agentleFS
Sign inStart free
ckt520728ckt520728/claude-skills/jev-autoresearch-rsi/SKILL.md

jev-autoresearch-rsi

Skill0 starsChanged 5 months agoNo licenceView on GitHub

Build and run a custom autoresearch agent on the Jev-Engineering two-phase workflow. A high-tier planner sets the plan, parallel medium-tier executors work it, and a high-tier auditor (ideally from a different provider) reviews the result, with a replan loop between them. The agent collects real evidence from PubMed, arXiv, ClinicalTrials.gov, a Gemini Notebook / NotebookLM notebook and local PDFs, then writes: - an English paper with APA 7 citations - a 15-slide PowerPoint deck - an interactive HTML deck - a zh-TW blog post Each run merges into an Obsidian "Second Brain" wiki, and a knowledge-base RSI step measures and improves that wiki, keeping only changes that measurably help. A local dashboard (port 8090) shows the graph, the sources, the deliverables, the wiki and the RSI ledger. Portable: - Providers: Claude, OpenAI or Gemini (OpenAI-compatible), with model tiers set in project.json. - Tools: these instructions work in Claude Code, Codex, Gemini CLI, Antigravity or OpenCode. - OS: Windows, macOS or Linux. Use when the user asks for an "autoresearch agent", "Jev planner/executor/auditor research loop", "research a topic and write paper + slides + blog and update my knowledge base", "知識庫 RSI", "自主研究代理", or "upgrade my RSI knowledge dashboard with a knowledge base". Not for a single article (article-writer), a single deck (soil-deck-pipeline), or a metrics dashboard (dashboard-builder).

  • Reads credentials
  • Commits and pushes

The file

We split this skill into the rules it gives an agent

12 rules. About 0 are common, 5 are distinctive, and 7 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 7

    Very specific

    Tied to their project's names, files or tools. Probably skip.

No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free