Stats
Actions
Tags
From hipocampo
Compact long-closed insights into a one-line archive index so they stop costing discovery context while staying traceable. Use when the user says "/archive-closed", "compact the insights", "clean up old insights".
How this skill is triggered — by the user, by Claude, or both
Slash command
/hipocampo:archive-closedThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Insights with a terminal status (closed/implemented/rejected/superseded) are dead
Insights with a terminal status (closed/implemented/rejected/superseded) are dead history: kept for traceability, but they shouldn't cost full-page context on every discovery sweep. This compacts them into an archive index (beads-style semantic compaction).
<vault>/insights/** for status in
{closed, implemented, rejected, superseded}. (Search with --all includes them.)<vault>/insights/_archive-index.md:
- [<title>](<path>) — <status> (<date>) — one-line outcome.status/dates while archiving; you're only
summarizing. raw/ and knowledge/ are out of scope (this is insights-only).npx claudepluginhub ferraz2000/hipocampo-memory --plugin hipocampoProvides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.