ワンクリックで
entity-episodic
Search prior session transcripts for specific events, conversations, and decisions
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Search prior session transcripts for specific events, conversations, and decisions
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Collaboratively refine a high-level ambition into a set of chunk prompts.
Migrate the project's ACTIVE chunks to the present-tense, intent-owning standard. Audits each chunk's goal against the code it claims to govern; rewrites retrospective framing inline; logs over-claims that need operator triage; historicalizes chunks with no enduring intent. Designed for full-corpus migrations — fans out across many parallel sub-agents at 5 chunks per agent.
Create a new chunk of work and refine its goal. Use when the operator wants to start new intent-bearing work, chunk something, define a piece of work, or break work into a chunk.
Update code references in the current chunk and move both the PLAN.md and the GOAL.md to the ACTIVE state.
Wake an entity by loading its identity, memories, and operational context
Set up a project steward via interactive interview
| name | entity-episodic |
| description | Search prior session transcripts for specific events, conversations, and decisions |
ve entity recall <name> <query> → distilled knowledge, lessons, skills, principles.
"What do I know about X?" These are insights extracted from prior sessions.
ve entity episodic --entity <name> --query "..." → raw session history, conversations,
decisions in context. "When did I encounter X? What did the operator say? What was the
outcome?" These are actual transcript snippets, not distilled.
Step 1 — Search
Run the search to get ranked snippets:
ve entity episodic --entity <name> --query "..."
If working in the vibe-engineer source repo, use uv run:
uv run ve entity episodic --entity <name> --query "..."
Scan the results to identify which hits look relevant. Each result includes a copy-pasteable expand command.
Step 2 — Expand
Run the expand command from the search output to read the surrounding conversation:
ve entity episodic --entity <name> --expand <session_id> --chunk <chunk_id> --radius 10
The hit region is marked with >>>, context lines with spaces. Read the expanded
output to understand:
Be selective — expand the top 1–2 results, not all of them. Each expansion costs context window space.
# "I think we had a similar merge conflict issue before"
ve entity episodic --entity steward --query "merge conflict orchestrator"
# "What did the operator say about how to handle chunk creation?"
ve entity episodic --entity steward --query "chunk creation SOP correction"
# "I'm seeing a WebSocket timeout — have we debugged this before?"
ve entity episodic --entity steward --query "websocket timeout reconnect"
ve entity claude (which archives
transcripts). Older sessions may not be indexed.