SKILLEMALL.ai
GitHub ↗ RU Sign in

CD sa-pro-workbench

【解决方案架构师/售前顾问超级工作台 / Solution Architect & Presales Consultant Super Workbench】 —— 面向解决方案架构师、售前顾问、方案专家、企业架构师的全栈自动化技能。 一人一 Skill，替代方案团队 80% 重复劳动。 ■ 核心定位：面向信息化/数字化/智能化项目，覆盖从"收到客户材料"到"交付投标材料包"的 完整售前-方案-设计-投标链路。无论你被叫做什么——解决方案架构师、售前工程师、方案专家、 技术顾问、咨询顾问、企业架构师、IT规划师——这个 Skill 都能胜任你的核心工作。 ■ 方法论驱动：内置 C4 模型（系统上下文图→容器图→组件图）、4+1 视图（逻辑/开发/进程/ 物理/场景）、TOGAF 4A 企业架构（业务→应用→数据→技术）、SPIN 需求挖掘法、ADR 架构 决策记录模板、DFD 数据流图多层级（Level 0-3）、BPMN 轻量版、NFR 驱动的设计原则。 ■ 图表工场（13 类可编辑 draw.io 源文件）：系统上下文图 C1、容器图 C2、技术架构图、 业务流程图（泳道+BPMN）、数据流图 DFD（Level 0-2 多层级）、功能架构图、系统集成图、 部署架构图（CIDR/安全组/实例规格）、数据架构图（五层）、业务架构图（能力地图）、 网络拓扑图（Hub-Spoke）、实施路线图/甘特图、AI/智能化方案图。 所有图表输出 .drawio 可编辑源文件 + .png 预览图，符合专业 Diagram Style Guide 标准。 ■ PPT 工场：高管简报（5-8页）、方案汇报（12-18页）、技术深潜（15-25页）、投标述标 （15-20页）、PoC 汇报（8-12页）。内置 6 套专业配色方案（企业沉稳/科技深蓝/专业蓝灰/ 高端深色/清新商务/科技紫），一套排版规范，三明治结构，AI痕迹消除。 ■ 文档工场：框架方案 HLD（12 章标准结构）、蓝图/初步设计 LLD（10 章标准结构）、 SOW 工作说明书（8 章标准结构）、RFP/RFI 逐条响应、竞品分析报告、会议纪要、客户沟通 预判与应答策略手册、投标材料包一键生成。统一命名规范、Word 格式标准、图表引用规范。 ■ 核心交付物矩阵：30+ 标准交付物，分核心必备/支撑交付/运营交付/售前特有四大类。 每个交付物明确阶段、目的、更新节奏。 ■ 角色覆盖（任一角色名均可触发）：解决方案架构师、售前工程师、售前、售前方案、 方案架构师、解决方案专家、SA、技术顾问、咨询顾问、IT 规划师、企业架构师、信息化顾问、 数字化顾问、投标工程师、产品方案经理。 ■ 英文角色覆盖（任一均可触发）：Solution Architect, Presales, Pre-sales, SA, Presales SA, Presales Engineer, Solution Consultant, Technical Consultant, Enterprise Architect, IT Architect, Technology Architect, Proposal Manager, Bid Manager, Technical Proposal Writer, RFP Specialist。 ■ 工作场景覆盖（任一场景提到即触发）：做方案、写方案、出方案、方案设计、技术方案、 框架方案、蓝图设计、初步设计、详细设计、概要设计、高阶设计、HLD、LLD、画架构图、 出架构图、做架构、架构设计、画流程图、出PPT、做汇报PPT、述标PPT、投标PPT、写SOW、 出标书、写标书、投标方案、RFP响应、RFI响应、写会议纪要、竞品分析、需求分析、挖掘需求、 PoC方案、TCO分析、ROI分析、技术选型、ADR决策、评审方案、方案汇报、客户交流准备。 ■ 图表场景覆盖：架构图、技术架构、业务架构、数据架构、应用架构、部署架构、系统集成、 网络拓扑、业务流程图、流程图、数据流图、DFD、功能架构图、组织架构图、路线图、甘特图、 ER图、实体关系图、C4图、上下文图、容器图、组件图、集成图、拓扑图、drawio、draw.io。 ■ 行业/领域覆盖（不限于）：政企信息化、企业数字化、智能制造、智慧城市、金融科技、 智慧医疗、智慧教育、新零售、供应链、能源、交通、运营商、军工、AI应用、大数据平台、 云原生、微服务、DevOps、物联网、低代码、中台架构。 ■ 一句话定位：给 Claude 装上解决方案架构师的大脑， 从 0 到 1 完成专业级售前方案全流程交付。

ClawHub Agent Skills author: yinjianheng v1.2.0 MIT-0 15 files body ≈ 11 280 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

【解决方案架构师/售前顾问超级工作台 / Solution Architect & Presales Consultant Super Workbench】 —— 面向解决方案架构师、售前顾问、方案专家、企业架构师的全栈自动化技能。 一人一 Skill，替代方案团队 80% 重复劳动。 ■…

As a process D 40/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureProcurementtype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
C
72/100
safety, quality, tests
Safety 60%
99
Quality 40%
31
Run on models
none yet
Process rating
D
40/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. Shorten the description to 1024 characters.
  3. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 1

✓ No critical or high findings

Medium and low: 1
  • low Risky intent intent-offensive-security SKILL.md:1013
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - **红队 (Red Teaming)**：对抗样本、越狱尝试、数据泄露测试，纳入上线前评估

Files scanned: 15. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • error description-long description is 1943 chars, limit 1024
  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning body-long SKILL.md body ≈ 11280 tokens (recommended < 5000); move details to references/
  • note description-budget description takes 1943 of the ~15000-char shared budget for all skills
  • note frontmatter-key unknown frontmatter key "contact"
  • note frontmatter-key unknown frontmatter key "language"

Process rating: all ten parameters 40/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 4 mutating operations with no state check
  • 40Execution cost. Instruction body is 11280 tokens: crowds the task out of the window
  • 60Tools and files. Uses tools (python, node) that frontmatter does not declare
  • 100Steps. 161 steps
  • 100Consistency. Name and required fields are in place
  • low 31 top-level sections: this looks like several domains in one skill
  • low The skill ranks results itself: that belongs to the system behind the tool, not the model

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +4Description does not say when NOT to use the skill (false activations)
  • +3Description length 1943: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -41 reference files, but SKILL.md never points to them: the model will not open them
  • +2Single-language instructions
  • +5Description quotes 2 example trigger phrases
  • +4Structure: 120 headings
  • +3Step-by-step instructions: 161 items
  • +4Has examples (23 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 31.

External checks

ClawHub: clean
This is a disclosed solution-architecture drafting workbench; its broad triggers and document-generation behavior are expected for its purpose, with no evidence of exfiltration, credential access, destructive actions, or hidden execution.
LLM: benign (high) · VirusTotal: · 10 Jul 2026