Menu
Execute PSKA extraction jobs by using PSKA MCP tools, preserving ACLs, source refs, review boundaries, and JSON-compatible candidate outputs.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Answer questions using PSKA MCP retrieval tools with citations, gaps, and no unsupported claims.
Execute PSKA digest jobs with claim-first knowledge extraction, grounded digest notes, and reviewable memory/action/relationship candidates.
Help review PSKA candidates without applying changes unless PSKA review tools and approvals permit it.
Guide for using GraphRAG knowledge graph tools to search and query entities and relationships. Use this SKILL for knowledge retrieval tasks like "search for X", "find entities about Y", "what is X". This SKILL is NOT for programming, implementation, or code writing tasks. GraphRAG知识图谱工具使用指南，用于知识检索和实体查询。适用于"搜索"、"查询"、"查找"等任务，不适用于编程实现任务。
Automated code review and quality analysis
Advanced file operations and navigation
| name | pska_extract |
| description | Execute PSKA extraction jobs by using PSKA MCP tools, preserving ACLs, source refs, review boundaries, and JSON-compatible candidate outputs. |
| tags | ["pska","extraction","knowledge","entities","hyperedges","review"] |
| version | 1.0.0 |
| mcp_servers | ["pska"] |
| recommended_tools | ["pska_pska_search","pska_pska_index_status","pska_pska_review_items"] |
Use this skill when FastReAct is asked to execute a PSKA extraction job.
Rules:
Output shape:
{
"entities": [],
"hyperedges": [],
"review_items": [],
"cited_source_ids": [],
"gaps": []
}