メニュー
This skill should be used when researching best practices, evaluating technologies, comparing approaches, or when research, evaluation, or comparison are mentioned.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/outfitter-dev/outfitter --skill researchコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
SKILL.md を表示中
SOC 職業分類に基づく
| name | research |
| description | This skill should be used when researching best practices, evaluating technologies, comparing approaches, or when research, evaluation, or comparison are mentioned. |
| metadata | {"version":"2.1.1","related-skills":["report-findings","codebase-analysis"]} |
Systematic investigation → evidence-based analysis → authoritative recommendations.
report-findings skill for synthesis<when_to_use>
NOT for: quick lookups, well-known patterns, time-critical debugging without investigation stage
</when_to_use>
Load the maintain-tasks skill for stage tracking. Stages advance only, never regress.
| Stage | Trigger | activeForm |
|---|---|---|
| Analyze Request | Session start | "Analyzing research request" |
| Discover Sources | Criteria defined | "Discovering sources" |
| Gather Information | Sources identified | "Gathering information" |
| Synthesize Findings | Information gathered | "Synthesizing findings" |
| Compile Report | Synthesis complete | "Compiling report" |
Workflow:
in_progresscompleted, add next in_progressFive-stage systematic approach:
1. Question Stage — Define scope
2. Discovery Stage — Multi-source retrieval
| Use Case | Primary | Secondary | Tertiary |
|---|---|---|---|
| Official docs | context7 | octocode | firecrawl |
| Troubleshooting | octocode issues | firecrawl community | context7 guides |
| Code examples | octocode repos | firecrawl tutorials | context7 examples |
| Technology eval | Parallel all | Cross-reference | Validate |
3. Evaluation Stage — Analyze against criteria
| Criterion | Metrics |
|---|---|
| Performance | Benchmarks, latency, throughput, memory |
| Maintainability | Code complexity, docs quality, community activity |
| Security | CVEs, audits, compliance |
| Adoption | Downloads, production usage, industry patterns |
4. Comparison Stage — Systematic tradeoff analysis
For each option: Strengths → Weaknesses → Best fit → Deal breakers
5. Recommendation Stage — Clear guidance with rationale
Primary recommendation → Alternatives → Implementation steps → Limitations
Three MCP servers for multi-source research:
| Tool | Best For | Key Functions |
|---|---|---|
| context7 | Official docs, API refs | resolve-library-id, get-library-docs |
| octocode | Code examples, issues | packageSearch, githubSearchCode, githubSearchIssues |
| firecrawl | Tutorials, benchmarks | search, scrape, map |
Execution patterns:
See tool-selection.md for detailed usage.
<discovery_patterns>
Common research workflows:
| Scenario | Approach |
|---|---|
| Library Installation | Package search → Official docs → Installation guide |
| Error Resolution | Parse error → Search issues → Official troubleshooting → Community solutions |
| API Exploration | Documentation ID → API reference → Real usage examples |
| Technology Comparison | Parallel all sources → Cross-reference → Build matrix → Recommend |
See discovery-patterns.md for detailed workflows.
</discovery_patterns>
<findings_format>
Two output modes:
Evaluation Mode (recommendations):
Finding: { assertion }
Source: { authoritative source with link }
Confidence: High/Medium/Low — { rationale }
Discovery Mode (gathering):
Found: { what was discovered }
Source: { where from with link }
Notes: { context or caveats }
</findings_format>
<response_structure>
## Research Summary
Brief overview — what investigated, sources consulted.
## Options Discovered
1. **Option A** — description
2. **Option B** — description
## Comparison Matrix
| Criterion | Option A | Option B |
| --------- | -------- | -------- |
## Recommendation
### Primary: [Option Name]
**Rationale**: reasoning + evidence
**Confidence**: level + explanation
### Alternatives
When to choose differently.
## Implementation Guidance
Next steps, common pitfalls, validation.
## Sources
- Official, benchmarks, case studies, community
</response_structure>
Always include:
Always validate:
Proactively flag:
ALWAYS:
in_progress at a timeNEVER:
Research vs Report-Findings:
research) covers the full investigation workflow using MCP toolsreport-findings skill covers synthesis, source assessment, and presentationUse research for technology evaluation, documentation discovery, and best practices research. Load report-findings during synthesis stage for source authority assessment and confidence calibration.
Patterns for @outfitter/daemon including lifecycle management, IPC communication, health checks, and PID files. Use when building background services, daemons, or when "daemon", "IPC", "health check", "background service", or "@outfitter/daemon" are mentioned.
Creates handlers, CLI commands, MCP tools, and daemon services following Outfitter Dev Kit conventions. Use when adding new components to a project, scaffolding code, or when "create handler", "new command", "add tool", or "daemon service" are mentioned.
Deep patterns for @outfitter/mcp including tool registration, Zod schemas, resources, and server configuration. Use when building MCP servers, registering tools, defining resources, or when "MCP server", "MCP tool", "registerTool", or "@outfitter/mcp" are mentioned.