootstrap install and setup flow are cross-platform across macOS, Linux, and Windows. The environment audit records audit.platform, install commands are platform-keyed, and the setup docs render OS-aware guidance.
| Tool | macOS | Linux | Windows | Notes |
|---|---|---|---|---|
| Install script | ✅ Full | ✅ Full | ✅ Full | install.sh on macOS/Linux, install.ps1 on Windows |
| Obsidian | ✅ Full | ✅ Full | ✅ Full | Native app on all three platforms; install commands differ by OS |
| liteparse | ✅ Full | ✅ Full | ✅ Full | npm install -g @llamaindex/liteparse on all three platforms |
| coli | ✅ Full | ✅ Full | ✅ Full | npm install -g @marswave/coli; some media formats may still need ffmpeg |
| defuddle | ✅ Full | ✅ Full | ✅ Full | npm install -g defuddle |
| gws | ✅ Full | ✅ Full | ✅ Full | npm install -g @googleworkspace/cli; Windows OAuth has a documented workaround |
| mineru | ✅ Full | ✅ Full | ✅ Full | Cloud service; requires MINERU_API_KEY |
| mistral_ocr | ✅ Full | ✅ Full | ✅ Full | Cloud OCR service; requires MISTRAL_API_KEY |
| paddleocr | ⚠️ Optional | ⚠️ Optional | ⚠️ Optional | Local OCR candidate for scanned PDFs; heavy Python/model install, not a default |
| markitdown | ✅ Full | ✅ Full | ✅ Full | Bundled with Carrel's Python environment |
/carrel-* for setup, conversion, automation, collaboration, reflection, migration, recovery, model teammates — 7 of these are now thin wrappers over typed CLI subcommands; see commands/CONVENTIONS.md)carrel CLI — paper, transcript, capture, google, vault, env, setup-state, trust, automate, batch, migrate subcommand groups)| Command | What it does |
|---|---|
/carrel-automate | Set up or update overnight vault maintenance and analytical tasks |
/carrel-batch | Batch convert or transcribe a folder of files and file them to your vault |
/carrel-capture | Save web content to your vault |
/carrel-cheatsheet | Regenerate your reference card |
/carrel-fix | Diagnose environment drift and guide recovery |
/carrel-setup | Full onboarding: interview, audit, scaffold vault |
/carrel-status | Check what's installed and working |
/carrel-convert | Convert PDF/Word/slides to markdown in your vault |
/carrel-feedback | Generate anonymized feedback digest for sharing |
/carrel-migrate | Check for updates, show what's new, apply migrations |
/carrel-mirror | Synthesize your research patterns from reflections and logs |
/carrel-reflect | End-of-session reflection |
/carrel-share | Generate a collaborator handbook for this vault |
/carrel-teammates | Add, remove, or review model teammates (Codex, Gemini, Kimi) |
/carrel-transcribe | Transcribe audio to text in your vault |
Carrel's automation trust model is now code-enforced, not just narrated in skill markdown. Advisory, Consultative, Delegated, and Partnership still define the relationship contract, but writes that cross those boundaries now go through carrel trust check <action> before the skill proceeds. Use uv run carrel trust list --vault . to see the current action matrix for a vault.
Claude Code plugin that delegates read-only review, challenge, free-form ask, and write-capable rescue work to the local kimi-code CLI. Includes an opt-in stop-time review gate and a PreToolUse hook that enforces per-command safety.
Collaborative memory for human-AI work — persistent, searchable, interconnected
Atelier of Co-Apprenticeship for interpretive qualitative research. Human and AI learn together as apprentices to the craft tradition (rigor, reflexivity, theoretical sensitivity). Three stages: Solo Practice → Side-by-Side Collaboration → Dialogue with Tradition. Prevents calculator mindset, embeds meta-cognition, maintains human interpretive authority.
Epistemic Partnership System for AI-Assisted Qualitative Research. Cowork-compatible version with commands and skills.
npx claudepluginhub linxule/carrel --plugin carrelHarness-native ECC plugin for engineering teams - 67 agents, 279 skills, 94 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses
v9.54.1 — Reliability wave: tangle contextual review correction loop with hard round ceiling, progress-supervised review rounds (per-agent stall watch, descendant-tree kills), council diversity and agy pin fixes, marketplace generator source-of-truth fix, provider troubleshooting runbook and cost-expectations docs. Run /octo:setup.
Evidence-gated AI coding workflow: scan → analyze → plan → TDD → execute → fix → verify → review, powered by Codebase Memory MCP >= 0.9.0 with optional Serena LSP intelligence. Includes blast-radius planning, test/cycle gates, independent review, and Windows Git Bash hook auto-resolution.
Claude harness - A harness for solo developers (Vibecoders) to handle full-cycle contract development.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.