agentleFS
jmolzjmolz/m0lz.01/.agents/skills/research/SKILL.md

research

Skill0 starsChanged 6 months agoMITView on GitHub

Use this skill when performing research tasks — codebase analysis, web research, documentation gathering, technology evaluation, or library comparison. Triggers: 'research', 'investigate', 'explore', 'find out', 'compare options', 'what are best practices for', 'look into'. Provides structured research patterns for both codebase and external research.

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

11 rules. 0 are common, 10 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 170 edited versions we read keep these.

  • 10

    Distinctive

    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:

    Read import statements to understand module relationships

    line 33
  2. Very specific:

    Check package.json/pyproject.toml for external dependencies

    line 34
  3. Distinctive:

    Start with entry points (main, index, app)

    line 39
  4. Distinctive:

    Follow the request/response path

    line 40
  5. Distinctive:

    Look for patterns: MVC, layered, event-driven, etc.

    line 42
  6. Distinctive:

    When comparing libraries or tools, assess:

    line 47
  7. Distinctive:

    When collecting docs for a plan or implementation:

    line 57
  8. Distinctive:

    Look for migration guides if upgrading

    line 63
  9. Distinctive:

    Always structure research findings as:

    line 67
  10. Distinctive:

    When running as a sub-agent for research:

    line 90
  11. Distinctive:

    Read broadly, summarize tightly

    line 92

“Common” is measured: kept by at least 6 in 10 of the 170 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

Research Skill

When to Use

The agent should read this skill when doing any research task — whether exploring a codebase, researching libraries, or gathering documentation.

Codebase Research

Finding Patterns

# Find all files matching a pattern
find . -name "*.ts" -not -path "*/node_modules/*" | head -30

# Search for a specific pattern in code
grep -rn "pattern" --include="*.ts" src/

# Find usage of a function or type
grep -rn "functionName" --include="*.ts" --include="*.tsx" .

# Find recent changes to a file or area
git log --oneline -10 -- path/to/file
git log --oneline -10 -- "src/area/**"

# See who changed what recently
git log --oneline --all --since="2 weeks ago" | head -20

Mapping Dependencies

  • Read import statements to understand module relationships
  • Check package.json/pyproject.toml for external dependencies
  • Trace data flow: entry point → handler → service → storage
  • Identify shared utilities and types

Understanding Architecture

  • Start with entry points (main, index, app)
  • Follow the request/response path
  • Identify boundaries between modules/packages
  • Look for patterns: MVC, layered, event-driven, etc.

External Research

Library Evaluation

When comparing libraries or tools, assess:

  1. Maintenance: Last commit, open issues, release frequency
  2. Adoption: GitHub stars, npm/pip weekly downloads
  3. Compatibility: Works with current tech stack versions
  4. Bundle size: Impact on build (for frontend)
  5. API quality: Clean, well-typed, good docs
  6. Migration path: Easy to adopt incrementally

Documentation Gathering

When collecting docs for a plan or implementation:

  • Find the official docs first (not blog posts or tutorials)
  • Link to specific sections, not just the homepage
  • Note the version the docs apply to
  • Capture gotchas and known issues from GitHub issues
  • Look for migration guides if upgrading

Research Output

Always structure research findings as:

## Research: {Topic}

### Key Findings
- {Finding 1 with source}
- {Finding 2 with source}

### Recommendation
{What to do and why}

### Risks / Gotchas
- {Risk 1}
- {Risk 2}

### Sources
- [Source 1](url) — {what we got from it}
- [Source 2](url) — {what we got from it}

As a Sub-Agent

When running as a sub-agent for research:

  • Be thorough in exploration but concise in reporting
  • Read broadly, summarize tightly
  • Include specific file paths, line numbers, and URLs
  • Flag anything uncertain or that needs human decision
  • Your summary is all the main agent will see — make it count

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.