agentmods.dev

t-prd-publish

t-prd-publish is a skill for Claude Code from timzaak/web-dev-skills. It costs 28 tokens per session (1,933 once invoked), scanned A, original, Apache-2.0.

A documentation step that updates a formal product requirements document after a feature has been built and accepted. A PRD is a lasting record of what a product should do, while draft requirements are temporary working notes.

In plain words
What is it for?
Use it after implementation, testing, and demo acceptance to publish stable product facts, update PRDs and user stories, adjust indexes, and remove the related temporary drafts.
Why use it?
It prevents the long-term documentation from becoming outdated or contradicting the delivered software. It compares the draft, existing documents, user stories, and implementation evidence before revising the formal records.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the t-tools plugin — 29 skills, 31 agents shipped together

not rated 74repo +5 changed 4d ago A scan 28 tokens original Apache-2.0

Good fit Use it after implementation, testing, and demo acceptance to publish stable product facts, update PRDs and user stories, adjust indexes, and remove the related temporary drafts.

Compare 6 skills from other repositories ↓
View source ↗ timzaak/web-dev-skills
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add timzaak/web-dev-skills
Claude Code
/plugin install t-tools

Made for: Claude Code.

Or install t-tools, the plugin that ships this one along with the rest of its 29 skills, 31 agents.

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 t-prd-publish

README.md
[![agentmods](https://agentmods.dev/badge/skills/timzaak/web-dev-skills/t-prd-publish/github.svg)](https://agentmods.dev/skills/timzaak/web-dev-skills/t-prd-publish)
Your own site
<a href="https://agentmods.dev/skills/timzaak/web-dev-skills/t-prd-publish"><img src="https://agentmods.dev/badge/skills/timzaak/web-dev-skills/t-prd-publish/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 t-prd-publish

Your own site · 80×15
<a href="https://agentmods.dev/skills/timzaak/web-dev-skills/t-prd-publish"><img src="https://agentmods.dev/badge/skills/timzaak/web-dev-skills/t-prd-publish.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,933 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.
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 $0.00028 $0.01933
Opus 5 $0.00014 $0.00966
Sonnet 5 $0.00006 $0.00387
Haiku 4.5 $0.00003 $0.00193

Measured 4d ago against content hash eb43ba06dfc4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

t-prd-publish 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/t-prd-publish/SKILL.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PRD 发布总结与正式文档修正

运行时边界：${CLAUDE_PLUGIN_ROOT}/protocols/runtime-boundaries.md（判断产物写入位置或脚本入口与插件默认冲突时读） 需求来源边界：${CLAUDE_PLUGIN_ROOT}/protocols/requirement-source-contract.md（区分草稿与已发布需求来源或处理两者冲突时读） 决策连续性和用户决策暴露：${CLAUDE_PLUGIN_ROOT}/protocols/decision-continuity-contract.md（提问、更新决策账本或处理决策暴露门禁时读）

若草稿、正式 PRD、用户故事或规范之间冲突，以明确澄清为继续条件：停止、说明冲突并等待决策。

目标

在实现、测试和 Demo 验收完成后，基于 .ai/prd/<domain>/<feature>.md 草稿、.ai/user-stories/<domain>/<feature>.md draft 用户故事、现有正式 PRD / 用户故事和实现后证据，先总结"草稿提出了什么、最终交付了什么、现有正式文档缺什么或哪里过期"，再修正增补现有 docs/prd/<domain>/<feature>.md 和 docs/user-stories/**/*.md。没有正式 PRD 或合适用户故事文件时才创建。完成后删除对应 .ai/prd 和 .ai/user-stories 草稿。

输出文件：

  • docs/prd/<domain>/<feature>.md
  • 可能更新：docs/prd/00-index.md、docs/user-stories/**/*.md

