recursion

Manage nightly research dispatch scheduling and state files under ~/.claude/recursion.

3|1|Updated Apr 4, 2026
One-click install
npx skills add https://github.com/epologee/leclause-skills --skill recursion-epologee
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: recursion
Source: https://github.com/epologee/leclause-skills/tree/main/packages/recursion/skills/recursion
Command: npx skills add https://github.com/epologee/leclause-skills --skill recursion-epologee

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Coordinates and automates the nightly workflow-improvement loop so you no longer have to manually schedule research runs, update run state, or manage rejected plans and blocklists. It centralizes schedule control, focus selection, and rejection handling while delegating actual research work to a dedicated sub-skill.

Core Features & Use Cases

  • Schedule Management: create and remove nightly cron triggers and store the trigger ID in state.
  • State Ownership: read and write only designated fields (schedule_id, focus) in ~/.claude/recursion/state.md.
  • Focus & Filtering: set or clear a thematic focus that downstream research runs consume.
  • Reject & Blocklist: mark plans as rejected by updating plan frontmatter and appending reasons to blocklist.md.
  • Delegation: dispatch synchronous research runs via the Skill tool or schedule background runs via RemoteTrigger without performing research itself.
  • Use Case: run a nightly automated discovery session at 01:03, review proposed plans the next morning, accept or reject them, and keep a persistent blocklist of rejected ideas.

Quick Start

Invoke the orchestrator now by issuing the slash command /recursion now to run a synchronous research dispatch.

Frequently Asked Questions about recursion

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate nightly cron scheduling for recurring research tasks?

Automate nightly research tasks by creating cron triggers that schedule recurring dispatches at specific times. The system stores the trigger ID in state files and manages schedule lifecycle without manual intervention.

What is the best way to manage state for recurring automation workflows?

Manage state for recurring workflows by reading and writing designated fields like schedule_id and focus to state.md files. This ensures persistent tracking across nightly runs and maintains workflow continuity.

How do I set up focus filtering for automated research dispatches?

Set up focus filtering by defining a thematic focus that downstream research runs consume. The system reads this focus from state files to guide automated discovery sessions toward specific topics.

Can I reject automated plans and maintain a blocklist for recurring workflows?

Reject plans by updating plan frontmatter and appending rejection reasons to blocklist.md. This maintains a persistent record of rejected ideas across nightly workflow-improvement loops.

Does the orchestration workflow perform research itself or delegate to sub-skills?

The orchestration workflow delegates research to sub-skills synchronously or via scheduled remote triggers. It handles scheduling, state management, and rejection without performing research directly.

What are the limitations of using cron triggers for nightly workflow automation?

Cron triggers require proper schedule lifecycle management, including trigger creation and deletion with ID persistence in state files. Without cleanup, orphaned triggers may accumulate and cause duplicate dispatches.