菜单
Monthly snapshot — activity level, top conversations, sample questions. Use when user wants to reconstruct a specific month's mental state.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Evaluate a decision against the user's stated principles + related past thinking. Loads principles from YAML, matches by keyword, surfaces semantically similar prior decisions.
Raw accounting of what's in the brain. Counts messages, embeddings, summaries, domains. Use when user asks "how much is in my brain" or "what's the size of the corpus."
Surface patterns in how the user thinks — cognitive pattern, problem-solving approach, emotional tone, content category. Optional domain scope. Use when user asks "when do I think best" or "what patterns show up in breakthroughs."
Full re-entry brief for a domain — recent summaries + accumulated open questions, decisions, insights, quotes. Longer and deeper than tunnel-state. Use after days/weeks away from a project.
Browse conversations by calendar date. Use when user asks "what was I working on last Thursday" or specifies a date.
Surface abandoned domains with unresolved breakthrough/significant open questions. Ranked by breakthrough count → question count → conversation count. Use when user feels important threads have been dropped.
| name | what-was-i-thinking |
| description | Monthly snapshot — activity level, top conversations, sample questions. Use when user wants to reconstruct a specific month's mental state. |
| layer | L2 |
| reads | ["L0.all_conversations"] |
| writes | [] |
| citations | required |
| determinism | pure-function |
| allowed-tools | mcp__my-brain__what_was_i_thinking |
L2 skill bounded to a single YYYY-MM window. Computes monthly averages, classifies activity as HIGH (>1.5× monthly avg) / NORMAL / LOW (<0.5×). Unlike tunnel-state, this is a temporal window not a topical window.
month: str # YYYY-MM format, strict
## 📅 What you were thinking: {month}
**Activity level**: 🔥 HIGH / 📊 NORMAL / 📉 LOW (N msgs vs avg M)
**Conversations**: N · **User messages**: M · **Questions asked**: K
### Top conversations (by message count)
1. **{title}** ({msg_count} messages) [conv_id · date]
...
### Sample questions that month
- "{q truncated 150ch}" [conv_id · date]
...