agentleFS
Sign inStart free
DeadpoolmineDeadpoolmine/systematic-research-skills/CLAUDE.md

systematic-research-skills

CLAUDE.md14 starsChanged 4 months agoMITView on GitHub

Research methodology skills for coding agents — structured paper writing, persona-driven peer review, and knowledge synthesis. Skills follow the writing-skills methodology. Style reference: Skills use superpowers-level conciseness — sharp <HARD-GATE> tags, flowcharts as primary structure, no verbose tables or rationalization sections. When working in this repo: - Write SKILL.md first, then supporting files as needed - When a skill references templates, tell the agent to list templates/ — never assume what's there - Cross-platform: provide both .cmd (Windows) and .sh…

The file

We split this CLAUDE.md into the rules it gives an agent

6 rules. About 0 are common, 2 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Scripts must support Windows + Linux: Every script has .cmd and .sh variants.

    line 26
  2. Distinctive:

    Description field is trigger-only: Start with "Use when..." — never summarize the skill's workflow.

    line 28
  3. Distinctive:

    When working in this repo:

    line 32
  4. Very specific:

    Write SKILL.md first, then supporting files as needed

    line 33
  5. Very specific:

    When a skill references templates, tell the agent to list templates/ — never assume what's there

    line 34
  6. Very specific:

    Keep SKILL.md under 100 lines — move details to supporting files

    line 36

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md 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
CLAUDE.md

Systematic Research Skills

Research methodology skills for coding agents — structured paper writing, persona-driven peer review, and knowledge synthesis.

Project Conventions

Skill Development

Skills follow the writing-skills methodology.

Style reference: Skills use superpowers-level conciseness — sharp <HARD-GATE> tags, flowcharts as primary structure, no verbose tables or rationalization sections.

Directory Structure

skills/<name>/
  SKILL.md           # Main reference (required) — concise, flowchart-driven
  *.md               # Supporting references (heavy content only)
  scripts/           # Reusable tools (cross-platform: .cmd + .sh)
  templates/         # Discoverable templates — agent lists, not hardcodes

Key Rules

  • Never hardcode template paths. Agents list templates/ recursively to discover available types.
  • Scripts must support Windows + Linux. Every script has .cmd and .sh variants.
  • SKILL.md is the entry point. Supporting files are loaded on demand, not force-loaded with @ syntax.
  • Description field is trigger-only. Start with "Use when..." — never summarize the skill's workflow.

Agent Behavior

When working in this repo:

  • Write SKILL.md first, then supporting files as needed
  • When a skill references templates, tell the agent to list templates/ — never assume what's there
  • Cross-platform: provide both .cmd (Windows) and .sh (Linux/macOS) scripts
  • Keep SKILL.md under 100 lines — move details to supporting files

Contributing

See CONTRIBUTING.md for guidelines.

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