원클릭으로
memory
Two-layer memory system with Reflection-managed knowledge files.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Two-layer memory system with Reflection-managed knowledge files.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Search and install agent skills from ClawHub, the public skill registry.
Schedule reminders and recurring tasks.
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.
| name | memory |
| description | Two-layer memory system with Reflection-managed knowledge files. |
| always | true |
SOUL.md — Bot personality and communication style. Managed by Reflection. Avoid editing unless the task is explicitly about identity/persona.USER.md — User profile and preferences. Managed by Reflection and inline learning.memory/MEMORY.md — Long-term facts (project context, important events). Managed by Reflection and inline learning.memory/BUGS.md — Confirmed bugs, limitations, and durable workarounds. Updated only via inline learning (not touched by Reflection).memory/history.jsonl — append-only JSONL, not loaded into context. Prefer the built-in grep tool to search it.memory/history.jsonl is JSONL format — each line is a JSON object with cursor, timestamp, content.
grep(..., path="memory", glob="*.jsonl", output_mode="count") or the default files_with_matches mode before expanding to full contentoutput_mode="content" plus context_before / context_after when you need the exact matching linesfixed_strings=true for literal timestamps or JSON fragmentshead_limit / offset to page through long historiesexec only as a last-resort fallback when the built-in search cannot express what you needExamples (replace keyword):
grep(pattern="keyword", path="memory/history.jsonl", case_insensitive=true)grep(pattern="2026-04-02 10:00", path="memory/history.jsonl", fixed_strings=true)grep(pattern="keyword", path="memory", glob="*.jsonl", output_mode="count", case_insensitive=true)grep(pattern="oauth|token", path="memory", glob="*.jsonl", output_mode="content", case_insensitive=true)memory/history.jsonl directly./reflection-log command.