Capture conversation learnings as structured memory items in a local JSONL store.
npx skills add https://github.com/T-rav/hydraflow --skill hf-memory
Please help me install this Agent Skill. Skill: hf.memory Source: https://github.com/T-rav/hydraflow/tree/main/.codex/skills/hf.memory Command: npx skills add https://github.com/T-rav/hydraflow --skill hf-memory
Capture Session Learnings as memory items to persist decisions, root causes, configuration choices, and workflow preferences from conversations into a local, machine-readable memory store for future reference.
Trigger memory capture by issuing the /hf.memory command in your chat or IDE to scan the current conversation and persist new memory items to the local JSONL store.
High-intent search queries and answers about installing and using this skill.
You can persist conversation decisions and root causes into a knowledge base by extracting them into structured memory items. This Skill scans chat histories, normalizes the discussion artifacts, and stores them locally in a durable JSONL format for future agent lookup.
The best way to deduplicate and normalize learnings from chat histories is to scan the conversation and apply rules that resolve configuration overlaps. This process structures disparate discussion artifacts into clean, machine-readable memory objects without redundant entries.
Yes, you can capture architectural decisions and configuration choices from project discussions into a local JSONL store. Triggering the memory capture command scans your current conversation and persists new structured memory items directly to the local data store.
This memory capture approach works effectively for tracking incident reviews and design rationale by preserving decision contexts. It is designed for project retrospectives and design discussions where configuration choices and workflow preferences need persistent tracking.
To trigger memory capture, issue the dedicated command in your chat or IDE. This action scans the current conversation, deduplicates the findings, and persists new structured memory items to the local JSONL store for immediate future reference.
No external dependencies are required to store conversation learnings as durable memory items. The Skill operates independently to normalize discussion artifacts and writes them directly to a local, machine-readable JSONL memory store.
hikchUpdate DESIGN.md with conversation-derived design decisions and log changes to the Changelog.
eggent-aiSearch and analyze JSONL session logs from the local Eggent agent store.
vellum-aiImport ChatGPT conversation histories from ZIP exports into Vellum.
muhammadhamad1104Manage and retrieve project learnings stored in a JSONL file.
