BC ontology-engineer
Extract candidate ontology models from enterprise business systems AND build/maintain personal knowledge graphs from any file system. Use when: ontology extraction, 本体提取, schema analysis, entity extraction, data dictionary (数据字典), 表结构分析, knowledge graph (知识图谱), 全量扫描, file scan, personal knowledge (个人知识), or analyzing business system data models. Three operating modes: (A) Database/schema extraction — SCAN→EXTRACT→MERGE from SQL DDL, Word/Excel data dictionaries. Outputs ontology.json + review.md. (B) Filesystem scanning — index→analyze pipeline for personal knowledge graph. Reads Office/PDF/text, extracts entities and domain structures. Outputs graph.jsonl + schema.yaml. (C) External data scanning — same as B for others' data spaces (clients, partners). Handles .docx .doc .wps .pdf .xlsx .xls .et .pptx .ppt .dps .md .txt .sql .yaml .json .csv. Uses python-docx, PyMuPDF, openpyxl, python-pptx. Supports multimodal image analysis. No external API keys or network access required — the LLM running this skill IS the semantic analysis engine. All processing is local. File scanning is user-scoped via mandatory Step 1.5 confirmation before any analysis begins.
As a process C 61/100 · Has gaps — weak spots: inputs and preconditions, running it twice
How to improve
- Shorten the description to 1024 characters.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 17. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1169 chars, limit 1024 - note
frontmatter-keyunknown frontmatter key "metadata.openclaw"
Process rating: all ten parameters 61/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 17 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 60Failures and branches. 2 branches
- 85Steps. 42 steps, 2 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3348 tokens
- 100Progress reporting. Reports progress
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1169: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +4Structure: 21 headings
- +3Step-by-step instructions: 42 items
- +3Output format is stated explicitly
- +4Has examples (8 code blocks)
- +4Reference files are cited in the instructions (10 of 10)
- +3All 4 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 65.