agentleFS
Sign inStart free
0SxD0SxD/agent-skills-plugin-v01/skills/research-gate/SKILL.md

research-gate

Skill0 starsChanged 7 months agoMITView on GitHub

Use when writing or editing .py files. Enforces approved-source research before code writes. Trigger: any .py file creation or modification. This skill reads config/approved_sources.json and validates that research.md contains URLs from approved domains that actually resolve. Blocks writes without valid research.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. aemerson-commits/shareable-skills★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository6 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before ANY .py file can be written or edited:

    line 14
  2. Very specific:

    Default approved domains: arxiv.org, github.com

    line 25

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Research Gate

What it enforces

Before ANY .py file can be written or edited:

  1. A research.md file must exist at the target project root
  2. It must be fresh (modified within the configured window)
  3. It must contain URLs from domains listed in config/approved_sources.json for the active project
  4. URLs must actually resolve (not just domain-match — the link must be real)
  5. Citations are logged to .claude/research_citations.log (append-only TSV)

Approved sources

Sources are defined per-project in config/approved_sources.json. The agent NEVER modifies this file. Only Sage adds entries via /sagex:approve-source or /sagex:edit-mode.

Default approved domains: arxiv.org, github.com

Project-specific domains inherit from global + project-level entries.

What happens on failure

  • No research.md: BLOCK. Agent must research first.
  • Stale research.md: BLOCK. Agent must refresh research.
  • No approved URLs: BLOCK. Agent must find approved sources.
  • URLs from unapproved domains: BLOCK. Denial message lists approved domains.
  • URL doesn't resolve: BLOCK. Agent must verify the link works.

Integration

This skill describes the behavior. The mechanical enforcement is in hooks/validate_research.py which fires as a PreToolUse hook on Write/Edit events. The skill exists so agents understand WHY they're being blocked and what to do about it.

Download now (ZIP)

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