memory-retriever

Solid

Use when the user explicitly chooses read-only RightMemory retrieval for relevant context from earlier work, preferences, project or domain knowledge, live Pursuits, or reusable agent guidance. This skill never submits updates or modifies RightMemory.

Code & Development 9 stars 2 forks Updated today Apache-2.0

Install

View on GitHub

Quality Score: 79/100

Stars 20%
33
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# Memory Retriever CLI ## Access Rules - The RightMemory root is `{{MEMORY_ROOT}}`; do not read or edit files there directly unless the user explicitly permits direct access. - Pick one stable session id for this agent conversation and reuse it for every retrieve call. ## Retrieval - Call `rightmemory retrieve --session <stable-session-id> "<memory need>"`. - Describe the context needed from the user's intent instead of blindly forwarding the user's message. - Give the retrieve command up to 3 minutes to return. Await or poll that command; do not run a separate blocking wait, explore files, or advance the task while it is pending. - The retriever skips unchanged content already returned in this session. When the user needs matching content repeated, add `--include-returned` for that call; do not change the session id. - Treat Memory as durable context and Pursuit as live intent or continuity. Do not blur their lifecycle meanings in the answer. - Retrieval output is authoritative source Markdown selected by the model and rendered by RightMemory, not a model-written summary. - A selected F# heading includes its parsed detail subtree. A local M#, S#, or MF# heading does not by itself expand linked content; local M# evidence uses source ranges and local S# expands only as a complete instruction. Imported MF# graph content uses ids scoped to `MF#<view-id>`, including F# detail items; direct MF ranges are invalid. Imported M# ranges and complete S# instructions use qualified so...

Details

Author
RightL
Repository
RightL/RightMemory
Created
2 months ago
Last Updated
today
Language
Python
License
Apache-2.0

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Solid

rightmemory-orchestrator

Use when the user explicitly chooses full RightMemory orchestration: conditionally retrieve relevant durable Memory or live Pursuit context, then submit task-state, durable-context, and explicit-correction candidates so the unified updater can maintain both document trees.

9 Updated today
RightL
AI & Automation Listed

right-memory

Manage your long-term memory powered by Hindsight

33 Updated today
onsails
AI & Automation Listed

memory-search

Searches the project's recorded memory (core-memory-kit) — decisions, conventions, architecture, the reasoning behind choices, and where things live — and returns a curated, cited summary. Fire whenever the answer might be something the project already established in past work, HOWEVER the question is phrased — any prior decision, convention, rationale, or "how/where/why is it this way" question, including oblique or roundabout asks ("why is everything so spread out?", "remind me what we settled on for X", "how come these files are tiny?"). Also fire when a "[core-memory-kit] Memory available" hint appears on the prompt. The examples are illustrative, not a checklist — prefer recalling over re-deriving an answer from the code. The session-start snapshot is a bounded index; this skill reaches the rest. Skip only when the question is purely about uncommitted or just-edited live code that memory cannot know, concerns this conversation only, or the user asked to ignore memory.

4 Updated today
LH8PPL