Research

Skill jhlee0409/all-for-claudecode/skills/research

Technical research — investigate technologies, compare libraries, explore optionsFrom its SKILL.md

Install

npx -y skills add jhlee0409/all-for-claudecode --skill research

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

7 stars7 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

3.4 KB, as published. Nobody here has run it

/afc:research — Technical Research

Investigates technical questions and summarizes conclusions. Results are persisted to .claude/afc/memory/research/{topic}.md.

Arguments

$ARGUMENTS — (required) research topic (e.g., "Zustand v5 migration", "WebCodecs API comparison")

Execution Steps

1. Analyze Topic

Extract from $ARGUMENTS:

Core question: What do we need to know?
Context: Why is it needed? (relevance to the current project)
Scope: Depth vs breadth (specific library comparison? general technology trends?)

2. Check Existing Research

Check .claude/afc/memory/research/ directory for related prior research:

If found: load existing content and decide whether an update is needed
If not found: proceed with new research

3. Gather Information

Use Agent Teams — run independent investigations in parallel:

Task("WebSearch: {topic} official docs", subagent_type: "general-purpose")
Task("Codebase: analyze current usage patterns", subagent_type: "general-purpose")

Source priority:

Official documentation (WebSearch/WebFetch)
Codebase (existing patterns in the current project)
Community (GitHub Issues, blogs)

3.5. Reconcile Findings

After parallel agents return, the orchestrator checks for conflicts between sources:

Compare codebase agent findings (current usage patterns) against web agent findings (official docs, latest versions)
If a codebase pattern conflicts with official documentation (e.g., deprecated API, changed behavior in newer version):
- Flag the conflict explicitly in Findings rather than silently adopting one source
- Note: "Current codebase uses {pattern} but official docs recommend {alternative} since {version/date}"
If no conflicts → proceed to Summarize

4. Summarize Conclusions

# Research: {topic}

> Date: {YYYY-MM-DD}
> Related feature: {related feature or "general"}

## Core Question
{what we needed to know}

## Findings

### {subtopic 1}
{content}
**Source**: {URL} (verified {date})

### {subtopic 2}
{content}

## Option Comparison (if applicable)
| Criterion | {OptionA} | {OptionB} | {OptionC} |
|-----------|-----------|-----------|-----------|
| {criterion1} | {evaluation} | {evaluation} | {evaluation} |
| {criterion2} | {evaluation} | {evaluation} | {evaluation} |

## Conclusion
**Recommendation**: {choice or conclusion}
**Rationale**: {key reason}
**Caveats**: {pitfalls or constraints}

## Project Application
{how this can be applied in the current project}

5. Save

Save to .claude/afc/memory/research/{topic-kebab-case}.md
If the file already exists, update it (refresh the date)

6. Final Output

Research complete
├─ Topic: {topic}
├─ Saved: .claude/afc/memory/research/{filename}.md
├─ Conclusion: {one-line summary}
└─ Sources: {number of key sources}

Notes

Current date basis: Use WebSearch to verify up-to-date information rather than relying on knowledge cutoff.
Sources required: Cite sources for all technical claims.
Project context: Derive conclusions applicable to this project, not generic research.
Persistent storage: Save to .claude/afc/memory/research/ for reuse across sessions.