技能详情（站内镜像，无评论）
许可证：MIT-0
MIT-0 ·免费使用、修改和重新分发。无需归因。
版本：v0.1.0
统计：⭐ 0 · 536 · 1 current installs · 1 all-time installs
⭐ 0
安装量（当前） 1
🛡 VirusTotal ：可疑 · OpenClaw ：良性
Package：danielfoch/idx-cma-report
安全扫描（ClawHub）
- VirusTotal ：可疑
- OpenClaw ：良性
OpenClaw 评估
The skill is internally consistent: it contains a self‑contained Python script and instructions to assemble CMA inputs, run the local script, and optionally paste generated prompts/data into Google AI Studio; it requests no credentials or installs and shows no signs of exfiltration.
目的
Name/description match the included assets: a local script (scripts/build_cma.py), input schema, valuation guidelines, and publishing checklist. The skill asks the user/agent to obtain listings via an existing IDX MCP/CLI skill — this dependency is coherent for IDX-based CMAs. No unrelated credentials, binaries, or config paths are requested.
说明范围
Runtime instructions stay within the CMA workflow: collect subject and comps (via IDX MCP/CLI), normalize to the provided schema, run the local Python script to produce report, and manually publish to Google AI Studio/Gemini Canvas by pasting the generated prompt and attaching cma_data.json. One minor oddity: the gemini prompt embedded in scripts/build_cma.py appears truncated in the distributed file ('…[truncated]'), which could mean the full…
安装机制
There is no install spec (instruction-only skill with a bundled script). The Python script is pure standard-library code and does not attempt to download or execute external artifacts. No archive downloads, package installs, or third‑party registries are used.
证书
The skill declares no required environment variables, no credentials, and no config paths. Note: the workflow expects an external IDX MCP/CLI skill to fetch listings — that other skill may require MLS/IDX credentials, which is reasonable and external to this package.
持久
The skill does not request persistent presence (always:false) and contains no code to modify agent/system configurations. Autonomous invocation is allowed by platform default but the skill itself does not request elevated or persistent privileges.
综合结论
This package appears to be a straightforward, local CMA generator, but please consider the following before use: 1) Inspect the included scripts/build_cma.py locally and run on sample data in a safe environment — it is pure Python and uses only the standard library, but you should still review code before execution. 2) The skill expects you to use an existing IDX MCP/CLI to fetch listings; that tool will likely require MLS/IDX credentials — ve…
安装（复制给龙虾 AI）
将下方整段复制到龙虾中文库对话中，由龙虾按 SKILL.md 完成安装。
请把本段交给龙虾中文库（龙虾 AI）执行：为本机安装 OpenClaw 技能「IDX CMA Report」。简介：Generate comparative market analysis (CMA) and home valuation reports from IDX …。
请 fetch 以下地址读取 SKILL.md 并按文档完成安装：https://raw.githubusercontent.com/openclaw/skills/refs/heads/main/skills/danielfoch/idx-cma-report/SKILL.md
（来源：yingzhi8.cn 技能库）SKILL.md
---
name: idx-cma-report
description: Generate comparative market analysis (CMA) and home valuation reports from IDX listing data and selected comparable properties. Use when a user wants to pick comps, estimate a market value range, produce seller-facing home evaluation reports, or publish an interactive CMA experience via Google Gemini Canvas or Google AI Studio.
---
# IDX CMA Report
Use this skill to turn subject-property data and IDX comparables into a defensible CMA package with:
- Structured valuation calculations
- A written report for agent/client review
- An interactive handoff prompt for Google Gemini Canvas / Google AI Studio
## Workflow
### 1. Gather Data Through IDX MCP/CLI
Use the IDX MCP/CLI skill already available in the environment to pull:
- Subject property details
- Candidate comparable listings (closed/pending/active based on user preference)
Ask the user which comps to include when the choice is ambiguous. Keep 3 to 8 comps unless the user requests otherwise.
Normalize data to JSON using the schema in `references/cma-input-schema.md`.
### 2. Build CMA Outputs
Run:
```bash
python3 scripts/build_cma.py
--subject subject.json
--comps comps.json
--output-dir cma-output
```
The script produces:
- `cma-output/cma_report.md` (summary report)
- `cma-output/cma_data.json` (calculation payload)
- `cma-output/interactive_local.html` (local interactive view)
- `cma-output/gemini_canvas_prompt.md` (prompt for Google tools)
### 3. Review and Explain Adjustments
Before final delivery:
- Show the comp set used
- Show estimated range and central estimate
- Explain assumptions and major adjustments in plain language
- Flag missing/low-quality fields that weaken confidence
Use `references/valuation-guidelines.md` for adjustment defaults and confidence guidance.
### 4. Publish Interactive Version in Gemini
Use `cma-output/gemini_canvas_prompt.md` as the base prompt. Then:
1. Open [Google AI Studio](https://aistudio.google.com/) or Gemini Canvas.
2. Paste the generated prompt and provide `cma_data.json`.
3. Ask for an interactive CMA web app with:
- Comp table with sorting/filtering
- Map-ready data fields (if lat/lng present)
- Value-range visualization
- Notes panel explaining adjustments
4. Request hosted/shareable output if available in the chosen Google tool.
See `references/gemini-canvas-publish.md` for a copy-ready checklist.
## Safety Rules
- Treat outputs as broker/agent CMA support, not a licensed appraisal.
- Surface data gaps, outliers, or stale comps before presenting a valuation.
- Never invent listing attributes; mark missing values as unknown.
- Keep a clear boundary between factual listing data and model assumptions.
## References
- `references/cma-input-schema.md`
- `references/valuation-guidelines.md`
- `references/gemini-canvas-publish.md`