Catalog
yeachan-heo/research

yeachan-heo

research

Investigate an open question and return grounded, sourced findings

v1.0LATEST
New~340Updated Aug 31, 2026

Research

Use this skill when the next step depends on something not yet known. Research answers questions; it does not implement.

This is the canonical research lane. deep-dive, sciomc, and autoresearch route here.

Goal

Replace assumptions with evidence, and say plainly what remains uncertain.

Workflow

  1. State the question precisely enough to know when it is answered.
  2. Search the repo and its docs first — local evidence outranks recollection.
  3. For external SDKs, frameworks, or APIs, consult official documentation.
  4. Sweep more than one way when the answer could hide: by file, by symbol, by caller, by history.
  5. Synthesize into findings, each tied to where it came from.

Scale

  • Narrow lookup — answer it directly.
  • Multiple independent questions — investigate in parallel.
  • Unknown-size discovery — keep going until additional passes surface nothing new.

Rules

  • Cite the source: file and line, or the document consulted.
  • Distinguish what was verified from what was inferred.
  • Report contradicting evidence rather than picking the tidier story.
  • Do not implement as a side effect of researching.

Output

  • The question
  • Findings, each with its source
  • What remains unknown or unverifiable
  • Recommended next step, if one follows
Files1
1 files · 1.0 KB

Select a file to preview

Overall Score

81/100

Grade

B

Good

Safety

92

Quality

78

Clarity

85

Completeness

72

Summary

This skill guides AI agents to systematically investigate open questions by searching local repositories first, then consulting external documentation, and finally synthesizing grounded findings with explicit source citations. It emphasizes evidence-based reasoning over assumptions and operates in a read-only, investigative mode without implementation side effects.

Detected Capabilities

file readingrepository searchdocumentation readingcode analysisinformation synthesis

Trigger Keywords

Phrases that MCP clients use to match this skill to user intent.

verify assumptionresearch codebaseexplore unknown questioninvestigate api behavioraudit existing patternsunderstand framework design

Use Cases

  • Verify architectural assumptions before development
  • Understand existing codebase patterns and conventions
  • Research third-party API or framework behavior
  • Determine why a system behaves unexpectedly
  • Gather evidence for design decisions or refactoring proposals

Quality Notes

  • Clear, concise workflow with logical 5-step progression
  • Excellent scope boundaries — explicitly prohibits implementation as side effect
  • Strong emphasis on source citation and verification vs. inference
  • Well-structured rules section that emphasizes intellectual rigor
  • Output format is clearly specified with actionable components
  • Minimal but practical — the skill teaches methodology rather than specific tool usage
  • Recognizes three scale patterns (narrow, parallel, discovery) for different research scenarios
  • One minor gap: lacks explicit guidance on when to stop searching or how to evaluate source credibility
Model: claude-haiku-4-5-20251001Analyzed: Aug 31, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

Use yeachan-heo/research in your dev environment

Command Palette

Search for a command to run...