Stats
Actions
Tags
From hipocampo
Fact-check a vault page against its cited sources — every claim must trace to a source that actually supports it. Use when the user says "/audit <path>", "fact-check this note", "verify this page against its sources".
How this skill is triggered — by the user, by Claude, or both
Slash command
/hipocampo:auditThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
The anti-model-collapse audit: `knowledge/` is only as good as its provenance.
The anti-model-collapse audit: knowledge/ is only as good as its provenance.
$ARGUMENTS = path (or slug) of a knowledge/ or insights/ page.
sources: list.raw/sources/ files directly; external URLs fetched if
tooling allows (else mark UNVERIFIABLE-HERE, don't guess). For several
independent sources, parallel read-only sub-agents keep the main context lean.[as of]/valid_until).superseded_by, or set valid_until. Apply only what's approved; raw/ is
never edited.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.