From echo-sleuth
Extract durable knowledge from a past Claude Code conversation session.
How this command is triggered — by the user, by Claude, or both
Slash command
/echo-sleuth:extractThe summary Claude sees in its command listing — used to decide when to auto-load this command
Extract durable knowledge from a past Claude Code conversation session.
Arguments: $ARGUMENTS
**Step 1: Find the session**
If a session-id UUID is provided, locate it directly. Otherwise, list recent sessions:
bash "${CLAUDE_PLUGIN_ROOT}/scripts/list-sessions.sh" current --limit 7 --since "$(date -v-7d +%Y-%m-%d 2>/dev/null || date -d '7 days ago' +%Y-%m-%d)"
Present the list and ask the user which session to extract from (or default to the most recent).
**Step 2: Run extraction**
bash "${CLAUDE_PLUGIN_ROOT}/scripts/extract-knowledge.sh" SESSION_JSONL_PATH
This outputs a JSON array ...Extract durable knowledge from a past Claude Code conversation session.
Arguments: $ARGUMENTS
Step 1: Find the session
If a session-id UUID is provided, locate it directly. Otherwise, list recent sessions:
bash "${CLAUDE_PLUGIN_ROOT}/scripts/list-sessions.sh" current --limit 7 --since "$(date -v-7d +%Y-%m-%d 2>/dev/null || date -d '7 days ago' +%Y-%m-%d)"
Present the list and ask the user which session to extract from (or default to the most recent).
Step 2: Run extraction
bash "${CLAUDE_PLUGIN_ROOT}/scripts/extract-knowledge.sh" SESSION_JSONL_PATH
This outputs a JSON array of candidate extractable items, each with:
category: value | decision | correction | pattern | lesson | referencecontent: summary texttimestamp: when it occurredsuggested_destination: memory | claude_md | knowledge_file | skipsuggested_type: value | user | feedback | project | referenceStep 3: Present items to user
For each item, present:
Step 4: Write approved items
For each approved item, write to the chosen destination:
Memory file: Create ~/.claude/projects/<project>/memory/<name>.md with frontmatter:
---
name: <name>
description: <one-line summary>
type: <chosen type>
---
<content>
Then append an entry to MEMORY.md. If MEMORY.md doesn't exist, create it. If only a standalone MEMORY.md exists (no individual files), create the first individual file and convert MEMORY.md to an index.
CLAUDE.md: Append to the project's CLAUDE.md at the resolved project root. If project root is unresolvable, offer memory file as fallback.
Knowledge file: Write markdown to the chosen path.
Step 5: Summary
Report what was extracted and where it was saved.
npx claudepluginhub xiaolai/claude-plugin-marketplace --plugin echo-sleuth/extractExtracts design tokens, components, architecture, and PRDs from codebases or live products. Supports PDF page selection for large files.
/extractExtracts a complete design language from a URL — DTCG tokens, Tailwind config, Figma variables, motion, voice, and component patterns. Also supports grading, comparison, remixing, and packaging.
/extractExtracts functions, components, modules, hooks, or class methods from code into new units. Analyzes dependencies, replaces inline code with calls, updates imports, and verifies with tests.
/extractExtracts repeated Tailwind class combinations and markup into components, lifts magic values into design tokens, and updates all call sites.
/extractExtracts text from PDF files or directories to Markdown (or TXT) using a multi-backend system with CLI options like --backends and --format.