- Home
- Skills
- Atlassian
- Atlassian Mcp Server
- Search Company Knowledge
search-company-knowledge_skill
- Python
239
GitHub Stars
1
Bundled Files
2 months ago
Catalog Refreshed
4 months ago
First Indexed
Readme & install
Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.
Installation
Preview and clipboard use veilstrat where the catalogue uses aiagentskills.
npx veilstrat add skill atlassian/atlassian-mcp-server --skill search-company-knowledge- SKILL.md16.7 KB
Overview
This skill searches across siloed company knowledge systems (Confluence, Jira, and internal docs) to find and explain internal concepts, processes, and technical details. It runs parallel searches, fetches relevant pages or tickets, and synthesizes a clear answer with source citations. Use it to get concise, sourced explanations of systems, deployments, architecture, and processes.
How this skill works
The skill extracts core search terms from your question and performs a cross-system search across Confluence and Jira as the first step. If needed, it runs targeted Confluence or Jira queries, fetches full page or issue content, and prioritizes official documentation and recent tickets. Finally, it synthesizes a direct answer, highlights discrepancies or gaps, and returns links to the original sources.
When to use it
- You need definitions or explanations of internal systems, terminology, or architecture.
- You want to find documentation on deployment, authentication, infrastructure, or processes.
- You need synthesis from multiple internal sources (pages + tickets).
- You suspect documentation and implementation disagree and want clarification.
- You need links to authoritative internal pages or recent Jira issues.
Best practices
- Start with specific technical terms or component names rather than full sentences.
- Use the cross-system search first, then target Confluence or Jira if needed.
- Prioritize official docs (guides, overviews) and recent issues (<1 year) for accuracy.
- Be selective when fetching content—pull full pages or tickets only for the most relevant hits.
- If results are sparse or conflicting, flag gaps and suggest follow-up actions (ask a team or expand terms).
Example use cases
- "What are Stratus minions and how do they scale?" — returns architecture summary and scaling tickets with links.
- "Explain our deployment pipeline" — compiles CI/CD docs and relevant runbook tickets, notes missing rollback steps.
- "How long is the session timeout?" — finds documented timeout and any Jira bug reports that indicate actual behavior.
- "Search for authentication flow docs" — pulls Confluence flow diagrams and Jira issues about recent changes or regressions.
- "Find all docs mentioning the billing system" — returns key pages and related tickets, grouped by component.
FAQ
I report that no results were found, suggest alternative search terms, and offer to expand the search or ask you for synonyms or more context.
How are conflicting sources handled?
I show the direct answer, list each source with its claim, highlight the conflict, note dates, and recommend which behavior to assume until the conflict is resolved.