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 skills add 854771076/oh-my-claude-roles --skill enterprise-prompt-development-specgit clone --depth 1 https://github.com/854771076/oh-my-claude-rolesWrote 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/854771076/oh-my-claude-roles/enterprise-prompt-development-spec)<a href="https://agentmods.dev/skills/854771076/oh-my-claude-roles/enterprise-prompt-development-spec"><img src="https://agentmods.dev/badge/skills/854771076/oh-my-claude-roles/enterprise-prompt-development-spec/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/854771076/oh-my-claude-roles/enterprise-prompt-development-spec"><img src="https://agentmods.dev/badge/skills/854771076/oh-my-claude-roles/enterprise-prompt-development-spec.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00045 | $0.01738 |
| Opus 5 | $0.00023 | $0.00869 |
| Sonnet 5 | $0.00009 | $0.00348 |
| Haiku 4.5 | $0.00005 | $0.00174 |
Grade A, and why
enterprise-prompt-development-spec 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 12d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
企业级AI提示词开发规范
本规范基于2026年大模型应用开发生态、企业级安全合规标准与生产实践制定，与TypeScript+Next.js全栈开发规范、以太坊开发规范、LangChain/LangGraph技术栈完全兼容对齐。所有标注「必须」的条款为强制执行项，特殊场景需AI技术委员会与安全合规委员会双审批后方可调整。
核心原则
- 安全合规优先：所有提示词开发以数据安全、系统安全、合规风控为最高优先级，杜绝提示词注入、越狱、敏感信息泄露、违规内容生成等风险
- 类型安全与标准化：全链路与企业现有TS技术栈对齐，强制结构化输入输出，实现编译时+运行时双校验，杜绝格式断层导致的业务故障
- 可复现可审计：所有提示词必须可稳定复现输出效果，全生命周期变更、调用、测试记录可追溯、可审计
- 业务确定性优先：企业级提示词以输出确定性、稳定性为核心目标，优先保障业务规则落地，而非创意性发散
- 资产化管理：所有提示词为企业核心数字资产，必须纳入统一的版本、权限、运维管理体系，禁止散落在业务代码、个人文档中
首选技术栈规范
严格遵循企业技术栈统一原则，禁止使用未纳入首选清单的工具/框架：
| 开发方向 | 唯一首选技术栈 | 禁止/不推荐替代方案 |
|---|---|---|
| 提示词核心框架 | LangChain.js ChatPromptTemplate | 硬编码字符串模板、自定义模板封装 |
| 输入输出类型校验 | Zod | Yup、Joi、无校验方案 |
| 提示词版本管理 | Git + 语义化版本 | 在线文档、本地文件、无版本管控 |
| 提示词测试与可观测性 | LangSmith | 自定义测试脚本、无测试方案 |
| 提示词安全防护 | Lakera Guard + Zod输出校验 | 无防护方案、自定义过滤规则 |
| 结构化输出 | LangChain.js 结构化输出 + Zod | 纯文本格式约束、无结构化方案 |
| 提示词编排 | LangGraph.js | 线性Chain、自定义流程封装 |
| 环境与配置管理 | Next.js 环境变量 + Vercel 环境隔离 | 硬编码密钥、环境混用 |
| 日志与审计 | Pino + Sentry | console.log、无日志方案 |
标准化编写规范
企业级提示词必须采用固定的8模块结构，顺序固定，无对应内容需标注「无特殊要求」，禁止省略模块：
- 角色定位：必须精准定义模型的身份、专业领域、能力边界，与业务场景强绑定
- 核心目标：必须用1-2句话明确唯一核心任务，禁止多目标混杂，明确交付标准
- 执行规则：必须分点列出可落地、可校验的执行步骤，明确顺序、判断逻辑、处理规则
- 输入规范：必须明确所有输入变量的含义、类型、约束，与Zod Schema、TS类型完全一致
- 输出规范：必须明确输出格式、结构、字段要求，与Zod Schema完全一致，明确异常场景格式
- 约束与禁忌：必须明确绝对禁止的行为、内容、输出，包含合规、安全、公司规范要求
- 异常处理规则：必须明确所有异常场景的标准处理方式，输出固定格式
- 参考示例（Few-Shot）：复杂场景必须提供2-3组高质量输入-输出示例，覆盖正常、边界、异常场景
编写强制红线
- 禁止在提示词中硬编码敏感信息，所有敏感信息必须通过环境变量管理
- 禁止使用模糊、模棱两可、主观化的描述，所有规则必须可落地、可校验、可复现
- 禁止在系统提示词中允许模型突破约束，禁止出现「除非用户要求」「特殊情况可例外」等表述
- 禁止无边界的泛化任务，必须明确模型的能力边界，禁止允许模型执行未授权的操作
- 禁止在提示词中要求模型编造、虚构信息，RAG场景必须明确要求模型仅使用提供的上下文信息
- 禁止使用纯自然语言约束输出格式，必须配合Zod Schema实现结构化输出强制约束
What ships with it
1 file 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.
- 12d ago First seen · 89 lines · 45 tokens per session scan A 100c66cf4afc
enterprise-prompt-development-spec is a skill published in the GitHub repository 854771076/oh-my-claude-roles (22 stars, last pushed 5mo ago), licensed MIT. It adds 45 tokens to every session and 1,738 once invoked, about $0.0002 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
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
prompt-optimization
Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…
enhance-prompt
Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.
prompt-engineer
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…
seedance-vocab-en
This skill should be used when an English Seedance 2.0 prompt needs clearer production wording, less generic prose, or precise vocabulary for camera, lighting, motion, VFX, audio, and constraints. Route blocked prompts through seedance-filter for context and boundary review.
ideogram4
Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…