Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/wanxingai/lightagent/front-tech-mapnpx skills add wanxingai/LightAgent --skill front-tech-mapgit clone --depth 1 https://github.com/wanxingai/LightAgentWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/wanxingai/lightagent/front-tech-map)<a href="https://agentmods.dev/skills/wanxingai/lightagent/front-tech-map"><img src="https://agentmods.dev/badge/skills/wanxingai/lightagent/front-tech-map.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00114 | $0.03992 |
| Opus 5 | $0.00057 | $0.01996 |
| Sonnet 5 | $0.00023 | $0.00798 |
| Haiku 4.5 | $0.00011 | $0.00399 |
Grade A, and why
front-tech-map scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Technology Mapping Skill (v2.1.1)
Overview
全自动生成指定前沿技术领域的技术全景图谱(技术源流 mapping)。通过 7 个阶段的系统性工作流,自动完成环境依赖检查、领域分析、目标发现、师承溯源、剪枝聚类、可视化输出和质量验证。
核心特点:
- 🧠 领域自适应:LLM 在运行时动态分析领域特征并生成定制化搜索策略(替代固定模板)
- 🔄 双向挖掘:正向追踪学术源头 + 逆向溯源明星项目创始团队
- 🔗 Wikidata 师承查询:整合 38 万条博士导师关系数据,大幅减少溯源断点
- ✂️ 强力剪枝 + 连接强度分级:三级连接强度体系,只保留 Tier 1/2 连接
- 📊 溯源质量可衡量:自动统计溯源完成率、验证率、孤儿率
When to Use
当用户需要对一个以技术为核心的前沿赛道进行全景式研究时使用:
- "帮我做一个中性原子量子计算的技术mapping"
- "生成 LLM Agent 框架的技术全景图"
- "核聚变领域的赛道图谱"
不适用:已高度成熟的非技术驱动产业。
输入与输出
输入
用户提供一个技术领域关键词:"中性原子量子计算" / "LLM Agent 框架" / "核聚变磁约束"
输出
-
[Topic]_TechMap.svg— Graphviz dot 生成的 SVG 矢量图谱 -
[Topic]_TechMap_Report.md— 伴随文字报告(节点简介 + 置信度标注 + 溯源统计 + VC 分析结论)
输出路径:[Topic]_TechMap_YYYYMMDD/
数据 Schema
节点类型表、边类型表、置信度规则详见 data_schema.md 连接强度三级分层体系详见 connection_strength.md 可视化节点配色/边样式/时间轴/Legend 规范详见 visual_spec.md VC 分析框架(创始人评估 + 技术路线 + 中外对比 + 可追溯性)详见 vc_framework.md
搜索工具选择规范
在任何需要执行网页搜索的步骤中,按以下流程选择工具:
- 优先使用:yiyanxuangu MCP 工具(get_stock_basic_info、search_securities_code 等)
- 新闻搜索:@skill://万行-news 检索工具
- Web 搜索:workbuddy 的网页搜索工具作为补充
执行工作流
[!CAUTION] 严格按照 Phase 0 → 1 → 2 → 3 → 4 → 5 → 6 的顺序执行。每个 Phase 完成后,在内部检查输出质量,再进入下一个 Phase。
Phase 0: 环境准备与依赖检查 🛠️
目的:检查依赖是否存在,并安装依赖,作为执行所有图谱生成逻辑的前置第一步。
步骤:
- 检查系统依赖:执行
dot -V,检查核心工具 Graphviz 是否可用。注意:如果遇到报错,这是正常现象,说明尚未安装。 作为 Agent 保持冷静,切勿报错中断或询问用户处理,而是直接在内置终端自动执行以下安装命令,按以下顺位尝试直到成功:- macOS:
brew install graphviz - 备选(若无 brew):下载免安装版并添加到 PATH
- macOS:
- 检查 Python 库:执行
pip install graphviz,确保 Pythongraphviz库已安装。
Phase 0 交付物:能够正常调用相应的依赖包和命令行工具(不会抛出 NotFound 的报错)。
Phase 1: 领域适应 & 策略生成 🧠
目的:让 LLM 在运行时分析该技术领域的特征,动态生成适配的搜索策略和溯源路径。
步骤:
- 创建文件夹:创建文件夹
[Topic]_TechMap_YYYYMMDD,用于保存所有中间文件、交付物和最终输出。 - 领域特征分析:基于 LLM 自身知识,分析以下维度并输出
domain_profile:{ "domain": "量子计算-中性原子", "knowledge_carrier": { "论文": 0.8, "专利": 0.3, "开源代码": 0.1, "产品": 0.05 }, "talent_flow_pattern": "大学PhD → 博后 → 教授创业 or 大厂", "known_anchor_persons": ["Mikhail Lukin", "Antoine Browaeys", "..."], "known_anchor_companies": ["QuEra", "Pasqal", "..."], "china_pattern": "海归教授 + 中科大/清华系", "upstream_path_type": "PhD advisor chain (2-3 layers)", "special_relations": ["同实验室师兄弟", "共同导师", "技术迁移(冷原子→中性原子)"], "search_templates": { "company_overseas": "[keyword] startup unicorn funding series", "company_china": "[关键词] 中国 创业公司 融资 A轮 B轮", "academic": "[person] PhD advisor [field] university", "academic_china": "[中文名] 博士 导师 留学 [领域]", "lab_alumni": "[advisor] lab alumni students notable startup" } }- ⚠️ AI/开源型领域:
talent_flow_pattern应为"大厂核心团队 → 独立创业"或"顶级实验室 → 开源项目 → 创业" - ⚠️ 硬科技领域(量子/核聚变/生物):应为
"大学PhD → 博后/教授 → 创业"
- ⚠️ AI/开源型领域:
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 247 lines · 114 tokens per session scan A fb3d3bacbb49
front-tech-map is a skill published in the GitHub repository wanxingai/LightAgent (1,213 stars, last pushed 12d ago), licensed Apache-2.0. It adds 114 tokens to every session and 3,992 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
agent-framework-py-release
Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
python-feature-lifecycle
Guidance for package and feature lifecycle in the Agent Framework Python codebase, including stage meanings, feature-stage decorators, feature enums, and how to move APIs from one stage to the next.
build-and-test
How to build and test .NET projects in the Agent Framework repository. Use this when verifying or testing changes.
pull-requests
Guidance for creating pull requests and handling PR review comments in the Agent Framework repository. Use this when writing a PR description (filling out the PR template) or when responding to and resolving review comments on an existing PR.
python-code-quality
Code quality checks, linting, formatting, and type checking commands for the Agent Framework Python codebase. Use this when running checks, fixing lint errors, or troubleshooting CI failures.