SuperAPI AI Directory

compound

General & other

View repository

Updated 10-16 05:05

About this skill

compound skill

Purpose: Immediately document insights validated during guild operations to build a searchable knowledge base that grows team knowledge compoundingly.

Overview

This skill captures insights the moment they are confirmed and stores them as structured documents based on YAML frontmatter. It uses a single-file-per-category architecture, and each insight is knowledge/solutions/[category]/[filename].mdis saved to.


<critical_sequence name="insight-capture" enforce_order="strict">

7-step process

Auto-detection phrases (recognized in conversation):

  • "This worked well"
  • "I like this approach"
  • "Let's do it this way next time too"
  • "Let's record this"
  • "This format worked"
  • "The customer liked it"
  • "This framework worked"
  • "This was effective"
  • "It worked when I did it this way"

OR manual: /compound command

Non-trivial only (insights worth reusing):

  • Patterns the team can repeat
  • Lessons applicable to other situations
  • Methods discovered through trial and error
  • Approaches validated by partners/customers
  • Discoveries that brought structural improvements to organizational operations

Skip criteria:

  • One-off methods that only work in this situation
  • Simple factual records (numbers, dates, etc.)
  • Repetition of already documented content
  • Hypotheses not yet validated

Extract from conversation history:

Required information:

  • domain: guild / contents / community / business / knowledge
  • insight_type: Insight type (see schema.yaml enum)
  • component: Sub-component within the domain (see schema.yaml enum)
  • context: In what situation did this insight arise (1-3 sentences)
  • key_learning: One-sentence core lesson (generalizable to other situations)
  • impact: critical / high / medium / low
  • tags: Search keywords (lowercase, hyphen-separated)

Additional items to collect:

  • Background: What project/activity was in progress
  • Things tried: Approaches that had no effect
  • What worked: The method that actually worked
  • Why it worked: Why it was effective
  • Reproduction conditions: When this method can be used

BLOCKING requirements: If domain, insight_type, or core insight is unclear, ask the user and wait for a response:

문서화를 위해 몇 가지 확인이 필요합니다:

1. 어떤 도메인인가요? (guild/contents/community/business/knowledge)
2. 인사이트 유형은? (예: content_pattern, consulting_pattern, process_improvement...)
3. 핵심 교훈을 한 문장으로 정리하면?

[응답 후 계속 진행]

knowledge/solutions/ Search for similar insights in:

# domain, tags, insight_type 기준으로 병렬 검색
Grep: pattern="domain: [domain]" path=knowledge/solutions/ output_mode=files_with_matches
Grep: pattern="tags:.*[keyword]" path=knowledge/solutions/ output_mode=files_with_matches -i=true
Grep: pattern="insight_type: [type]" path=knowledge/solutions/ output_mode=files_with_matches

When a similar document is found Present options to the user and wait:

유사 문서 발견: knowledge/solutions/[path]

어떻게 할까요?
1. 새 문서 생성 + 교차 참조 추가 (권장)
2. 기존 문서 업데이트 (동일한 인사이트의 보완인 경우)
3. 기타

선택 (1-3): _

After waiting for the user's response, execute the selected action.

If no similar document exists Proceed directly to Step 4.

Format: YYYYMMDD-[sanitized-insight-slug].md

Sanitization rules:

  • lowercase
  • spaces → hyphens
  • remove special characters (except hyphens)
  • truncate to under 80 characters

Example:

  • 20260224-linkedin-hook-pattern.md
  • 20260224-workshop-icebreaker-framework.md
  • 20260224-weekly-sync-standup-format.md
  • 20260224-upstage-consulting-onboarding.md
  • 20260224-meetup-networking-structure.md

Validate all required fields based on schema.yaml.

<validation_gate name="yaml-schema" blocking="true">

Validation items:

  • domain: one of the enum values in schema.yaml
  • date: YYYY-MM-DD format
  • insight_type: one of the enum values in schema.yaml
  • component: one of the enum values mapped to the corresponding domain (checkdomain_component_mapping )
  • context: 20-300 characters, describing a specific situation
  • key_learning: 10-200 characters, a generalizable lesson
  • impact: critical / high / medium / low
  • tags: 1-8 items, lowercase hyphen-separated

Block Step 6 if validation fails:

YAML 검증 실패

오류:
- domain: 허용된 값이 아님: "marketing" → guild, contents, community, business, knowledge 중 하나
- component: domain 'guild'에는 허용되지 않는 컴포넌트: "linkedin" → operations, culture, hiring, sync, decision-making, season-planning 중 하나
- tags: 대문자 포함 → 소문자로 변환 필요

수정된 값을 제공해주세요.

Enforce GATE: Do not proceed to Step 6 until all validations pass.

</validation_gate>

Determine category directory: schema.yaml의 category_mappingmap insight_type → storage path.

Document generation:

INSIGHT_TYPE="[검증된 YAML에서]"
CATEGORY_DIR="[category_mapping에서 매핑]"
FILENAME="[Step 4에서 생성]"
DOC_PATH="${CATEGORY_DIR}${FILENAME}"

# 디렉토리 없으면 생성
mkdir -p "${CATEGORY_DIR}"

# assets/resolution-template.md 기반으로 문서 작성
# (Step 2에서 수집한 컨텍스트 + Step 5에서 검증한 YAML frontmatter)

Result:

  • Create a single file in the category directory
  • Ensure consistent classification through Enum validation

If a similar document was found in Step 3:

# 기존 문서에 Related 섹션 추가
# 새 문서에도 기존 문서 링크 추가

Detect pattern candidates:

If 3 or more similar insights exist in the same category:

패턴 문서 후보 감지: [카테고리]에 유사 인사이트 X개
→ patterns/ 문서로 종합하시겠습니까?

