mfs-find
Search, grep, browse, and read across registered MFS data sources via the `mfs` CLI — codebases, docs, PDFs, web crawls, databases (postgres/mysql/mongo/snowflake/bigquery), issue trackers (jira/linear/github), CRMs (hubspot), chat (slack/discord/gmail/feishu), object stores (s3/gdrive). Use whenever the user asks to find, locate, look up, look across, or read something out of an already-configured MFS index. Trigger phrases include "search the codebase for", "find anywhere about", "where is X mentioned", "look across our [slack/jira/postgres/etc]", "any past tickets/RFCs/commits about", "what does our wiki say about", "cat / head / tail / ls / tree this MFS path". Do NOT use for: registering a NEW data source (use `mfs-ingest`), changing connector config, kicking off re-ingest, or any write/delete operation — `mfs` is read-only.
zilliztech · 已有 AI 审核记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add zilliztech/mfs --skill mfs-find技能说明
name: mfs-find
version: 0.4.0
mfs_compat: ">=0.4,<0.5"
description: >-
Search, grep, browse, and read across registered MFS data sources via the
mfs CLI — codebases, docs, PDFs, web crawls, databases
(postgres/mysql/mongo/snowflake/bigquery), issue trackers
(jira/linear/github), CRMs (hubspot), chat (slack/discord/gmail/feishu),
object stores (s3/gdrive). Use whenever the user asks to find, locate,
look up, look across, or read something out of an already-configured MFS
index. Trigger phrases include "search the codebase for", "find anywhere
about", "where is X mentioned", "look across our [slack/jira/postgres/etc]",
"any past tickets/RFCs/commits about", "what does our wiki say about",
"cat / head / tail / ls / tree this MFS path". Do NOT use for:
registering a NEW data source (use mfs-ingest), changing connector config,
kicking off re-ingest, or any write/delete operation — mfs is read-only.
MFS — find / read across configured sources
1. What MFS is
A retrieval layer that exposes many kinds of content as a unified path tree and makes that tree searchable through one hybrid index:
- One CLI (
mfs), one mental model. Local dir, Postgres, GitHub repo, Slack workspace, S3 bucket, BigQuery dataset — all addressed as paths under their<scheme>://URI. Same verbs everywhere:ls / tree / cat / head / tail / grep / search / export. - One hybrid index. Dense vectors (semantic) + BM25 (keyword) fused per query — covers conceptual recall and exact-token recall in one call.
- POSIX-style locators. Every search hit carries a
locatorthat reopens the exact unit:{"lines":[s,e]}for text/code, a PK dict for rows/issues/threads.
2. When to use MFS — and when NOT to
| Situation | Use MFS? |
|---|---|
| 1000+ files / rows / pages, you don't know where the answer is | ✅ |
| Cross-source question ("any past tickets / commits / RFCs about X") | ✅ --all |
| Concept-style query that won't match literally | ✅ --mode semantic |
| You already know the exact file + roughly where to look | ❌ plain cat/grep |
| Exact identifier / error code in 5 files you can list | ❌ plain grep/rg |
| Real-time tailing of a live log | ❌ index lags ingest |
| The source isn't in MFS yet | wrong skill, use mfs-ingest to register first |
Rule: use the smallest tool that answers the question. MFS pays off
when the scope is too big for rg.
Borderline — ASK the user:
| Ask | Likely answer | Why |
|---|---|---|
| "Summarise these 10 PDFs" | ✅ mfs search + cat --peek per hit | each PDF gets a converted_md artifact + searchable chunks |
| "Find similar tickets to this one" | ✅ paste the ticket text as the search query | semantic over row_text does similarity matching |
| "Watch for new slack messages" | ❌ no watch capability; use Slack's API | index lags ingest |
| "Look up user 12345" | ❌ mfs cat <source> --locator '{"id":12345}' directly (skip search) | one-record-by-id doesn't need ranking |
3. Pre-flight — confirm the source is indexed
Before running any query, especially on cross-source asks:
mfs status # server up? any connectors registered?
mfs connector inspect <uri> # this connector's object/job summary
mfs ls <uri> --json # per-entry capabilities + indexable / search_status
- Server unreachable → tell user to start it (
mfs serve startif self-hosted), or this skill can't proceed. connectorsempty → user hasn't ingested anything yet. Redirect tomfs-ingest— don't try to search nothing.search_status: unavailablefor the target URI → onlygrep/ls/catwork; offer those or redirect tomfs-ingestfor a re-sync.building→ sync in flight; fall back tomfs grep(works without an index) until done.partial→ recall incomplete but usable; flag the caveat to the user.
4. The core workflow: search → locate → browse
search locate browse
┌──────────────────┐ ┌──────────────────┐ ┌─────────────────────┐
│ semantic + BM25 │ → │ result has lines │ → │ cat --range / cat │
│ finds candidates│ │ or a locator │ │ --peek to confirm │
└──────────────────┘ └──────────────────┘ └─────────────────────┘
On large corpora this loop is the whole point: read only the part that matters. On small corpora it's still fine, just lighter.
Concrete:
- Search:
mfs search "<what the user actually wants>" <path-or-uri> --top-k 10 - Locate — every hit's envelope carries
locator:- text/code →
{"lines":[start,end]}→mfs cat <source> --range start:end - structured (row/issue/thread) → PK dict →
mfs cat <source> --locator '{...}' - once-per-object (dir/schema summary, image VLM) →
null→mfs cat <source>
- text/code →
- Browse — verify only what's needed:
mfs cat --peek <file> # outline (headings / function signatures) mfs cat --skim <file> # peek + one-line summaries per section mfs head -n 20 <uri> # first records of a structured object mfs tree <uri> -L 2 # subtree shape
5. Index requirement rules of thumb
mfs searchrequires an index.mfs grepworks without — pushdown → BM25 → linear scan fallback.mfs ls / tree / cat / head / tailbrowse without an index.
6. Search modes
mfs search defaults to hybrid. Override only when you know why.
--mode | Mechanic | When |
|---|---|---|
hybrid (default) | dense + BM25 fused with RRF | almost always |
semantic | dense only | conceptual query, wording won't match literally |
keyword | BM25 only | exact-term (config key, error code) without semantic drift |
Other useful flags:
--top-k N— default 10; raise to 20-30 on a weak first round.--all— search every registered connector. Otherwise scope to a path/URI prefix.--kind <list>— restrict chunk kinds (row_text,