From ideas-funnel
Answer a question against the vault. Scans index.md for candidate pages, reads the relevant bodies, synthesizes a response with [[wikilink]] citations, and optionally files the answer back as a new Concept page if the answer is novel enough to deserve one. Trigger phrases: "query the vault", "/ideas-funnel:query", "what does the vault say about X".
How this skill is triggered — by the user, by Claude, or both
Slash command
/ideas-funnel:queryThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
**Used by:** human (on demand).
Used by: human (on demand).
Answer a question using tiered retrieval over the vault.
A natural-language question. Example: /ideas-funnel:query what do we know about Karpathy's LLM Wiki pattern?
Read ~/Vaults/Neurons/index.md. Match the question against page titles, summaries, tags. Build a ranked shortlist of candidate pages (up to 15).
If the shortlist is thin (< 3 candidates), do a full-text search:
cd ~/Vaults/Neurons
grep -rliF "<key-term>" Concepts Entities Sources Domains --include="*.md"
Open the shortlist. Pay attention to summary: frontmatter — that's the one-line gist. Skim bodies for the specific claims that answer the question.
Write a response:
[[Path/Page]].tension_score if present in frontmatter).If the answer represents a synthesis that doesn't exist as its own Concept page, offer to create one:
This answer is a synthesis across [[A]], [[B]], [[C]]. File as a new Concept page?
If user accepts, write Concepts/<Name>.md with provenance.origin: ai-generated and state: fresh.
Append to log.md:
## [YYYY-MM-DD] query | "<question>" | pages_read: N | filed_new: <yes|no>
Concepts/ and Bridges/ for synthesis; Sources/ for primary evidence.npx claudepluginhub cosmicdreams/claude-plugins --plugin ideas-funnelFetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.
Applies a firm's KYC/AML rules grid to parsed onboarding records: assigns risk rating, checks required documents, outputs rule outcomes with citations, and routes for escalation.
Generates daily or weekly digests of activity from connected sources (chat, email, docs, tasks, CRM), highlighting action items, decisions, mentions, and project updates.