AgentSkillsCN

research-and-incorporate

研究外部主题，开展全面分析，评估项目的适用性，并将学习成果融入 Brain 记忆系统。将知识转化为可搜索、可付诸行动的项目背景信息。

SKILL.md
--- frontmatter
name: research-and-incorporate
version: 1.0.0
description: Research external topics, create comprehensive analysis, determine project
  applicability, and incorporate learnings into Brain memory system. Transforms
  knowledge into searchable, actionable project context.
license: MIT
model: claude-opus-4-5
agents:
  - analyst
metadata:
  timelessness: 8/10
  source: Chesterton's Fence research workflow (Session 203)

Research and Incorporate

Transform external knowledge into actionable, searchable project context through structured research, analysis, and memory integration.

Quick Start

text
/research-and-incorporate

Topic: Chesterton's Fence
Context: Decision-making principle for understanding existing systems before changing them
URLs: https://fs.blog/chestertons-fence/, https://en.wikipedia.org/wiki/G._K._Chesterton
InputOutputDuration
Topic + Context + URLsAnalysis doc + Brain notes (5-10 atomic notes)20-40 min

Triggers

  • •/research-and-incorporate - Main invocation
  • •"research and incorporate {topic}" - Natural language
  • •"study {topic} and add to memory" - Alternative phrasing
  • •"deep dive on {topic}" - Research focus
  • •"learn about {topic} for the project" - Project integration focus

Parameters

ParameterRequiredDescription
TOPICYesSubject to research (e.g., "Chesterton's Fence")
CONTEXTYesWhy this matters to the project
URLSNoComma-separated source URLs

Workflow Overview

text
┌─────────────────────────────────────────────────────────────────┐
│ Phase 1: RESEARCH (BLOCKING)                                    │
│ • Check existing knowledge (Brain)                              │
│ • Fetch URLs with quote extraction                              │
│ • Web search for additional context                             │
│ • Synthesize: principles, frameworks, examples, failure modes   │
├─────────────────────────────────────────────────────────────────┤
│ Phase 2: ANALYSIS DOCUMENT (BLOCKING)                           │
│ • Write 3000-5000 word analysis to .agents/analysis/            │
│ • Include: concepts, frameworks, applications, failure modes    │
│ • Verify: 3+ examples, 3+ failure modes, 2+ relationships       │
├─────────────────────────────────────────────────────────────────┤
│ Phase 3: APPLICABILITY (BLOCKING)                               │
│ • Map integration points: agents, protocols, memory, skills     │
│ • Propose applications with effort estimates                    │
│ • Prioritize: High/Medium/Low based on project goals            │
├─────────────────────────────────────────────────────────────────┤
│ Phase 4: MEMORY INTEGRATION (BLOCKING)                          │
│ • Create Brain project note with cross-references               │
│ • Create 5-10 atomic Brain notes with observations/relations    │
│ • Link notes to related concepts via relations                  │
├─────────────────────────────────────────────────────────────────┤
│ Phase 5: ACTION ITEMS                                           │
│ • Create GitHub issue if implementation work identified         │
│ • Document in session log                                       │
└─────────────────────────────────────────────────────────────────┘

Quality Gates (BLOCKING)

GateRequirementPhase
Research depthCore principles + frameworks + 3 examples1
Analysis length3000-5000 words minimum2
Concrete examples3+ with context and outcomes2
Failure modes3+ anti-patterns with corrections2
Relationships2+ connections to existing concepts2
Note atomicityEach note covers ONE concept4
Note count5-10 Brain notes created4

Verification Checklist

After completion, verify:

  • • Analysis document exists at .agents/analysis/{topic-slug}.md
  • • Analysis is 3000-5000 words with concrete examples
  • • Applicability section documents integration opportunities
  • • Brain project note created with cross-references
  • • 5-10 Brain notes created with observations/relations
  • • Notes linked to related concepts via relations
  • • Each note is atomic (one concept)
  • • Action items documented (issue or next steps)

Anti-Patterns

AvoidWhyInstead
Superficial researchSurface definitions miss actionable insightsDig into frameworks, examples, failure modes
Missing applicabilityResearch without integration is wastedEvery insight must show HOW it applies
Non-atomic notesMultiple concepts pollutes graphONE concept per note
Disconnected knowledgeOrphaned artifacts aren't discoverableLink notes via relations
Template over-complianceForcing irrelevant sections wastes tokensOrganize for the topic, not the template
Skipping verificationQuality gates exist for a reasonVerify each phase before proceeding

Related Skills

SkillRelationship
brain:writing-notesNote creation best practices
brain:research-agentDeep research with progressive note building
exploring-knowledge-graphNavigate created knowledge

References

DocumentContent
workflow.mdDetailed phase workflows with templates
memory-templates.mdBrain note structure templates

Extension Points

  1. •Additional research sources: Add MCP tools for specialized domains
  2. •Custom analysis templates: Topic-specific document structures
  3. •Automated validation: Scripts to verify memory atomicity
  4. •Integration hooks: Connect to ADR review for architecture topics