Multica Platform Knowledge Base

Community

it235

multica-platform-knowledge-base

Remote Wiki knowledge-base Q&A (Knowledge Base Bridge). Platform skill, mounted on demand by tester/frontend/backend/architect; invoked by name from content skills.

Overview

Publisher	it235
Repository	`multica-best-practices`
Skill name	`multica-platform-knowledge-base`
Stars	199
Forks	29
Bundled files	2
License	MIT
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
2 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by it235 on GitHub. Read the source before you install it.

Installation

Install the Multica Platform Knowledge Base AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/it235/multica-best-practices/tree/main/templates/en_US/skills/platform/multica-platform-knowledge-base
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/it235/multica-best-practices/tree/main/templates/en_US/skills/platform/multica-platform-knowledge-base

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/it235/multica-best-practices.git /tmp/multica-best-practices
mkdir -p .claude/skills
cp -r /tmp/multica-best-practices/templates/en_US/skills/platform/multica-platform-knowledge-base .claude/skills/multica-platform-knowledge-base

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Multica Platform Knowledge Base in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Multica Platform Knowledge Base on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Multica Platform Knowledge Base is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Platform · Knowledge Base (remote Wiki)

Purpose

Query the team Wiki knowledge base via the Knowledge Base Bridge HTTP API. Used by @Tester / @FrontendDev / @BackendDev / @Architect to look up entry paths, terminology, and historical context.

Integrated from the internal knowledge-base squad; script scripts/kb_ask.py (stdlib only, cross-platform).

Architecture

text
Agent (local)
    ↓ kb_ask.py (HTTP)
Knowledge Base Bridge :3910
    ↓ Cursor SDK Agent + Skills
Team Wiki
    /home/ubuntu/cursor-workspace/.cursor/skills/knowledge-base/wiki/

(The path lives on the knowledge-base service side; the local Agent only accesses it through the Bridge HTTP API.)

Agent execution rules (mandatory)

Step	Action	Forbidden
1	`python scripts/kb_ask.py --health`	SSH fallback, hand-written curl
2	`python scripts/kb_ask.py "question" [system-code]`	Fabricating the source of a citation
3	Present the `answer` from stdout	Expanding historical rules into current acceptance criteria

Bridge identification rules

The script automatically satisfies the Wiki Q&A conditions (the Agent must not switch to another HTTP method to bypass it):

taskId >= 500000000 (default generated by script)
prompt prefix 【Wiki 知识库问答】

When to use

The local machine has no knowledge-base copy and you need to look up business Wikis such as CRM/MES/BOSS
The user asks to query the team knowledge base remotely
T1 Step 0.5b: retrieve entry paths / terminology / historical context by module keyword (acceptance still uses the current JIRA as source of truth)

When not needed

A complete local knowledge-base copy already exists and Read/Grep hits the needed content directly
The question is unrelated to the current requirement, or only verifying Bridge connectivity (use --health)

Usage

bash
python scripts/kb_ask.py --health
python scripts/kb_ask.py "Where is the CRM case-management entry?"
python scripts/kb_ask.py "MES work-order status" MES
python scripts/kb_ask.py "question" --json

Configuration

Variable	Description
`KB_BRIDGE`	Bridge address, default in `config.yaml`
`KB_POLL_INTERVAL`	Poll interval seconds, default 2
`KB_POLL_TIMEOUT`	Timeout seconds, default 600

Timeout / unavailable stop rule (mandatory)

Do not stall in "running" waiting for the knowledge base.

--health fails, or kb_ask.py times out/errors → mark "team knowledge base unavailable/timeout"
End this round of waiting immediately, explain the block and options (retry / skip KB / check Bridge)
The caller (e.g. T1 Step 0.5) may annotate and continue, but must not poll repeatedly until the user perceives a hang
Do not fabricate business rules or citation sources because of unavailability

Troubleshooting

Symptom	Handling
Cannot reach Bridge	VPN/intranet; `python scripts/kb_ask.py --health`
Timeout	Follow the stop rule above; only raise `KB_POLL_TIMEOUT` when the user explicitly asks
status=error	Add `--json` to inspect `error`

Relationship to the test flow

T1 functional cases (multica-test-t1-design): before generation, Step 0.5 queries the KB for entry/terminology; acceptance still uses current JIRA/PRD as source of truth
Interface scenario supplement (multica-platform-apifox): query historical auth/data-seeding for the same module
Frontend/backend implementation: query module conventions, error codes, permission semantics

Why it works

The knowledge base was extracted from a test-only squad into a platform skill, mounted by role on demand, avoiding hardcoding the Bridge address or SSH path in role prompts.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

config.yaml1 KB
scripts/kb_ask.py6 KB

Frequently asked questions

What does the Multica Platform Knowledge Base AI skill do?

Remote Wiki knowledge-base Q&A (Knowledge Base Bridge). Platform skill, mounted on demand by tester/frontend/backend/architect; invoked by name from content skills.

Why use Multica Platform Knowledge Base on TypingMind?

Because you install it once and use it with any model. Multica Platform Knowledge Base is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Multica Platform Knowledge Base in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/it235/multica-best-practices/tree/main/templates/en_US/skills/platform/multica-platform-knowledge-base. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Multica Platform Knowledge Base?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Multica Platform Knowledge Base?

As many as you like. As long as a model supports skills, you can use Multica Platform Knowledge Base with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Multica Platform Knowledge Base AI skill free?

Yes. It is published on GitHub by it235 under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Gitcrawl

openclaw

OrganizationPopular

GitHub archive: issue/PR search, sync freshness, duplicate clusters, current GitHub handoff, and Gitcrawl repo work.

Graincrawl

Granola archive: search, sync freshness, notes, transcripts, panels, SQL counts, and Graincrawl repo work.

Openclaw Changelog Update

openclaw

OrganizationPopular

Regenerate OpenClaw release changelog sections from git history before beta, stable, or extended-stable releases.

Openclaw Ci Limits

Manage OpenClaw GitHub Actions and Blacksmith CI capacity, runner-registration budgets, fanout caps, main-push single-flight, shard sizing, hosted-runner offload, queue health, and safe…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Platform · Knowledge Base (remote Wiki)

Purpose

Architecture

Agent execution rules (mandatory)

Bridge identification rules

When to use

When not needed

Usage

Configuration

Timeout / unavailable stop rule (mandatory)

Troubleshooting

Relationship to the test flow

Why it works

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now