From omni
Orchestrates iCenter knowledge reverse engineering: fetches pages from --page-root URLs, links architecture docs, extracts requirements/system-contexts/scenarios/logical-architectures by --target to specs. Triggers on reverse --source icenter.
npx claudepluginhub zte-aicloud/co-omnispec --plugin omniThis skill uses the workspace's default tool permissions.
- **职责**:按阶段编排,从 iCenter 拉取页面并完成架构-文档关联,然后按 `--target` 提取并落盘以下一种或多种知识产物:
references/scripts/common.pyreferences/scripts/fetch_page_ids.pyreferences/scripts/fetch_pages_local.pyreferences/scripts/relate_architecture_page.pyreferences/scripts/requirement-icenter.txtreferences/stages/01-fetch-page-ids.mdreferences/stages/02-fetch-pages-local.mdreferences/stages/03-icenter-doc-architecture-linking.mdreferences/stages/04a-extract-knowledge.mdreferences/stages/04b-extract-whole-knowledge.mdOrchestrates reverse engineering of codebases to extract interfaces, logic architecture, functions, scenarios, constraints into standardized Markdown documents. Supports full pipeline or on-demand targets.
Searches and navigates PDFs/DOCX/PPTX/Markdown documents, extracts tables/figures, builds wiki knowledge bases using retrieval, deep reading, and ingestion tools.
Ingests an external data source into the Second Brain. Fetches content from Confluence, Google Docs, GitHub repositories, remote URLs, or any local file format supported by docling (DOCX, PPTX, XLSX, PDF, HTML, EPUB, images, Markdown, CSV, and more), converts non-markdown formats to markdown via docling, runs the /graphify extraction pipeline, and delegates entity persistence (including the graphify-output merge) to /bedrock:preserve. Use when: "bedrock learn", "bedrock-learn", "learn", "ingest source", "import document", "/bedrock:learn", or when the user provides a Confluence, Google Docs, or GitHub URL, a remote file URL, or a local file path to incorporate into the vault.
Share bugs, ideas, or general feedback.
--target 提取并落盘以下一种或多种知识产物:
requirementssystem-contextsscenarioslogical-architecturesreverse --source icenter ...;--page-root 必须由用户提供(支持英文逗号分隔多个 URL);--target 未指定时,必须默认使用 all(不再二次询问用户)。{REPO_ROOT}/.cache/icenter/
page_ids.jsonpage/*.mdarchitecture_doc_links/ 文件目录.cache-status.json{REPO_ROOT}/omni-doc/specs/{target}/./references/scripts/ 脚本(拉取页面、架构关联、提取前置处理)。./references/scripts/requirement-icenter.txt在 {REPO_ROOT} 下执行(Linux/macOS Bash):
python -m venv .venv
source .venv/bin/activate
pip install -r ./references/scripts/requirement-icenter.txt
在 {REPO_ROOT} 下执行(Windows PowerShell):
python -m venv .venv
.\.venv\Scripts\Activate.ps1
pip install -r .\references\scripts\requirement-icenter.txt
注意:如果你的环境里
python指向的不是目标版本,请改用python3;若在受限网络环境中安装失败,应按组织规范配置 pip 源/代理后再重试。
reverse 命令的关系reverse 负责:
$ARGUMENTS,统一处理 --source icenter、--target、--page-root 等参数;REPO_ROOT 与全局缓存目录;references/stages/*.md,并要求执行时逐条遵守。本 Skill 按以下阶段编排,阶段详细说明见本 Skill 目录下 references/stages/:
{
"fetch_page_ids": {
"confirmed": false
},
"fetch_pages_local": {
"confirmed": false
},
"architecture_linking": {
"confirmed": false
},
"extract_requirements": {
"confirmed": false
},
"extract_scenarios": {
"confirmed": false
},
"extract_system_contexts": {
"confirmed": false
},
"extract_logical_architectures": {
"confirmed": false
}
}
{REPO_ROOT}/.cache/icenter/page_ids.jsonpage_ids.json 批量下载页面 Markdown 到本地缓存目录。{REPO_ROOT}/.cache/icenter/page/*.md{REPO_ROOT}/.cache/icenter/architecture_doc_links/文件目录{REPO_ROOT}/omni-doc/specs/requirements/。.claude/commands/reverse.icenter/stages/04a-extract-knowledge.md{REPO_ROOT}/omni-doc/specs/scenarios/。.claude/commands/reverse.icenter/stages/04a-extract-knowledge.md{REPO_ROOT}/omni-doc/specs/system-contexts/。.claude/commands/reverse.icenter/stages/04b-extract-whole-knowledge.md{REPO_ROOT}/omni-doc/specs/logical-architectures/。.claude/commands/reverse.icenter/stages/04b-extract-whole-knowledge.mdAI Agent 在执行本 Skill 时,必须逐一读取上述阶段文档,并严格按照其中描述的约束与脚本调用方式执行。