Technical Proposal Expert Agent Skill
Drafts and refines standardized Chinese technical proposals, bidding documents, and system design specifications with rigorous compliance…
- Context cost
- 124.9k tokensestimated from the bundle, loaded when it triggers
- Bundle
- 79 files · 521.3 kB3 scripts among them — read before you run
- Licence
- not declarednone named by its author
- Last change
- —no release on file
- Servers it uses
- Noneruns standalone
What it does
MUST be used when writing, drafting, or polishing Chinese formal documents. Use when the user asks for 技术标书, 投标, 招标, 技术方案, 投标书, 方案设计报告, 系统设计说明, 测试报告, 测试总结, 工作周报, 周总结, or unspecified 公文/方案/文档. Also use when the document type is unclear and a writing scene must be chosen first.
Installed, it changes the agent in these ways.
What this skill changes about the agent has not been set out here as a list. Its SKILL.md, shown below, says it in the author’s own words.
And these are the jobs people reach for it for.
The skill itself
A skill is instructions the model reads, so you can see what you are getting: below is the start of its SKILL.md. The front matter loads with every session, the body loads when the skill triggers, and the whole file comes with the install.
Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.
What it costs in context
Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.
124.9k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Heavy. Teams tend to install this one per project rather than globally, and load it only when the job comes up.
A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.
Before and after
The same question, put to the same model twice: once as it comes, and once with these instructions loaded.
No worked example has been published for this skill yet.
The procedure it runs
The procedure has not been set out here step by step. It is in the body of its SKILL.md: the start of it is shown above, and the whole file comes with the install.
These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.
Servers it uses
None. This skill calls no MCP servers at all.
Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.
Its SKILL.md does not declare which tools it asks the agent for, so what it touches is whatever the instructions themselves ask for — read them before you install it.
This SKILL.md carries no allowed-tools line, so neither is declared. A skill grants no permissions of its own — it can only ask for tools your client already has.
What it will not do
Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.
What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.
What is in the bundle
79 files, 521.3 kB on disk. Mostly text — the instructions the model reads — with 3 scripts in it that your client would run only if the instructions tell it to. 5 files of its source are not in the download — listed after these, with why.
- SKILL.md11.3 kB
- README.md8.3 kB
- examples/浅vs深-高可用功能点.md2.4 kB
- knowledge/00-来源登记.md19.4 kB
- knowledge/README.md2.3 kB
- references/design-report.md3.8 kB
- references/general.md1.1 kB
- references/technical-proposal.md4.0 kB
- references/test-report.md1.0 kB
- references/weekly-report.md0.9 kB
- scripts/index_materials.py7.0 kB
- scripts/split_gjb_templates.py7.7 kB
- scripts/test_index_materials.py6.9 kB
- 素材库/README.md1.0 kB
- knowledge/AI与视频分析/README.md0.2 kB
- knowledge/云原生与开源组件/Apache-Kafka设计要点.md9.1 kB
- knowledge/云原生与开源组件/Istio服务网格.md3.7 kB
- knowledge/云原生与开源组件/Kubernetes架构与组件.md7.5 kB
- knowledge/云原生与开源组件/README.md0.4 kB
- knowledge/云原生与开源组件/Redis-Cluster-分片与故障转移.md10.3 kB
- knowledge/云原生与开源组件/Redis-Sentinel-主从哨兵.md5.6 kB
- knowledge/低代码与BPM/README.md0.2 kB
- knowledge/信创与国产化/README.md0.2 kB
- knowledge/信创与国产化/信创适配改造.md4.3 kB
- knowledge/合规与标准/README.md0.3 kB
- knowledge/合规与标准/标准引用核对表-模板.md3.2 kB
- knowledge/大数据/01-Apache-Flink-流计算核心机制.md11.6 kB
- knowledge/大数据/02-Apache-Flink-Stateful-Functions.md9.1 kB
- knowledge/大数据/03-Spark-Structured-Streaming-流批一体.md9.8 kB
- knowledge/大数据/04-Kafka-Streams-客户端流处理.md11.2 kB
- knowledge/大数据/05-ClickHouse-OLAP-列式数据库.md9.5 kB
- knowledge/大数据/06-Apache-Doris-OLAP-实时分析.md8.8 kB
- knowledge/大数据/07-Apache-Iceberg-数据湖表格式.md10.9 kB
- knowledge/大数据/08-Apache-Airflow-工作流调度.md8.5 kB
- knowledge/大数据/README.md0.2 kB
- knowledge/安全与等保/README.md0.2 kB
- knowledge/安全与等保/等保2.0与合规设计.md4.7 kB
- knowledge/微服务与中台/CQRS读写分离-Fowler.md5.2 kB
- knowledge/微服务与中台/README.md0.2 kB
- knowledge/微服务与中台/微服务-定义与九大特征-Fowler.md7.2 kB
- knowledge/微服务与中台/微服务架构权衡.md5.5 kB
- knowledge/微服务与中台/微服务模式-模式库索引.md7.3 kB
- knowledge/数据治理与交换共享/README.md0.2 kB
- knowledge/数据治理与交换共享/数据治理与交换共享.md4.2 kB