核心约束

  • 固定在实现、测试和 Demo 验收完成之后运行；缺少完成证据时停止。
  • 核心动作是先做发布总结并获用户确认，再修正增补现有正式文档；以差异归纳和事实合并为主，只把仍然成立、且属于长期产品语义的内容写入 docs/prd。
  • 正式 PRD 内容聚焦产品语义；端点明细、schema、建表、代码类型和实施进度状态留在设计、任务或实现证据中。
  • 发布范围限定为正式 PRD、正式用户故事、PRD 索引和草稿清理。

Input Contract

必须读取：

  • .ai/prd/<domain>/<feature>.md — 待发布 PRD 草稿
  • .ai/user-stories/<domain>/<feature>.md — 待发布 draft 用户故事（如存在）
  • docs/prd/<domain>/<feature>.md — 已发布正式 PRD（如存在）
  • docs/prd/00-index.md — 正式 PRD 索引（如存在）
  • docs/user-stories/**/*.md — 草稿引用的用户故事
  • .ai/design/<feature>.md — 相关技术设计（如存在）
  • .ai/decision-log/<feature>.md — 跨阶段决策账本（存在时必须读取）
  • .ai/task/<feature>/.state.json — 可选实现阶段背景材料（如存在）
  • ${CLAUDE_PLUGIN_ROOT}/guides/product/prd.md
  • ${CLAUDE_PLUGIN_ROOT}/guides/product/user-story.md
  • ${CLAUDE_PLUGIN_ROOT}/protocols/requirement-source-contract.md
  • ${CLAUDE_PLUGIN_ROOT}/protocols/prd-check-rubric.md

如果找不到草稿，立即失败并提示先执行 /t-prd [feature]。

工作流程

1. 校验参数与定位草稿

  • 检查 [feature] 非空且符合文件名规则（英文、数字、空格、下划线、连字符）
  • 在 .ai/prd/**/*.md 中按文件名精确匹配 [feature]；多个 domain 匹配时停止并让用户选择
  • 目标路径固定为 docs/prd/<domain>/<feature>.md

2. 发布前检查与发布摘要确认

读取草稿、正式 PRD、索引、相关用户故事、设计和验收报告（.ai/task/<feature>/.state.json 如存在，仅用于理解实现阶段背景；发布判断以 PRD 草稿、正式文档、设计、质量报告、Demo 验收和交付证据为准）。检查并形成结论：

Read the full file on GitHub · 105 lines

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 · -50 lines eb43ba06dfc4
  2. 9d ago First seen · 155 lines · 28 tokens per session scan A b28231b186a5

Subscribe to this mod's changes

t-prd-publish is a skill published in the GitHub repository timzaak/web-dev-skills (74 stars, last pushed yesterday), licensed Apache-2.0. It adds 28 tokens to every session and 1,933 once invoked, about $0.0001 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.

PlanningWriting and docsai-codingskills
Related

Other skills, from other repositories

chinese-git-workflow

A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.

jnMetaCode/superpowers-zh · 69 tokens

chinese-commit-conventions

A Chinese-language guide to Conventional Commits, a format for writing consistent Git commit messages, plus related changelog, commit-checking, and commit-helper configuration.

jnMetaCode/superpowers-zh · 65 tokens

chinese-documentation

A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.

jnMetaCode/superpowers-zh · 62 tokens

systematic-debugging

A step-by-step method for finding the underlying cause of technical problems before changing code. It covers reading errors, reproducing failures, checking recent changes, and tracing data across system components.

jnMetaCode/superpowers-zh · 24 tokens

workflow-runner

A procedure for running agency-orchestrator YAML workflows directly inside Claude Code, OpenClaw, or Cursor. The current AI session performs each named role, so no separate API key is needed.

jnMetaCode/superpowers-zh · 61 tokens

build-executor

Govern implementation from an approved execution contract. Invoke when execution-contract.md is approved and the user wants disciplined build work, TDD execution, or guarded batch-by-batch implementation.

MageByte-Zero/spec-superflow · 39 tokens