agi-is-going-to-arrive/memory-palace-openclaw/gemini

Claude Code and agent skill by agi-is-going-to-arrive/memory-palace-openclaw

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Use this skill whenever the user asks about Memory Palace durable memory, recall across sessions, saving notes for later, memory deduplication, guard_action or guard_target_uri handling, search_memory, compact_context, rebuild_index, index_status, or read_memory("system://boot"). Also use it whenever the user asks about this repository's memory-palace skill itself: its first memory tool call, NOOP behavior, trigger sample path, workflow rules, or how to use it in Gemini CLI. Do not answer these requests from generic intuition; load this skill first and use its repository-local facts.

Install

npx vskill@latest install agi-is-going-to-arrive/memory-palace-openclaw/gemini

SKILL.md

Memory Palace

Use this skill for Memory Palace memory operations and for questions about this skill itself.

Repository-local anchors

  • First memory tool call: read_memory("system://boot")
  • If guard_action is NOOP: stop the write, inspect guard_target_uri / guard_target_id, read the suggested target, then decide whether to update or leave unchanged
  • Trigger sample set path: docs/skills/memory-palace/references/trigger-samples.md

Required workflow

  • Read docs/skills/memory-palace/references/mcp-workflow.md before choosing tools when the user is asking about workflow or tool behavior.
  • If the URI is unknown, use search_memory(..., include_session=true) before read_memory.
  • Use include_expired=true only when the user explicitly asks for historical, future-validity, or superseded memories.
  • Read before every mutation: create_memory, update_memory, delete_memory, add_alias.
  • Use index_status() before rebuild_index(wait=true) unless the user explicitly wants immediate rebuild.
  • Use compact_context(force=false) for long or noisy sessions that should be distilled.
  • Treat guard_action=IGNORE as “not worth storing”; do not force-write unless the user explicitly re-confirms.
  • Do not invent provenance, temporal fields, or memory links, and do not expose raw compact-context metadata such as session_id, source_hash, gist_method, or flushed_at.

Important boundary

  • Prefer repo-visible canonical paths under docs/skills/...
  • Do not rely on hidden mirror-relative paths such as .gemini/skills/... when answering repository-local questions

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
36
7-day trend score
18

Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 3 Jun 2026, 5 months ago.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/agi-is-going-to-arrive/memory-palace-openclaw/gemini/badge)](https://verified-skill.com/skills/agi-is-going-to-arrive/memory-palace-openclaw/gemini)

Something wrong with this skill or its page? Tell us.