- knowledge/文档模板/01-软件开发计划-SDP.md13.3 kB
- knowledge/文档模板/02-软件安装计划-SIP.md8.4 kB
- knowledge/文档模板/03-软件移交计划-STrP.md8.0 kB
- knowledge/文档模板/04-软件测试计划-STP.md10.8 kB
- knowledge/文档模板/05-运行方案说明-OCD.md9.1 kB
- knowledge/文档模板/06-系统·子系统规格说明-SSS.md17.9 kB
- knowledge/文档模板/07-接口需求规格说明-IRS.md9.9 kB
- knowledge/文档模板/08-系统·子系统设计说明-SSDD.md13.1 kB
- knowledge/文档模板/09-接口设计说明-IDD.md7.5 kB
- knowledge/文档模板/10-软件需求规格说明-SRS.md17.3 kB
- knowledge/文档模板/11-软件设计说明-SDD.md15.0 kB
- knowledge/文档模板/12-数据库设计说明-DBDD.md12.8 kB
- knowledge/文档模板/13-软件测试说明-STD.md10.1 kB
- knowledge/文档模板/14-软件测试报告-STR.md5.5 kB
- knowledge/文档模板/15-软件产品规格说明-SPS.md8.2 kB
- knowledge/文档模板/16-软件版本说明-SVD.md4.8 kB
- knowledge/文档模板/17-软件用户手册-SUM.md9.4 kB
- knowledge/文档模板/18-计算机编程手册-CPM.md4.9 kB
- knowledge/文档模板/19-固件保障手册-FSM.md5.2 kB
- knowledge/文档模板/20-软件研制总结报告-SDSR.md9.7 kB
- knowledge/文档模板/README.md0.5 kB
- knowledge/测试与质量/README.md0.2 kB
- knowledge/测试与质量/测试金字塔-Fowler.md5.2 kB
- knowledge/物联网与感知/01-MQTT-5-协议机制.md9.7 kB
- knowledge/物联网与感知/02-EMQX-Broker-集群架构.md8.5 kB
- knowledge/物联网与感知/03-InfluxDB-时序数据模型.md9.0 kB
- knowledge/物联网与感知/04-TDengine-时序数据库架构.md10.4 kB
- knowledge/物联网与感知/05-KubeEdge-边缘计算框架.md9.1 kB
- knowledge/物联网与感知/06-OpenYurt-边缘计算平台.md8.4 kB
- knowledge/物联网与感知/07-AWS-IoT-Device-Shadow-设备影子.md9.8 kB
- knowledge/物联网与感知/08-阿里云-物模型-TSL.md9.5 kB
- knowledge/物联网与感知/README.md0.2 kB
- knowledge/移动端/README.md0.2 kB
- knowledge/高可用与容灾/README.md0.2 kB
- knowledge/高可用与容灾/高可用集群与故障转移.md3.1 kB
Not in the download
Not carried is a type a skill download does not hold. Take them from its source.
- .gitignorenot carried
- 文档示例/.DS_Storenot carried
- 文档示例/01 计划阶段/.DS_Storenot carried
- 文档示例/05 测试阶段/.DS_Storenot carried
- 文档示例/06 验收阶段/.DS_Storenot carried
A skill installs nothing and depends on nothing: it is a folder your client reads. This one carries 3 scripts beside the text, so the download is 79 files — not the whole of its source: 5 files are left out. They are listed under the files, with why.
Install
Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.
# Technical Proposal Expert · 124.9k tokens when loaded · macOS, Linux
mkdir -p .claude/skills && t=$(mktemp -d) &&
curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/technical-proposal-expert/bundle.tar.gz &&
tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/technical-proposal-expert" ] &&
{ [ ! -e .claude/skills/technical-proposal-expert ] || { mv .claude/skills/technical-proposal-expert "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } &&
mv "$t/technical-proposal-expert" .claude/skills/ && echo "Installed .claude/skills/technical-proposal-expert"npx mcprush@latest skill add yanhaoluo0/technical-proposal-expertWindows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither. Writes to .claude/skills/technical-proposal-expert/ in the current project. For every project instead, run mkdir -p ~/.claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/technical-proposal-expert/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/technical-proposal-expert" ] && { [ ! -e ~/.claude/skills/technical-proposal-expert ] || { mv ~/.claude/skills/technical-proposal-expert "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/technical-proposal-expert" ~/.claude/skills/ && echo "Installed ~/.claude/skills/technical-proposal-expert" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/technical-proposal-expert/ only after the download succeeds, so files left there by another skill of the same name, or by an older release, do not mix in. A copy already there is moved aside, not deleted, and the line prints where. Not in this download: 5 files of its source (the full list, and why). Take them from its source.
Which clients pick it up on their own
A skill is a folder of text. Most of these read a skills folder and pick it up without being told; the rest take the same folder another way — an upload in the app, a parameter on an API call — and then choose it by its description just the same.
Versions
Its author publishes no version number, so there is nothing here to pin to: what you install is the folder as it stands today. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.
Nothing to pin to: this skill carries no version number of its own. What you install is what the folder holds on the day you install it.
Reviews
Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.
A review is tied to an account so it can be answered, edited and taken down by the person who wrote it.
Sign inAnybody with an account, one review each. It carries the version that was current when you wrote it, and the publisher may reply once.