knowledge-base
/knowledge-base
Query the local scheda knowledge base for past decisions, environment facts, runbooks and project history. Use before deriving an answer from scratch, or when the user asks "how did we do X", "what did we decide about Y", "is there a write-up".
- Author
- LUgABeEEE ↗
- Repository
- scheda ↗
- Licence
- AGPL-3.0
- Last repository change
- 08.11.2026
Assessment and security
- Files in this package
- 2
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 08.11.2026, without references to retired models or APIs.
AGPL-3.0, copyleft: przeróbki udostępniane innym muszą mieć tę samą licencję.
What it does and when to use it
Query the local scheda knowledge base for past decisions, environment facts, runbooks and project history. Use before deriving an answer from scratch, or when the user asks "how did we do X", "what did we decide about Y", "is there a write-up".
Triggers from the description
Original author description
Query the local scheda knowledge base for past decisions, environment facts, runbooks and project history. Use before deriving an answer from scratch, or when the user asks "how did we do X", "what did we decide about Y", "is there a write-up".
How it works
- When to call search
- How to use the result
- Zones
SKILL.md preview
--- name: knowledge-base description: Query the local scheda knowledge base for past decisions, environment facts, runbooks and project history. Use before deriving an answer from scratch, or when the user asks "how did we do X", "what did we decide about Y", "is there a write-up". --- # Local knowledge base You have a local Markdown knowledge base exposed over MCP as the server `kb` (tools: `search`, `read`, `status`, `skills`). ## When to call `search` - The user asks how something was done before, or why a decision was made. - The task touches infrastructure, deployments, credentials *names*, or project history that may already be written down. - You are about to say "I don't have information about that". Do **not** call it per turn, and do not pre-load documents. One call when it is actually needed is the whole design: a search returns ~2.4 KB regardless of how large the base is. ## How to use the result 1. `search` returns `path`, `line`, `snippet` and a score. A snippet is 240 characters — **never quote it as if it were the page**. 2. Expand with `read` (`path`, `start`, `lines`) before relying on it. 3. Cite the path and line in your answer. If the base contradicts itself, say so and show both. ## Zones `zone=z01` (default) covers the public and restricted areas. `z2` is sensitive and is **not** mirrored or indexed by default — if a search returns nothing, `status` tells you whether the index is stale before you conclude the topic is not covered.
Files in this package (2)
- README.md 1 KB
- SKILL.md 1 KB
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · LUgABeEEE/scheda | 85 | AGPL-3.0 |
| FrancoStino/opencode-skills-collection | 100 | MIT |
| bis-med-it/marco-BIS | 100 | Apache-2.0 |
| HG-ha/Argusai | 100 | GPL-3.0 |
| rommapp/romm | 100 | AGPL-3.0 |
| AI-Business-Tools/claude-code | 100 | MIT |
| sickn33/agentic-awesome-skills | 100 | MIT |
| wonderwhy-er/DesktopCommanderMCP | 100 | MIT |
| mkurman/zorai | 100 | MIT |
Database snapshot: 13.11.2026 · package version c58975b56706 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100knowledge-search
Retrieval (RAG) over the local knowledge base. Use BEFORE searching the web, wikis or MCP tools whenever a question or task touches a domain, project, system, convention, decision or past experiment the user has worked on before ("how does X work here", "where is Y", "what did… - 90superbrain-recall
Search the user's SuperBrain second-brain vault. Use whenever the user references past work, prior decisions, "how did we", "did we already", earlier sessions, a project's history, or anything that may already be recorded — before answering from scratch. - 100knowledge-research
This skill should be used when the user asks to "search knowledge", "what do we know about X?", "look up prior decisions on X", "find conventions for X", or "research the knowledge base". - 90llm-wiki
Build and maintain a persistent knowledge base (LLM Wiki) using native backend tools. Supports ingesting PDFs, Markdown, and TXT files, and querying or linting the data. Use this whenever the user wants to add, retrieve, or manage their own local knowledge base and documents. - 100knowledge-search
Search the user's knowledge bases and knowledge spaces (企业知识库检索). Use this whenever the user wants to 查知识库 / 检索资料 / 搜一下有没有… / 查内部文档、规范、流程、发版说明, or asks any question their organisation's knowledge base may answer. Read-only retrieval with the user's own permissions. - 90knowledge-base-health-check
Audits a local Claude-managed knowledge base under a 'Knowledge Base/' folder. Surfaces contradictions between articles, broken backlinks, unsourced claims, stale articles, writing-rules violations, and three suggested new articles. Files a full report into the KB's 'Outputs/'…