vl-msa
Skill4 starsChanged 36 days agoApache-2.0View on GitHub
Use when indexing or retrieving documents, notes, research or past conversations through a VL-MSA long-term-memory MCP server, including collections, batch indexing, BM25 or hybrid search, full-document grounding, remember/forget and bounded multi-hop interleaving. Enforce locate-then-ground retrieval and choose the user-facing language from the request.
In this repository8 other files it gives its agents.
- aidesktopSkill
- cellforgeSkill
- crewSkill
- liveSkill
- mail-assistantSkill
- memorySkill
- nexuscrew-agentSkill
- nexuscrewSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
14 rules. About 0 are common, 6 are distinctive, and 8 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
8
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Use VL-MSA for durable searchable source material.
- Distinctive: line 20
Keep collection IDs, document IDs, tool names, metadata fields and quoted source text unchanged unless the user explicitly asks to …
- Very specific: line 27
Call msa_search {collection, query, k} to locate relevant chunks.
- Very specific: line 28
Call msa_fetch_doc for the selected hit before using it as evidence.
- Distinctive: line 30
Search chunks are locators, not complete sources.
- Very specific: line 35
Use msa_index for one document or note.
- Very specific: line 36
Use msa_index_batch for bulk ingest.
- Very specific: line 46
Use msa_remember for a standalone agent memory.
- Very specific: line 48
Use msa_forget for an explicitly requested removal.
- Distinctive: line 50
Do not claim a memory was stored or removed until the tool confirms the outcome.
- Very specific: line 55
Use msa_interleave_round for one bounded route, deduplicate and read step.
- Distinctive: line 61
Use BM25 by default.
- Distinctive: line 64
Do not describe lexical-only results as semantic retrieval.
- Very specific: line 66
If no VL-MSA tool is available and this skill is packaged with NexusCrew, the optional companion is documented in ../../MCP_COMPANIONS.md.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
VL MSA
Use VL-MSA for durable searchable source material. Collections persist across sessions; BM25 works without embeddings, while hybrid reranking is optional.
Select response language
Choose the language for explanations and answers in this order:
- the user's explicit language preference;
- the language of the current request;
- a reliable client or system locale;
- English.
Keep collection IDs, document IDs, tool names, metadata fields and quoted source text unchanged unless the user explicitly asks to translate them.
Locate, then ground
Retrieval has two required steps:
- Call
msa_search {collection, query, k}to locate relevant chunks. - Call
msa_fetch_docfor the selected hit before using it as evidence.
Search chunks are locators, not complete sources. Do not answer a context-dependent question from truncated snippets alone.
Index material
- Use
msa_indexfor one document or note. - Use
msa_index_batchfor bulk ingest. - Group related material into a stable named collection.
- Inspect
msa_list_collections,msa_statsormsa_manifestbefore assuming a collection exists or is populated.
Index only material the user is authorized to store. Preserve provenance and do not place credentials or unrelated personal data in collection metadata.
Manage standalone memories
- Use
msa_rememberfor a standalone agent memory. Its deduplication and low-signal gate may decline a write. - Use
msa_forgetfor an explicitly requested removal.
Do not claim a memory was stored or removed until the tool confirms the outcome.
Handle multi-hop questions
Use msa_interleave_round for one bounded route, deduplicate and read step.
Repeat only as needed, carrying forward the grounded facts from the prior
round. Avoid a single unbounded search.
Choose ranking
- Use BM25 by default.
- Pass
dense_alphaonly when the server is built and configured for hybrid retrieval. - Do not describe lexical-only results as semantic retrieval.
If no VL-MSA tool is available and this skill is packaged with NexusCrew, the
optional companion is documented in ../../MCP_COMPANIONS.md. Explain the
missing capability and ask before installing or configuring anything.
Dependencies
Bundled: nothing — this skill is documentation only.
External (you must provide):
| Need | Install | Probe / failure mode |
| A VL-MSA MCP server (companion) | optional companion mcp-vl-msa-rs: https://github.com/DioNanos/mcp-vl-msa-rs — the repository's Install section is authoritative and may change; this skill deliberately does not duplicate its commands (not verified here) | if the companion is not registered, the client exposes no msa_* tools; ask the client for its tool list |
| Client MCP registration | register the companion's stdio command in the AI client's MCP config | same failure mode: absent tools, not a runtime error |
Without the companion, durable retrieval is simply unavailable in that session: say so and suggest the companion once instead of reading the server's on-disk collections directly (which this skill forbids).
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

