菜单
Extract pixel-anchored P&ID valve symbol instances from prepared tiles using isolated-crop classification before any row may count.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | pandid-valve-symbol-instance |
| description | Extract pixel-anchored P&ID valve symbol instances from prepared tiles using isolated-crop classification before any row may count. |
| compatibility | TASK shell |
| metadata | {"chirality-skill-version":"1.0.0","chirality-task-profile":"DRAWING_EXTRACT"} |
Extract visible P&ID valve body symbol instances from one prepared tile. A row may exist only after an isolated symbol crop has been classified as a valve class. Text never produces rows, and tag profiles never delete rows.
count_include=true only for valve classes with symbol_confidence of medium or high.nearby_line_text with tag_status=line_spec_only or ambiguous only after a valve row exists.visible_tag_text only for actual valve/control-loop tags and set tag_status=true_tag.NO_FINDINGS_REFERENCE for reference/legend sheets unless explicitly allowed by the brief.The output file is a markdown stub using valve_schema_version: symbol_instance_v1 and the canonical table columns from tools/drawing_extract/valve_stub_layout.py.
Required row evidence:
center_x_px, center_y_pxbbox_*_pxsymbol_crop_pathsymbol_classsymbol_confidencecount_includereview_statusreview_reasonValid valve classes are manual_block, manual_throttle, check, control, esd_block, relief, and specialty_valve.
Read one deliverable folder and produce a structured 7-section content digest summarizing identity, scope, document kit, dependencies, references, semantic framework, and quality observations.
Transform raw concordance evidence atoms and risk inventory rows into typed publication concordance candidates for register freeze review.
Post-synthesis cross-section semantic concordance verification for rewritten DBM package outputs.
Review a human-prepared draft DBM against the governed knowledge base — build review substrate, prepare candidate findings for human disposition.
Post-authoring evidence bundle and review for pipeline-produced DBM sections — build review substrate, prepare candidate findings for human readiness judgment.
Assemble the full rewritten DBM package from approved section outputs and produce package QA artifacts.