gr-product-dev-ops

gr-product-dev-ops is a skill for Claude Code, Codex from Gingiris-1031/gingiris-skills. It costs 576 tokens per session (5,636 once invoked), scanned A, original, MIT.

A playbook for coordinating product, engineering, and operations teams around user feedback, feature work, and business goals.

In plain words
What is it for?
Use it to plan sprints, run reviews and standups, record feedback, set issue severity, and decide which existing features or bugs to improve.
Why use it?
It provides shared priorities and meeting routines when teams disagree about new features, reported bugs, technical limits, or delivery speed.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to plan sprints, run reviews and standups, record feedback, set issue severity, and decide which existing features or bugs to improve.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gingiris-1031/gingiris-skills/gr-product-dev-ops
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 Gingiris-1031/gingiris-skills --skill gr-product-dev-ops
Clone the repo
git clone --depth 1 https://github.com/Gingiris-1031/gingiris-skills

Made for: Claude Code, Codex.

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 gr-product-dev-ops

README.md
[![agentmods](https://agentmods.dev/badge/skills/gingiris-1031/gingiris-skills/gr-product-dev-ops.svg)](https://agentmods.dev/skills/gingiris-1031/gingiris-skills/gr-product-dev-ops)
Your own site
<a href="https://agentmods.dev/skills/gingiris-1031/gingiris-skills/gr-product-dev-ops"><img src="https://agentmods.dev/badge/skills/gingiris-1031/gingiris-skills/gr-product-dev-ops.svg" alt="Measured on agentmods" height="20"></a>
Per session 576 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,636 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 $0.00576 $0.05636
Opus 5 $0.00288 $0.02818
Sonnet 5 $0.00115 $0.01127
Haiku 4.5 $0.00058 $0.00564

Measured 7d ago against content hash b5683393355b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

gr-product-dev-ops 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 7d 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/gr-product-dev-ops/SKILL.md · 485 lines

How it starts

The opening of the file, as written. The whole thing — 485 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🌍 Language / 语言: 中文 | English | 日本語 | 한국어

📦 Install

clawhub install product-dev-ops-playbook

What you get after installing:

  • Complete 10-day sprint cadence with tri-party alignment checkpoints
  • Issue template + severity auto-escalation rules (3x reported = must-fix)
  • Ready-to-use meeting templates for sprint planning, review, and daily standups

产品研发 × 运营协同 SOP

证据补充:避免“40 分功能”陷阱

本地播客逐字稿中的 AFFiNE 复盘指出:方案被想出来时,产品工作才刚开始。若团队不断追逐新点子,会留下大量只做到 40–60 分、没有验证激活和留存的功能。每次迭代规划必须回答:本期把哪个已有能力从“能用”磨到“可靠”,完成阈值是什么,以及为此明确停止什么。

本 SOP 整合一场真实产品战略会议纪要、用户反馈录入模板、内测用户访谈体系,提炼出一套产品、研发、运营三方协同的通用工作框架。

核心原则: 一切面向商业化服务。一切为赚钱服务。

使用说明: 本文档为通用模板,将所有 [产品名称] / [项目代号] / [系统名称] 替换为对应信息即可直接使用。


一、核心问题诊断:为什么产研运总是协同不好?

1.1 几乎所有成长期产品都会遇到的三个矛盾

矛盾 表现 本质原因
新功能 vs 用户反馈 开发团队总在追新功能,用户反馈的小 Bug 被无限搁置 没有统一的优先级决策机制
研发想做什么 vs 运营要什么 研发觉得运营不懂技术,运营觉得研发不听用户 缺少共同目标
快 vs 稳 产品形态还没稳定就急着增长,技术债越积越多 没有明确的产品阶段判断

1.2 解决思路

来自真实会议洞察: 商业化变现做得好的公司(如 Manus、DeepSeek),COO 或运营负责人直接为商业化服务,产研运三方高度协同。

四大核心机制:

# 机制 说明
1 统一看板 用户反馈和产品需求进同一个池子,用同一套标签体系
2 共同目标 每次迭代有明确的商业化指标(如"注册→付费转化率从 4.5% → 7%")
3 运营有一票否决权 直接伤害用户体验或付费转化的问题,运营可以直接提议推迟发版
4 每个迭代前三方对齐 产研运负责人共同决定做什么、哪些先做、哪些放下一期

二、统一协作载体:看板体系设计

2.1 两层看板结构

来自真实经验: 不要只有每个迭代的小看板,一定要有总看板。所有原始 Issue 先进总池子,再流向下游各个迭代。

层级 名称 内容 负责人
第一层:总需求池 [产品名称] 总 backlog 所有来源的原始 Issue(用户反馈/竞品分析/战略需求) 产品负责人
第二层:迭代看板 [版本号] - [目标描述] 本次迭代确认要做的需求 + 必须修的 Bug 迭代 owner

流向逻辑:

总需求池(所有来源的 Issue)
    ↓ 经过评审,认为可以形成方案
形成方案的需求
    ↓ 经过排期会议决策
进入某个迭代的项目
    ↓ 迭代内开发
发布上线 / 回滚到需求池 / 延到下一期

2.2 Issue 录入模板(通用格式)

关键原则: 运营提的每个 Issue 必须包含可复现信息,否则研发无法 fix。

字段 说明 示例
Issue 标题 简明描述问题 "iOS 版本排盘结果与 Android 不一致"
来源渠道 用户反馈 / 竞品 / 战略 用户反馈
反馈次数 同一问题被反馈几次 3次以上 → 打严重标签
系统/平台 Web / iOS / Android / Self-host iOS
版本号 具体版本 v2.3.1
复现步骤 能复现才能修 1. 打开合盘 2. 选择XX 3. 查看结果
预期行为 用户期望是什么 两版排盘结果应一致
实际行为 当前实际表现 iOS 显示顺序与 Android 相反
截图/录屏 附上证据 [附件]
影响评估 对体验/付费的影响 导致1名用户申请退款
标签 Bug / Feature Request / UX优化 Bug
优先级建议 运营侧判断(高/中/低)

Read the full file on GitHub · 485 lines

Files

What ships with it

3 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. 7d ago First seen · 485 lines · 576 tokens per session scan A b5683393355b

Subscribe to this mod's changes

gr-product-dev-ops is a skill published in the GitHub repository Gingiris-1031/gingiris-skills (77 stars, last pushed 2d ago), licensed MIT. It adds 576 tokens to every session and 5,636 once invoked, about $0.0029 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.