Deep Recall — Development skill for Claude Code
Deep semantic search over the ENTIRE vault (2k+ notes incl.
How to install Deep Recall
Installs to ~/.claude/skills/leo-atienza-atlas-claude-deep-recall/SKILL.md
mkdir -p ~/.claude/skills/leo-atienza-atlas-claude-deep-recall && curl -fsSL https://raw.githubusercontent.com/Leo-Atienza/atlas-claude/HEAD/commands/deep-recall.md -o ~/.claude/skills/leo-atienza-atlas-claude-deep-recall/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Deep Recall does
description: "Deep semantic search over the ENTIRE vault (2k+ notes incl. session-log, handoffs, transcripts, graph) via the local TurboQuant index — the tier /recall deliberately skips. Use when /recall comes up thin or the answer likely lives in past session history." argument-hint: ""
/deep-recall — full-corpus semantic search (TurboQuant, offline)
!`python ~/.claude/scripts/semantic/recall_semantic.py search "$ARGUMENTS" -k 8`
The block above is pure **semanti
Alternatives in Development
- Resume Work From A Handoff Document — You are tasked with resuming work from a handoff document through an interactive process 10k ★
- Translate Book — Claude Code skill that translates entire books (PDF/DOCX/EPUB) into any language using parallel subagents 542 ★
- Clear Cache — Clear validation cache for a plugin or entire system (project) 209 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Session Recall
Search and analyze Claude Code session transcripts to recover context after compaction
V Memory Refresh
(Re)index docs/superpowers prose into the local V-memory cache so recall is current. Incremental by file hash;
V Remember
Recall relevant past Compound V context — prior decisions, failures, routing lessons, specs/plans — from docs/
Compass Recall
/compass-recall — Semantic Recall on Project Memory
Agent Memory Kits
Persistent local-first semantic memory for any agent: (Hermes, claude code, codex, etc..) : plugin (auto-recal
PM Recall
Semantic search across all memories (global + every project)
Related Agents
Recall
Runs the recall CLI over the user's past Claude Code sessions and returns the one actionable item — a command,
Engine Grounding Scout
Use when you are about to run the memory-recall sweep or a knowledge-graph impact traversal and the sweep will
Teamai Recall
Search the team knowledge base (skills + learnings + docs + rules + codebase graph) and return a compact, stru