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 kelegele/oh-my-pm --skill retrospectivegit clone --depth 1 https://github.com/kelegele/oh-my-pmWrote 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/kelegele/oh-my-pm/retrospective)<a href="https://agentmods.dev/skills/kelegele/oh-my-pm/retrospective"><img src="https://agentmods.dev/badge/skills/kelegele/oh-my-pm/retrospective/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/kelegele/oh-my-pm/retrospective"><img src="https://agentmods.dev/badge/skills/kelegele/oh-my-pm/retrospective.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 | $0.00186 | $0.04426 |
| Opus 5 | $0.00093 | $0.02213 |
| Sonnet 5 | $0.00037 | $0.00885 |
| Haiku 4.5 | $0.00019 | $0.00443 |
Grade A, and why
retrospective 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 11d 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 — 372 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Retrospective
喂数据复盘 → 直接产出下轮迭代计划。
What This Skill Does
一条验证线闭环：用户贴入指标/上线结果后，对照 PRD 目标做差距分析，产出复盘结论（达成情况、定性反馈、意外发现），然后基于复盘结论滚动产出下轮迭代计划——待办分类、RICE 排序、容量分配、跟踪指标，并把新洞察路由回感知与设计层，完成反馈闭环。
Data Policy (诚实定位)
本 skill 不接入任何实时数据源——不读数据库、不调埋点平台、不抓监控后台。所有指标数据由用户提供：你贴数据，我做分析。
- 有数据时：走完整主线——差距分析 → 复盘结论 → 迭代计划。
- 无数据时：不编造数字，只产出复盘框架（该收集什么数据、基线怎么定、按什么方法分析），待数据到位后再补正式复盘与迭代计划。
When to Use
Activate this skill when:
- 用户贴了上线后的指标数据，想评估发布或功能的结果
- Phrases like "表现如何"、"衡量影响"、"上线复盘"、"效果分析"、"did it work"
- 对照 PRD 成功指标检查目标达成情况
- 规划下一个冲刺/迭代，或问 "what should we build next"
- 需要平衡新功能、缺陷和技术债务，分配团队容量
- 回顾上一轮迭代哪些有效、哪些无效
How It Works
- 确认数据前提 - 有用户提供的指标数据走复盘主线；无数据则只产出复盘框架（收集清单 + 分析方法）
- 完整度检查 - 按证据纪律输出信息完整度清单，经用户确认
- 对照 PRD 目标 - 逐项差距分析（target vs actual vs baseline）
- 提炼复盘结论 - What worked / what didn't / surprises，标记需要验证的假设
- 滚动迭代计划 - 待办分类（bug/优化/新功能/技术债）→ RICE 排序 → 容量分配
- 闭环路由 - 新洞察路由回感知层与设计层（见 Context Integration）
Input Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
metrics_data |
object | Yes* | 用户提供的上线后指标数据（*无数据时只产出复盘框架） |
release_ref |
string | Yes | Reference to release being analyzed |
prd_ref |
string | Yes | Reference to PRD with success metrics |
period |
string | No | Analysis period (default: "7 days post-launch") |
capacity |
object | No | Team capacity constraints (e.g., {"points": 20, "weeks": 2}) |
debt_ratio |
number | No | Percentage allocation for tech debt (default: 20%) |
Evidence Discipline (证据纪律)
- 缺失信息标记【待确认】：任何无法从输入或上下文获得的信息，标记为【待确认】，不得脑补填默认值。
- 证据追溯【未验证】：用户需求/市场断言必须追问证据来源；无证据的标记为【未验证】并注明所需验证方式。
- 完整度检查门：正式输出交付物前，先输出信息完整度清单（已确认 ✅ / 待确认 ⚠️ / 未验证 ❓），经用户确认后才生成正文。
- 可追溯：正式输出中的关键结论必须能追溯到以下来源之一：已确认的用户输入、引用的证据（含 URL）、或用户的显式决策；无法追溯的结论视为脑补，删除或改标【待确认】。
Output Structure
The skill generates four outputs:
docs/product/.ompm/impact-analysis.json- 结构化复盘结果（契约文件名，不变）docs/product/.ompm/iteration-plan.json- 结构化迭代计划（契约文件名，不变）- 复盘 + 迭代计划报告 (
docs/product/retrospectives/[release]-[date].md) - 完整人类可读交付物 - A/B 验证方案 - 针对复盘中待验证假设的实验设计（无待验证假设时可省略）
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.
- 11d ago First seen · 372 lines · 186 tokens per session scan A 286c7caa4812
retrospective is a skill published in the GitHub repository kelegele/oh-my-pm (4 stars, last pushed 1mo ago), licensed MIT. It adds 186 tokens to every session and 4,426 once invoked, about $0.0009 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.
Other skills, from other repositories
create-site
Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…
configure-env-variables
Configures environment variables for Power Pages site settings to support ALM across environments. Creates environment variable definitions in Dataverse, guides the user through linking site settings to those variables via the Power Pages Management app, adds the variables to the solution, and generates a…
deploy-site
Deploys an existing Power Pages code site to a Power Pages environment using PAC CLI. Handles tooling verification, authentication, environment confirmation, building, and uploading. Use when the user wants to deploy, upload, or publish their code site.
top-design
Create award-winning, immersive web experiences at the level of Awwwards-featured agencies. Use when the user mentions "Awwwards quality", "make my site stunning", "scroll animations", "parallax storytelling", "cinematic web design", "portfolio site", or "brand experience". Also trigger when elevating a standard…
create-business
Guided journey from raw idea to a validated, positioned, priced business with a chosen beachhead. Orchestrates ten skills phase by phase - jobs-to-be-done, mom-test, design-sprint, lean-startup, good-strategy-bad-strategy, blue-ocean-strategy, obviously-awesome, hundred-million-offers, monetizing-innovation…
clean-code
Write readable, maintainable code through disciplined naming, small functions, and clean error handling. Use when the user mentions "clean up this code", "this function is too long", "code smells", "naming conventions", "boy scout rule", "single responsibility", or "unit test quality". Also trigger when reviewing a…