315 skills · sorted by relevance
Use OpenViking through OpenClaw to manage long-term memories, search archived conversations, and find imported resources or Agent Skills. Inspect recall traces to understand search results and recover full tool outputs stored outside the conversation.
Manually sync OpenClaw chat transcripts to OpenViking and search stored memories using explicit commands. Receive a sync summary or relevant memory entries while leaving the OpenClaw contextEngine slot available for its existing use.
Use Memori Cloud from Claude Code to consult stored preferences, decisions, and project history before substantive work, then save the exchange afterward. Recall can span sessions and use filters for dates and information types.
Persistent compounding memory for AI agents. 5 default MCP tools: session_start, session_end, remember, recall, check. Full surface: 6 tools with --full (adds check_action); 13 tools with AR_EXTRAS=1 --full. Two-verb model: inhale (session_start) and exhale (session_end). Correction-first memory with decision trail tracking, watch_for warnings, palace rooms with salience scoring, cross-project insight matching, same-day journal merging, ambient recall hooks. Local markdown only. Zero cloud, zero telemetry, Obsidian-compatible. Optional Supabase backend: when configured via `ar setup supabase`, recall() uses pgvector cosine similarity on OpenAI/Voyage embeddings instead of keyword search — same API, semantic understanding. Gracefully degrades to local search if not configured.
The English summary is being prepared. Showing the original description.
Answer questions about past work, people, projects, and decisions by searching stored MemPalace records first. Retrieve exact source wording, check facts at relevant dates, and maintain session continuity without guessing when records are unavailable.
Carry context between scheduled or event-triggered routine runs using Hindsight memory. Add recall and recording steps to routine instructions so each run can use previous findings, resume unfinished work, compare changes, and leave guidance for the next run.
Set up the OpenViking long-term memory plugin for OpenClaw through conversation. The skill handles installation, configuration, and verification so chat facts can be saved and relevant memories recalled across sessions, using an existing OpenViking server.
Diagnose missing recall, failed captures, and connection errors in the OpenViking memory plugin for Codex. Check installation, configuration, authentication, and server readiness, then use the findings to guide fixes and verify that memory works again.
Diagnose OpenViking memory problems by checking plugin installation, client settings, server connections, and recent activity. The skill helps trace missing recalled context, failed saves, and authentication errors, then guides targeted fixes and checks whether they worked.
Query documents and conversations stored in cognee to retrieve answers, supporting passages, or context for an AI model. This skill guides search method selection, source filtering, result interpretation, and troubleshooting empty or unexpected results.
[omh] Previously rejected options to revisit: recall scoped reviewed rejected decisions without elevating them to approved memory. Use when the user says: decision-recall, rejected decision recall, rejected decisions, why was this rejected, previously rejected alternative, 거절된 결정, 기각된 대안.
The English summary is being prepared. Showing the original description.
Check for open safety recalls on a vehicle using the CarsXE API. Use this when a user asks whether a car has any recalls, safety issues, or wants to know if their vehicle needs a recall repair.
The English summary is being prepared. Showing the original description.
Check safety recalls by year, make, and model (no VIN) using the CarsXE Recalls by YMM API. Use this when the user asks about recalls for a model line, or has year/make/model but no VIN.
The English summary is being prepared. Showing the original description.
Submit and retrieve bulk safety-recall checks for many VINs using the CarsXE Recalls Batch API. Use this when the user wants to check recalls for a fleet, inventory list, CSV of VINs, or more than a handful of vehicles at once.
The English summary is being prepared. Showing the original description.
Persistent compounding memory for AI agents. 5 default MCP tools: session_start, session_end, remember, recall, check. Full surface (18 tools) available with --full flag. Two-verb model: inhale (session_start) and exhale (session_end). Correction-first memory with decision trail tracking, watch_for warnings, palace rooms with salience scoring, cross-project insight matching, same-day journal merging, ambient recall hooks. Local markdown only. Zero cloud, zero telemetry, Obsidian-compatible. Optional Supabase backend: when configured via `ar setup supabase`, recall() uses pgvector cosine similarity on OpenAI/Voyage embeddings instead of keyword search — same API, semantic understanding. Gracefully degrades to local search if not configured.
The English summary is being prepared. Showing the original description.
Decision protocol for strategic work: recall the knowledge vault, run a gap analysis, emit a deep-research prompt for external tools, then synthesize the returned reports into a decision memo. Use before any new product, feature, market, pricing, GTM or architecture call, where local recall alone is not enough. Triggers: "/alfa-search-recall-deepresearch", "alpha protocol", "R+DR".
The English summary is being prepared. Showing the original description.
Search screen text and audio recorded by Screenpipe to recall meetings or activity in other apps. Filter by topic, time, or application, then optionally save selected facts with source references into claude-mem.
Use Hindsight to recall past context, save reusable facts, and reason across accumulated memories. Supports continuity between conversations by preserving preferences, project decisions, and lessons learned, while helping explain the reasoning behind earlier choices.
Search past conversations to recover decisions, discussions, and context across sessions. Find related ideas by meaning, match exact terms, or locate code identifiers, with options to search only user or assistant messages through local AI Maestro tools.
Retrieve past work, decisions, and lessons from agentmemory using keyword, meaning, and relationship searches. It expands selected records, groups findings by session, and prioritizes important observations so earlier context can inform the current task.
Organize knowledge notes with links that explain their relationships, search saved information, review conflicting claims, and prepare weekly digests. Retrieve earlier work sessions and conversations by topic or date to recover context before continuing a task.
Retrieve past decisions, recurring patterns, and unexpected issues from MemPalace before planning a phase. The skill produces a concise file with source references for the planner and falls back to GSD’s native memory when MemPalace is unavailable.
Recall why a past change was made, drawing on Codex session history when available and falling back to commit diff and surrounding code. Use when the user asks to "recall the rationale", "find the rationale", "look up the rationale", "why did I do X", "why did we do X", "why was this changed", or "find the transcript for this commit".
The English summary is being prepared. Showing the original description.
Recall why a past change was made by locating the Claude Code transcript that produced it. Use when the user asks to "recall the rationale", "find the rationale", "look up the rationale", "why did I do X", "why did we do X", "why was this changed", or "find the transcript for this commit".
The English summary is being prepared. Showing the original description.