Aggregate cross-source project memory into a single recall report.
npx skills add https://github.com/linenoize/topia --skill recall-linenoize
Please help me install this Agent Skill. Skill: recall Source: https://github.com/linenoize/topia/tree/main/skills/recall Command: npx skills add https://github.com/linenoize/topia --skill recall-linenoize
This Skill solves the problem of starting with missing context by gathering scattered project memory into one dependable Recall Report. It helps you resume work, make architecture decisions, and preserve continuity across sessions without manually hunting through old notes.
Ask the assistant to run recall for your project so it can gather available memory sources and return a concise Recall Report.
High-intent search queries and answers about installing and using this skill.
Recovering session context involves aggregating scattered project memory from file-based stores and optional MCP backends into a single read-only Recall Report. This unified view helps you resume work and make architecture decisions without manually hunting through old notes.
Aggregating architecture decisions is best handled by gathering cross-source project state and session notes into a single report. The process applies source tagging and precedence rules to consolidate prior decisions and active checkpoints in a read-only format.
Gathering project state with missing sources relies on graceful degradation behavior to return partial but useful context. The read-only aggregation still compiles available file-based memory when optional semantic memory backends or MCP queries are unavailable.
Recall does not write to memory stores during session-start recovery. It operates with strict read-only file gathering safety, ensuring your existing project memory across neural-memory and agora-memory stores remains completely unmodified.
You can use optional MCP queries to pull semantic memory into your project state report. The aggregation process combines these optional backends with local file-based sources, applying source tagging to deliver a unified recall view.
rush-dbStore and link agent memories as structured records in RushDB.
jonkikySave and resume working state checkpoints with git state and decisions.
gancimOrganizes knowledge into PARA-based memory files with YAML frontmatter for cross-session recall.
EotelGenerate docs/CONTRIB.md and docs/RUNBOOK.md from package.json scripts and .env.example.
