conjure — community conjure, distillate, rlacombe, community, ai agent skill, ide skills, agent automation, AI agent skills, Claude Code, Cursor, Windsurf

v1.0.0
GitHub

About this Skill

Perfect for Research Agents needing automated paper reading workflow and experimentalist agent setup. Automate paper reading workflow between Zotero and reMarkable

rlacombe rlacombe
[63]
[2]
Updated: 3/23/2026

Quality Score

Top 5%
38
Excellent
Based on code quality & docs
Installation
SYS Universal Install (Auto-Detect)
> npx killer-skills add rlacombe/distillate/conjure
Supports 19+ Platforms
Cursor
Windsurf
VS Code
Trae
Claude
OpenClaw
+12 more

Agent Capability Analysis

The conjure skill by rlacombe is an open-source community AI agent skill for Claude Code and other IDE workflows, helping agents execute tasks with better context, repeatability, and domain-specific guidance.

Ideal Agent Persona

Perfect for Research Agents needing automated paper reading workflow and experimentalist agent setup.

Core Value

Empowers agents to automate paper reading workflows between Zotero and reMarkable, utilizing AI coding for experimentalist agent setup, and supports research goal definition, directory path management, and time budget allocation, all while leveraging AI-driven analysis and experimental design.

Capabilities Granted for conjure

Automating research paper analysis and organization
Generating experimentalist agents for research hypothesis testing
Streamlining research workflows between Zotero and reMarkable

! Prerequisites & Limits

  • Requires user-provided research goal and optional directory path or template name
  • Dependent on AI coding capabilities for experimentalist agent setup
  • Time budget per iteration must be defined, defaulting to 5 minutes if not specified
Project
SKILL.md
1.4 KB
.cursorrules
1.2 KB
package.json
240 B
Ready
UTF-8

# Tags

[No tags]
SKILL.md
Readonly

Conjure a Experimentalist Agent

Summon a new experiment agent into being. From an empty flask (directory) to a living, running experimentalist agent.

Arguments

The user provides a research goal, and optionally a directory path, constraints, or a template name.

Steps

  1. Gather requirements: Ask the user for:

    • Research goal / hypothesis
    • Experiment directory path (or create a new one under EXPERIMENTS_ROOT)
    • Time budget per iteration (default: 5 minutes) — controls the MAX_SECONDS guard
    • Constraints (max sessions, hardware, model preference)
    • Whether to base on a template (mcp__distillate__list_templates) or start fresh
  2. Initialize: Call mcp__distillate__init_experiment with the path and goal

    • This scans the directory, drafts PROMPT.md with Claude, sets up hooks and tracking
    • Review the generated protocol with the user
  3. Set goals: Call mcp__distillate__update_goals to set measurable success criteria

    • Pull baselines from literature if relevant (mcp__distillate__extract_baselines)
  4. Launch: On user approval, call mcp__distillate__manage_session with action="start"

    • The experimentalist agent comes alive in a tmux session
  5. Verify: Call mcp__distillate__manage_session with action="status" to confirm it's running

  6. Create GitHub repo: Offer to call mcp__distillate__create_github_repo for public tracking

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is conjure?

Perfect for Research Agents needing automated paper reading workflow and experimentalist agent setup. Automate paper reading workflow between Zotero and reMarkable

How do I install conjure?

Run the command: npx killer-skills add rlacombe/distillate/conjure. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for conjure?

Key use cases include: Automating research paper analysis and organization, Generating experimentalist agents for research hypothesis testing, Streamlining research workflows between Zotero and reMarkable.

Which IDEs are compatible with conjure?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for conjure?

Requires user-provided research goal and optional directory path or template name. Dependent on AI coding capabilities for experimentalist agent setup. Time budget per iteration must be defined, defaulting to 5 minutes if not specified.

How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add rlacombe/distillate/conjure. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use conjure immediately in the current project.

Related Skills

Looking for an alternative to conjure or another community skill for your workflow? Explore these related open-source skills.

View All

widget-generator

Logo of f
f

Generate customizable widget plugins for the prompts.chat feed system

149.6k
0
Design

flags

Logo of vercel
vercel

The React Framework

138.4k
0
Browser

pr-review

Logo of pytorch
pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

98.6k
0
AI

antd-commit-msg

Logo of ant-design
ant-design

Generate a single-line commit message for ant-design by reading the projects git staged area and recent commit style. Use when the user asks for a commit message, says msg, commit msg, 写提交信息, or wants

97.8k
0
Design