caixu-build-asset-library
Build Personal Asset Library. Use when the user wants to convert parsed materials into asset cards and a queryable library at the asset-build stage, including “建资产库”“生成资产卡”“去重整理版本”. Prefer caixu-skill when the user asks for the full end-to-end mainline or is unsure which stage to run. This skill creates a build_asset_library pipeline run, reads parsed files from caixu-data-mcp, extracts canonical asset cards from trustworthy parsed text, merges likely duplicate versions conservatively, persists assets and merged groups, and completes the pipeline run with library_id. Do not use it for querying, lifecycle judgment, package creation, or submission.
Best use case
caixu-build-asset-library is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Build Personal Asset Library. Use when the user wants to convert parsed materials into asset cards and a queryable library at the asset-build stage, including “建资产库”“生成资产卡”“去重整理版本”. Prefer caixu-skill when the user asks for the full end-to-end mainline or is unsure which stage to run. This skill creates a build_asset_library pipeline run, reads parsed files from caixu-data-mcp, extracts canonical asset cards from trustworthy parsed text, merges likely duplicate versions conservatively, persists assets and merged groups, and completes the pipeline run with library_id. Do not use it for querying, lifecycle judgment, package creation, or submission.
Teams using caixu-build-asset-library should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/caixu-build-asset-library/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How caixu-build-asset-library Compares
| Feature / Agent | caixu-build-asset-library | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Build Personal Asset Library. Use when the user wants to convert parsed materials into asset cards and a queryable library at the asset-build stage, including “建资产库”“生成资产卡”“去重整理版本”. Prefer caixu-skill when the user asks for the full end-to-end mainline or is unsure which stage to run. This skill creates a build_asset_library pipeline run, reads parsed files from caixu-data-mcp, extracts canonical asset cards from trustworthy parsed text, merges likely duplicate versions conservatively, persists assets and merged groups, and completes the pipeline run with library_id. Do not use it for querying, lifecycle judgment, package creation, or submission.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Marketing
Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.
AI Agents for Startups
Explore AI agent skills for startup validation, product research, growth experiments, documentation, and fast execution with small teams.
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
SKILL.md Source
# Build Personal Asset Library 在用户要“建资产库”“生成资产卡”“去重整理版本”时使用这个 skill。 ## Quick flow 1. 读取已解析文件 2. 先做 document triage，再抽取 `asset_card` 3. 保守归并并写入资产库 ## Read next only when needed - 要确认本批次和全库读取策略时，读 [references/workflow.md](references/workflow.md) - 要确认 `BuildAssetLibraryData`、`asset_card` 或归并字段时，读 [references/tool-contracts.md](references/tool-contracts.md) - 要对齐 triage / extraction / merge 的 JSON 形状时，读 [references/output-patterns.md](references/output-patterns.md) - 遇到低置信、`binary_only`、归并不确定时，读 [references/failure-modes.md](references/failure-modes.md) ## Required tools - `caixu-data-mcp.create_pipeline_run` - `caixu-data-mcp.get_parsed_files` - `caixu-data-mcp.append_pipeline_step` - `caixu-data-mcp.upsert_asset_cards` - `caixu-data-mcp.upsert_merged_assets` - `caixu-data-mcp.complete_pipeline_run` ## Required input - `library_id` - `file_ids[]?` ## Workflow 1. 先创建 `build_asset_library` pipeline run，并在关键阶段追加 `append_pipeline_step`。 2. 调用 `get_parsed_files`，优先限定到当前批次的 `file_ids[]`。 3. 跳过没有可信文本的文件；`binary_only` 不能仅靠文件名生成 `asset_card`。 4. 先逐文件做 document triage，判断是否应进入资产库，并给出保守的文档角色提示。 5. 只对 triage 通过的文件，从 parsed text 和 file metadata 抽取 canonical `asset_card`。 6. 先写入 `upsert_asset_cards`，再本地构造保守的 `merged_assets`。 7. 如果存在可确认的归并组，再调用 `upsert_merged_assets`；没有归并组不是失败。 8. 用 `complete_pipeline_run` 结束 build run，并返回 `BuildAssetLibraryData`，必须包含 `library_id`、`asset_cards`、`merged_assets` 和 summary。 ## Guardrails - 不得虚构 holder、issuer、日期或高置信度。 - 高歧义字段返回 `null`，不要输出 `"unknown"`。 - 不确定是否同一材料时，不合并。 - 不得删除原始 `asset_card`。 - 这是单人个人资产库；公示、名单、团队材料只有在能保守映射到 owner 时才允许进入。 - 简历类材料必须视为 `experience`，且不得携带 issuer/date。 - 没有任何可信材料时，返回结构化 `partial` 或 `failed`，不要伪造资产库。 - 如果 `document_triage` 遇到 recoverable model failure，允许 pipeline 保守放行到 `asset_extraction`，但必须留下 warning / audit。
Related Skills
Go-to-Market Strategy Builder
Build a complete GTM plan for product launches, market entries, or expansion plays. Covers positioning, channel strategy, pricing, launch timeline, and success metrics.
Energy Audit — Commercial Building Assessment
Run a full energy audit for commercial or industrial facilities. Identifies waste, models savings, and generates a prioritized retrofit roadmap with ROI timelines.
Data Room Builder
Build a structured virtual data room checklist and folder hierarchy for fundraising, M&A, or due diligence.
Building Permit & Construction Permitting Agent
You are a construction permitting specialist. Help contractors, developers, and property owners navigate the building permit process from application through final inspection.
AI Governance Policy Builder
Build internal AI governance policies from scratch. Covers acceptable use, model selection, data handling, vendor contracts, compliance mapping, and board reporting.
Nightly Build 🌙
An automation skill that runs maintenance tasks while you sleep and delivers a morning briefing.
doppel-block-builder
Place MML blocks in Doppel worlds. Use when the agent wants to submit builds, place blocks on the grid, or understand MML format. Covers integer grid rules and m-block attributes (including type= for textures).
douyin-cover-builder
这是一个面向中文创作者的 OpenClaw Skill，输入主题与人物气质后，会输出可直接用于生图模型的高质量提示词与创意说明。
agentic-mcp-server-builder
Scaffold MCP server projects and baseline tool contract checks. Use for defining tool schemas, generating starter server layouts, and validating MCP-ready structure.
ai-prompt-library-pro
AI 绘画提示词库，包含 1000+ 高质量 Midjourney/Stable Diffusion 提示词模板，覆盖人像、风景、产品、插画等场景。
caixu-query-assets
Search Personal Asset Library. Use when the user wants to search or filter an existing 材序 asset library at the query stage, including “查我有哪些材料”“看哪些可复用”“按类型筛资产”“用自然语言找相关材料”. Prefer caixu-skill when the user asks for the full end-to-end mainline or is unsure which stage to run. This skill normalizes filters into precise retrieval inputs, uses agent tags plus FTS by default, and only calls the optional semantic vector retrieval function when the user explicitly asks for similar or related materials.
caixu-maintain-asset-library
Maintain Personal Asset Library. Use when the user wants to inspect, review, patch, archive, restore, or verify a personal material asset library after initial build, including “看库概览”“修一条资产”“归档这条不该进库的材料”“看待复核队列”. Prefer caixu-skill when the user asks for the full end-to-end mainline or is unsure which stage to run. This skill loads library overviews and review queues from caixu-data-mcp, applies minimal maintenance actions such as patching or archiving one asset at a time, and re-checks query results. Do not use it for fresh ingest, asset extraction, lifecycle judgment, package building, or submission.