agentleFS
Sign inStart free
Scientific-ToolingScientific-Tooling/structured-intelligence/skills/research/SKILL.md

research

Skill4 starsChanged 12 days agoMITView on GitHub

Rigorous research workflow for deep synthesis, first-principles reasoning, cross-domain transfer, adversarial review, prediction calibration, reproducibility, and research_vault memory writeback.

189 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use daily-arxiv, exp-eval and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • LambenthanSkill

    daily-arxiv

    每日从 arXiv 拉取新论文，过滤相关性，auto-ingest 高优先级论文，检测 SOTA 更新

    Also in 5 projects that use this

  • LambenthanSkill

    exp-eval

    实验判决门：Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 claims confidence、ideas status、graph edges

    Also in 5 projects that use this

  • truongtv22Skill

    Problem-Solving Techniques

    Apply systematic problem-solving techniques for complexity spirals (simplification cascades), innovation blocks (collision-zone thinking), recurring patterns (meta-pattern recognition), assumption constraints (inversion exercise), scale uncertainty (scale game), and dispatch when stuck. Techniques derived from Microsoft Amplifier project patterns adapted for immediate application.

    Also in 5 projects that use this

  • liufeng1976Skill

    setup-ts-deep-modules

    Wire dependency-cruiser into a TypeScript repo so each package is a deep module — implementation hidden in subfolders, reachable only through its entry-point files. User-invoked.

    Also in 43 projects that use this

  • skyllwtSkill

    exp-pilot-eval

    Pilot result evaluation — read pilot results, apply success criteria, update idea page (pilot_result, failure_reason if failed), generate PILOT_VERDICT_REPORT. Called by /ideate Phase 5 after /exp-pilot-run.

    Also in 4 projects that use this

  • skyllwtSkill

    exp-pilot-run

    Pilot experiment execution — read Pilot Spec YAML, write pilot code, run experiment(Confirm with the user before operation and require the applicant to conduct manual inspection), return results. Called by /ideate Phase 5. Does NOT modify wiki pages or judge pass/fail.

    Also in 4 projects that use this

  • +5 more from Lambenthan
  • +1 more from skyllwt

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 169 edited versions we read keep these.

  • 2

    Distinctive

    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. Distinctive:

    Use this skill for deep research tasks that require:

    line 10
  2. Very specific:

    Follow the full protocol in references/research_protocol.md.

    line 29
  3. Very specific:

    Treat references/system_prompt.md as behavioral constraints.

    line 30
  4. Very specific:

    Use local memory at ./research_vault/ when available.

    line 31
  5. Very specific:

    If filesystem write is restricted, return Simulated Vault Output and state limitations.

    line 32
  6. Distinctive:

    Use exact section titles:

    line 36

“Common” is measured: kept by at least 6 in 10 of the 169 edited versions of this file we could read. “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

Skill: Research

Use When

Use this skill for deep research tasks that require:

  • structured problem framing
  • state-of-the-art mapping
  • historical evolution and future direction mapping
  • falsifiable hypothesis generation
  • explicit uncertainty and evidence attribution
  • adversarial challenge and replication planning

Inputs

  • Required:
    • research question, decision, or hypothesis to investigate
    • enough context to define scope, audience, and constraints
  • Optional:
    • seed sources, prior notes, or local research_vault/ material
    • target output format, deadline, or calibration horizon

Workflow

  1. Follow the full protocol in references/research_protocol.md.
  2. Treat references/system_prompt.md as behavioral constraints.
  3. Use local memory at ./research_vault/ when available.
  4. If filesystem write is restricted, return Simulated Vault Output and state limitations.

Output Contract

Use exact section titles:

  1. Core Essence
  2. Evolutionary Map
  3. Vulnerabilities and Blind Spots
  4. Cross-Boundary Inspiration
  5. Falsifiable Conclusions

Append:

  • Source Table
  • Uncertainties
  • Self-Audit
  • Priority Matrix
  • Predictions and Calibration Plan
  • Adversarial Review
  • Replication Pack
  • Vault Writeback Log

Install

From repository root:

# Codex (default)
./scripts/install_skill.sh research

# Claude Code
./scripts/install_skill.sh research --tool claude

# Other tools
./scripts/install_skill.sh research --dest ~/.my-tool/skills

Limits

  • This skill is designed for rigorous synthesis, not instant answers.
  • Output quality depends on source quality, scope clarity, and available evidence.
  • Common failure cases:
    • weak or missing primary sources
    • underspecified scope or success criteria
    • missing filesystem access for real vault writeback

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