Critical Pattern promotion conditions (automatic promotion prohibited, user decision):

  • impact가 criticalif
  • When it can be applied across multiple domains
  • When the entire team must know it

In this case, in the Decision Menu, add a comment to the "2. Add to critical patterns" option:

💡 이 인사이트는 크리티컬 패턴 승격을 고려해볼 만합니다

</critical_sequence>


<decision_gate name="post-documentation" wait_for_user="true">

Decision Menu After Capture

After successful documentation, present options and wait for user response:

인사이트가 기록되었습니다.

파일 생성:
- knowledge/solutions/[category]/[filename].md

다음 작업:
1. 계속 진행 (권장)
2. 크리티컬 패턴에 추가 - critical-patterns.md에 승격
3. 관련 문서 연결 - 유사 인사이트와 교차 참조
4. 기존 스킬에 추가 - .claude/skills/에 연결
5. 문서 확인 - 생성된 내용 보기

선택: _

Handling each option:

Option 1: Continue

  • Return to the current task/workflow
  • Documentation complete

Option 2: Add to critical patterns

If the user selects it:

  • Patterns that are repeatedly applied to the entire team
  • Lessons that must never be forgotten
  • Rules that are counterintuitive but essential

Action:

  1. Extract the pattern from the document
  2. Structure it in the format of assets/critical-pattern-template.md
  3. knowledge/solutions/patterns/critical-patterns.md(maintain the sequence number)
  4. Add a cross-reference to the document
  5. Confirmation: "Added to critical patterns. From now on, learnings-researcher will always check this pattern."

Option 3: Link related documents

  • Prompt: "Which document would you like to link? (filename or topic description)"
  • knowledge/solutions/Search for the target document in
  • Add a bidirectional cross-reference
  • Confirmation: "Cross-reference added"

Option 4: Add to an existing skill

  • Prompt: "Which skill would you like to add it to?"
  • .claude/skills/[skill-name]/Add a link and description to the appropriate file in
  • Confirmation: "Added to the [skill-name] skill"

Option 5: Review the document

  • Display the generated document content
  • Present the Decision Menu again

</decision_gate>


<integration_protocol>

Integration points

Invocation triggers:

  • /compound command (main interface)
  • Automatically detect confirmation phrases during conversation
  • Manual invocation after workflow completion

Skills/agents to invoke:

  • None (terminal skill - does not delegate to other skills)

Handoff conditions: There must be sufficient context in the conversation history before invocation.

</integration_protocol>


<success_criteria>

Success criteria

Documentation succeeds when all of the following conditions are met:

  • YAML frontmatter validation passes (all required fields, correct format, valid enum values)
  • knowledge/solutions/[category]/[filename].mdfile created in
  • domain-component mapping matches schema.yaml
  • Context, What Worked, Why This Works sections written concretely
  • Cross-references added when similar documents are found
  • Decision Menu presented to user and action confirmed

</success_criteria>


Error handling

Insufficient context:

  • Ask the user for the missing information
  • Do not proceed until the required information is obtained

YAML validation failure:

  • Show the specific error items
  • Retry with corrected values
  • Block until it passes

Similar insight ambiguity:

  • Show all candidates
  • User choice: new document / update existing / link separately

Category mapping uncertain:

  • Propose the closest category
  • Proceed after user confirmation

Execution guidelines

Must do:

  • YAML frontmatter validation (Step 5 validation gate is blocking)
  • Verify domain-component mapping validity
  • Before writing the file, mkdir -pcreate directory with
  • If context is missing, ask the user and wait
  • Generalize key_learning so it can apply to other situations

Must never do:

  • Skip YAML validation (validation gate is blocking)
  • Document with vague descriptions (unsearchable)
  • Document hypotheses or unverified content
  • Automatically promote critical patterns (user decision required)

Example scenario

User: "At the Upstage workshop, when I did 'sharing AI usage experiences' first as an icebreaker, participation went way up. Let's do it this way next time too."

Skill activation:

  1. Trigger detection: "Let's do it this way next time too" → auto-activation
  2. Context collection:
    • domain: business
    • insight_type: consulting_pattern
    • component: consulting
    • context: "When an 'AI usage experience sharing' session was conducted as an icebreaker before the hands-on technical practice at the Upstage AI workshop, participation and atmosphere improved significantly"
    • key_learning: "In B2B workshops, a personal experience sharing icebreaker before hands-on practice increases participants' psychological safety and participation"
    • impact: high
    • tags: [workshop, icebreaker, consulting, engagement, upstage]
  3. Existing document search: search knowledge/solutions/consulting-patterns/
  4. Filename generation: 20260224-workshop-icebreaker-experience-sharing.md
  5. YAML validation: ✅ passed
  6. Document writing: knowledge/solutions/consulting-patterns/20260224-workshop-icebreaker-experience-sharing.md
  7. Cross-references: None (no similar documents)

Output:

인사이트가 기록되었습니다.

파일 생성:
- knowledge/solutions/consulting-patterns/20260224-workshop-icebreaker-experience-sharing.md

다음 작업:
1. 계속 진행 (권장)
2. 크리티컬 패턴에 추가 - critical-patterns.md에 승격
3. 관련 문서 연결 - 유사 인사이트와 교차 참조
4. 기존 스킬에 추가 - .claude/skills/에 연결
5. 문서 확인 - 생성된 내용 보기