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 jaylpp/pandajay-skills --skill req-to-dev-docgit clone --depth 1 https://github.com/jaylpp/pandajay-skillsWrote 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/jaylpp/pandajay-skills/req-to-dev-doc)<a href="https://agentmods.dev/skills/jaylpp/pandajay-skills/req-to-dev-doc"><img src="https://agentmods.dev/badge/skills/jaylpp/pandajay-skills/req-to-dev-doc/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/jaylpp/pandajay-skills/req-to-dev-doc"><img src="https://agentmods.dev/badge/skills/jaylpp/pandajay-skills/req-to-dev-doc.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 | $0.00071 | $0.00995 |
| Opus 5 | $0.00036 | $0.00498 |
| Sonnet 5 | $0.00014 | $0.00199 |
| Haiku 4.5 | $0.00007 | $0.00100 |
Grade A, and why
req-to-dev-doc 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 10d 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.
What it actually says
需求转开发文档
工作流程
-
读取
references/module-structure.md：- 判断最可能涉及的模块（允许不完全确定）
- 提取该模块的【模块依赖/变更风险/注意点（长期边界）】作为约束与风险来源
-
读取
references/impact_rules.md：- 先扫描 L0 必跑规则，明确“命中哪些规则”（必须显式输出规则编号）
- 再按第 1 步的模块检索 L1 规则补全“必查落点、回归对象、风险与待确认项”
- 若模块不明确：先按“通用能力”生成卡片，并在【待确认项】列出需要确认的模块/入口；不要阻塞输出
-
按模板输出任务卡片：
- 重点把命中规则转成【影响范围/风险项/验收标准】里的具体“落点”和“回归清单”
- 只写可执行内容，不写背景长文
若需求涉及模块不明确，先询问用户确认模块范围，再生成文档。
输出模板
每个需求输出一张卡片，严格按以下结构：
# 功能名称：xxxx
## 用户故事
作为[角色]，我希望[行为]，从而[目的]。
（仅一句话，保持简短、聚焦价值。）
## 功能描述
- 用项目符号简明列出该模块需要实现的核心功能点（以"支持…"、"允许…"、"点击…"等动词开头）。
- 避免描述背景或实现方式，只关注"系统需要实现的行为"。
## 影响范围
> 必须是“本次改动需要同步检查/修改的落点”，不要泛泛写模块名
- 涉及模块：xxx（不确定可写“候选模块：A/B”，并在待确认项里问）
- 涉及对象/字段：xxx
- 必查入口/链路：按命中规则列出（例如：编辑态/详情态/列表态/搜索筛选/导入导出/打印报表/通用CRUD链路等）
- 涉及接口：xxx（如涉及通用CRUD必须标注“通用/对象扩展点”）
## 注意点 / 风险项
> 必须同时满足：
> 1) 引用模块地图的“变更风险/注意点（长期边界）”
> 2) 引用 Impact Rules 命中规则对应的风险
- 命中规则：L0-?, L1-?（必须写）
- 风险项：…
## 待确认项
- 列出尚不确定、需进一步确认或可能变更的要点。
- 可包含设计、接口、性能或交互类问题。
- 如果没有，则为空。
## 验收标准
- ✅ 正向验证：描述成功操作后应出现的正确结果。
- ❌ 负向验证：描述错误或异常场景下应出现的提示或限制。
- 每条标准前加符号（✅/❌），确保测试可读性。
- 语言保持通俗、简洁明确，避免歧义，用"→"描述操作到结果的逻辑。
规则
- 严格使用 Markdown 格式，不写多余的背景或叙述
- 若输入包含多个模块，分模块分别输出多张卡片
- 模块地图用于“模块级提醒与边界”；Impact Rules 用于“本次改动必查落点”
- 若模块地图无记录：标注“该模块暂无平台规范记录，以下为通用建议”
参考资料
references/module-structure.md：平台完整模块结构，包含各模块的实体、核心功能、模块依赖、变更风险和注意点references/impact_rules.md：影响范围与风险项规则库（L0 必跑规则 / L1 模块规则 / L2 案例库），用于补全影响范围、风险项、待确认项、验收标准和回归清单
What ships with it
2 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.
- 10d ago First seen · 77 lines · 71 tokens per session scan A 981c8fca57e5
req-to-dev-doc is a skill published in the GitHub repository jaylpp/pandajay-skills (11 stars, last pushed 3mo ago), licensed MIT. It adds 71 tokens to every session and 995 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…