Pre-action boundary checking — validates agent tool calls against declared capabilities and task contracts
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Memory persistence operations using claude-mem
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
설치 방법 보기설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.
Provide memory persistence operations using claude-mem for session context survival across compactions.
operation: save
description: Store session context in claude-mem
steps:
1. Collect session data:
- Tasks completed
- Decisions made
- Open items
- Key code changes
2. Format document:
- Add project tag: "my-project"
- Add session ID: {date}-{uuid}
- Add relevant tags
3. Store in claude-mem:
- Use chroma_add_documents
- Include metadata
operation: recall
description: Search and retrieve relevant memories
steps:
1. Build query:
- Always prefix with "my-project"
- Add user-provided search terms
- Include date for temporal searches
2. Search claude-mem:
- Use chroma_query_documents
- Request top N results
3. Format results:
- Sort by relevance
- Present summary
- Provide access to full content
operation: get
description: Retrieve specific memory by ID
steps:
1. Use chroma_get_documents with ID
2. Return full document content
# Always include project name
chroma_query_documents(["my-project {search_terms}"])
# Examples:
chroma_query_documents(["my-project authentication flow"])
chroma_query_documents(["my-project 2025-01-24 memory system"])
# When you have a specific document ID
chroma_get_documents(ids=["document_id"])
content: |
## Session Summary
Date: {date}
Session: {session_id}
### Tasks Completed
- Task 1: Description
- Task 2: Description
### Decisions Made
- Decision 1: Rationale
- Decision 2: Rationale
### Open Items
- Item 1: Status
- Item 2: Status
### Notes
Additional context...
metadata:
project: my-project
session: {date}-{uuid}
tags: [session, task, decision, ...]
created_at: {timestamp}
results:
- id: doc_1
score: 0.95
summary: "Authentication flow implementation"
date: 2025-01-20
tags: [authentication, oauth]
- id: doc_2
score: 0.87
summary: "JWT token decision"
date: 2025-01-18
tags: [authentication, decision]
do:
- Always include "my-project" prefix
- Use semantic, intent-based queries
- Include dates for temporal searches
- Use multiple queries for better coverage
dont:
- Use complex where filters ($and, $or)
- Omit project name
- Use overly generic terms
- Expect exact string matching
do:
- Include meaningful tags
- Write clear summaries
- Capture decisions with rationale
- Note open items for future reference
dont:
- Save trivial conversations
- Include sensitive data (API keys, etc.)
- Create duplicate entries
sys-memory-keeper agent uses this skill for:
- sys-memory-keeper:save command
- sys-memory-keeper:recall command
- PreCompact hook
- SessionStart hook
Other agents can trigger memory operations via:
- Direct sys-memory-keeper:save/recall commands
- Delegating to sys-memory-keeper
save_errors:
- Connection failure: Retry 3 times, then log and continue
- Invalid format: Validate before save, report issues
- Storage full: Archive old memories, then retry
recall_errors:
- No results: Suggest alternative queries
- Connection failure: Return empty with warning
- Invalid query: Help user reformulate
아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.
로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.
아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.
Pre-action boundary checking — validates agent tool calls against declared capabilities and task contracts
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Auto-detect project context and optimize harness — deactivate unused agents/skills, suggest missing experts, generate project profile
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Adversarial code review using attacker mindset — trust boundary, attack surface, business logic, and defense evaluation
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Apache Airflow best practices for DAG authoring, testing, and production deployment
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Alembic migration patterns for naming conventions, safety checks, expand-contract, env.py configuration, and CI integration
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Pre-routing ambiguity analysis — scores request clarity and asks clarifying questions when needed (inspired by ouroboros)
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.