requirement-doc-writer

requirement-doc-writer is a skill for Claude Code, Codex from ccoalm/ccl-skills. It costs 163 tokens per session (3,058 once invoked), scanned A, original, Apache-2.0.

A writing process that assembles a product requirements document from requirements that have already been clarified and approved.

In plain words
What is it for?
Use it to produce a readable PRD with confirmed product goals, scope, versions, owners, decisions, and traceable requirements.
Why use it?
It prevents an unfinished discussion or uncertain scope from being presented as a final specification.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the ccl-skills plugin — 33 skills, 4 commands, 7 hooks shipped together

Good fit Use it to produce a readable PRD with confirmed product goals, scope, versions, owners, decisions, and traceable requirements.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ccoalm/ccl-skills/requirement-doc-writer
Install

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.

Any agent
npx skills add ccoalm/ccl-skills --skill requirement-doc-writer
Clone the repo
git clone --depth 1 https://github.com/ccoalm/ccl-skills

Made for: Claude Code, Codex.

Or install ccl-skills, the plugin that ships this one along with the rest of its 33 skills, 4 commands, 7 hooks.

Wrote 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.

agentmods badge for requirement-doc-writer

README.md
[![agentmods](https://agentmods.dev/badge/skills/ccoalm/ccl-skills/requirement-doc-writer/github.svg)](https://agentmods.dev/skills/ccoalm/ccl-skills/requirement-doc-writer)
Your own site
<a href="https://agentmods.dev/skills/ccoalm/ccl-skills/requirement-doc-writer"><img src="https://agentmods.dev/badge/skills/ccoalm/ccl-skills/requirement-doc-writer/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.

agentmods 80×15 button for requirement-doc-writer

Your own site · 80×15
<a href="https://agentmods.dev/skills/ccoalm/ccl-skills/requirement-doc-writer"><img src="https://agentmods.dev/badge/skills/ccoalm/ccl-skills/requirement-doc-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 163 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,058 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00163 $0.03058
Opus 5 $0.00081 $0.01529
Sonnet 5 $0.00033 $0.00612
Haiku 4.5 $0.00016 $0.00306

Measured 4d ago against content hash 7007abab8aa4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

requirement-doc-writer 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 4d 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.

skills/requirement-doc-writer/SKILL.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Requirement Doc Writer

在 lifecycle 判定 PRD Ready 之后,把已关闭的需求组装成一份人能读懂、能评审的 PRD。已有澄清、现状盘点与范围关闭材料、所有需求点已有确定口径时进入本技能。

硬约束(先读,全程适用)

  1. Ready 是门,不是措辞。 只消费带 productversionscopeclosure_table_revisionbehavior_inventory_revisionissued_at 绑定的 lifecycle-issued PRD Ready;绑定不匹配或输入变化时回 lifecycle 重判。任一 P0 行不是 closed、或 Ready 条件任一不满足,不得生成 PRD。用语本身不决定状态,关闭表语义才是门。
  2. PRD Not Ready 时不得输出 PRD 标题、目录、骨架、模板或正文;WIP、讨论稿、会议材料也不得命名为 PRD。此时只输出产品决策视图并保留机器账本引用,不删底层审计字段。
  3. writer 不改事实。 不得修改推导、决策权、决策证据或行状态;不得把 human-decision 字段改成自动确定;不得设置整行 closed
  4. writer 不做技术设计。 不得设计 Agent 技术 schema、prompt/model policy、tool contract 或 eval 实现——分别转 llm-inference-integration、架构/技术栈 owner 与 testing-strategy;writer 只检查命名引用、适用版本、owner 和逐条可追踪性在机器侧是否完整。
  5. 不冒充设计 owner。 UI/用户可见产品的 IA、交互、页面状态和原型由 product-ui-ux-design 产出或审核,writer 只转写已确认内容。

安全 4 问(命中即阻断)

PRD 涉及身份、计费、配额、租户/用户隔离、权限、删除、覆盖时,文档必须有"安全与滥用"小节,逐条写安全 4 问的答案;无命中则显式记"无安全敏感输入",命中后仍记"无命中"为违规。作答前必须先读取 references/security-four-questions.md(问题本体与落点细则 canonical),并在产物中写明所依据的 canonical 文件名 security-four-questions.md(实测:要求一段固定字样的旧写法命中率仅 20.5%,而逐项作答与写明来源文件分别可达 82% / 59%——本仓无法机械校验运行时产物,故只要求可核的实质,不要求不可核的字面戳);凭记忆或转述作答、未写明来源、或命中后仍记"无命中",均为违规。读取不可得时(本会话无文件读取工具 / 文件缺失 / 读取失败)走这条路径,不得声称已读:改写 依据: 不可得(<原因>);按常驻反射尽力作答、本节标 interim 并写出解除方式,缺口连同风险标签交 feature-risk-router,由风险 owner 决定是否接受推迟——接受的是推迟、不是关闭:本节转正式关闭仍须真实读取 canonical 后逐项重答;agent 与需求提出方均不得自行判为已关闭。always-on 常驻反射见 agent-context/session-start.md「设计期安全 4 问」;本节只定义产物落点与交接。

命中后 PRD 只完成需求表达;风险标签/gate 交给 feature-risk-router,研发生命周期交给 product-rd-workflow

产出

生成前读取 references/requirement-closure-contract.md。通过门后组装人读 PRD:先帮读者建立产品认知,再表达已关闭的产品决定、业务规则、边界和验收。 正文先回答三问:

  1. 这是什么产品:区分目标/非目标用户、触发问题/一般愿望、可观察结果/宣传口号,并写出价值、P0 结果和至少一个明确非目标。只替换产品名仍适用于大量无关产品的句子不合格。
  2. 有哪些产品模块或等价结构:模块按稳定产品能力、业务责任或价值流定义,参与端到端状态或结果变化,并说明作用、输入、输出、上游和下游。不得按路由、菜单、页面或弹窗定义模块;页面必须映射到模块,删掉页面名后说不清产品责任或结果的不是模块。非页面型产品可用能力地图、价值流、角色责任或状态流,但必须说明责任边界、关系和端到端运行,不得虚构模块或页面。
  3. 产品如何端到端运行:主链路,以及关键异常、纠错和回退。

Read the full file on GitHub · 131 lines

Files

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.

Changes

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.

  1. 4d ago Changed · +30 tokens per session 7007abab8aa4
  2. 11d ago First seen · 131 lines · 133 tokens per session scan A 7716f0e4324b

Subscribe to this mod's changes

requirement-doc-writer is a skill published in the GitHub repository ccoalm/ccl-skills (6 stars, last pushed today), licensed Apache-2.0. It adds 163 tokens to every session and 3,058 once invoked, about $0.0008 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 2026-08-31.

Related

Other skills, from other repositories

mle-workflow

Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML systems beyond one-off notebooks.

affaan-m/ECC · 44 tokens

autonomous-loops

Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.

affaan-m/ECC · 26 tokens

react-patterns

React 18/19 patterns including hooks discipline, server/client component boundaries, Suspense + error boundaries, form actions, data fetching, state management decision trees, and accessibility-first composition. Use when writing or reviewing React components.

affaan-m/ECC · 49 tokens

article-writing

Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.

affaan-m/ECC · 57 tokens

security-review

Perform a focused security review of pending git changes to identify high-confidence security vulnerabilities with real exploitation potential. Use this skill when the user asks for a security review, security audit, vulnerability scan, or wants to check pending changes on a branch for security issues before merging.…

waybarrios/opencode-power-pack · 64 tokens

huggingface-llm-trainer

Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.

waybarrios/opencode-power-pack · 65 tokens