一键在 Manus 中运行任何 Skill

pmstack-onboarding

星标8

分支1

更新时间2026年5月5日 20:30

An interactive 9-step tutorial that walks a new user through every pmstack capability using a realistic AI-code-review scenario. Includes Anthropic's vibe-test (read raw transcripts before formalizing an eval) and transcript-review (diagnose failed trials as model / grader / task errors) rituals. Works in claude.ai web, desktop, and mobile (no terminal needed). Trigger when the user says "I just installed pmstack," "how do I use this," "tutorial," "walk me through pmstack," "getting started," or "show me what pmstack does."

安装

用 Codex 或 Claude 帮你安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。

在 Manus 中运行

来源

RyanAlberts

RyanAlberts/pmstack

打开 GitHub 仓库查看创作者相关仓库

下载

在 Manus 中运行

相关职业SOC

基于 SOC 职业分类

项目管理专家商业与金融运营类职业·SOC 13-1082

SKILL.md

readonly

同仓库更多 Skills

同仓库

pmstack-eval-report

RyanAlberts/pmstack

Turns a /run-eval result into a single self-contained, shareable HTML report — a verdict hero (pass/conditional/fail), the per-case table with PASS/FAIL color-coding, and the metrics table — that a PM can paste into Slack, a launch doc, LinkedIn, or a PR. The report carries a "run your own eval" backlink to pmstack. Use when the user says "make this eval shareable," "turn my eval run into a report," "export the eval results," "an HTML report of my eval," "share my eval results," or has a /run-eval output directory and wants a presentable artifact. Renders real run data only (from summary.md) — never invents numbers. Runs bin/eval-report.py on a run directory. Output: report.html next to the run's summary.md.

2026-06-248

pmstack-eval-grade

RyanAlberts/pmstack

Grades an eval the user already has against Anthropic's eval-design principles and returns an Eval Report Card — a letter grade A–F, the failures that earned it with the offending line, the single highest-leverage fix, and a shareable verdict card. It is the inverse of /eval (which writes a suite); this checks whether a suite is any good. Use when the user says "grade my eval," "is my eval any good," "review my eval suite," "roast my eval," "what's wrong with this eval," "did I write this eval right," pastes an eval YAML or rubric and asks for feedback, or wants to check an eval against the Anthropic framework before trusting it. Catches grader leakage, missing negative cases, no target, vibes-as-metric, and uncalibrated LLM-as-judge. Accepts a file path, a pasted/attached eval, or a plain-English success metric. Output: outputs/eval-grade-<feature>-<date>.md.

2026-06-208

pmstack-voc

RyanAlberts/pmstack

Synthesize many raw customer signals (support tickets, interview snippets, churn reasons, sales notes, NPS verbatims, app reviews) into a small set of ranked, PRD-ready problems. Use when a PM pastes or attaches a pile of feedback and asks "what's the real problem / what should we build first / what are the themes", when there are too many signals to read one by one, or when someone needs to turn voice-of-customer data into prioritized problem statements before writing a PRD. This is the front-of-funnel step that precedes pmstack-prd.

2026-05-298

pmstack-transcript-review

RyanAlberts/pmstack

Walks a PM through Anthropic's Step 6 ritual — reading transcripts from many trials to diagnose every failed eval task as one of three things — model mistake, grader mistake, or task-spec error. Implements the practice Anthropic describes as "critical" — without it, badly-calibrated graders mask real model improvements. Use when the user has a /run-eval result with failures, asks "why did this fail?", says "let's read the transcripts," wants to debug an eval, suspects grader bugs, or mentions Anthropic's transcript-review practice. Accepts a run folder path, pasted summary + cases, or attached files. Output: a markdown memo at outputs/transcript-review-<feature>-<date>.md with verdict counts and per-trial diagnoses.

2026-05-058

pmstack-vibe-test

RyanAlberts/pmstack

Walks a PM through the layer-1 ritual of reading raw transcripts of an AI feature in action — what Anthropic calls "manual testing, dogfooding, and intuition" — before formalizing a structured eval. Surfaces failure patterns, drafts task candidates (including balanced negative cases per Anthropic Step 3), and produces a verdict on whether the feature is ready for /eval. Use when the user says "I want to vibe-test this," "I have transcripts of our AI feature," "before we write evals let's read the data," "we have support tickets / bug reports about this AI feature," or asks how to start an eval from scratch. Accepts pasted transcripts, attached files, or a folder path. Output: a markdown memo at outputs/vibe-test-<feature>-<date>.md.

2026-05-058

pmstack-eval

RyanAlberts/pmstack

Design a PM-runnable evaluation suite for an AI feature, implementing Anthropic's eval framework (Demystifying Evals for AI Agents). Walks the user through Anthropic's 8-step roadmap — source tasks from real failures, write unambiguous tasks with reference solutions, build balanced problem sets (test where behavior should AND shouldn't occur), choose graders thoughtfully (code / model / human). Use when a PM mentions "eval", "evaluation suite", "test suite for AI", "agent eval", "AI quality bars", "how would we know if X works", "designing tests for our AI feature", or wants to define what "good" looks like before shipping. Output: a YAML test suite that /run-eval can execute end-to-end.

2026-05-058

name

pmstack-onboarding

description

pmstack-onboarding — interactive tutorial

A 9-step walkthrough of pmstack's full capability set. Every step is runnable, has an example input, and produces a real artifact.

Procedure

For each step: print the header, explain the capability in 2–3 plain-English sentences, show the exact command (or, on web/desktop, show the natural-language phrasing that triggers the skill), then stop and wait for the user to type next, skip, back, or ask a question.

The 9 steps:

Welcome + customer signal — present the tutorial signal: "Three of our biggest enterprise customers said code reviews are taking 24+ hours and devs are skipping them or merging without review."
/prd — translate the signal into a PRD.
/competitive — scan the market.
/premortem — stress-test the PRD with 3 failure stories.
/vibe-test — Anthropic's layer-1 ritual: read raw transcripts before writing the eval. Tutorial uses 5 mock transcripts at examples/walkthrough-code-review/transcripts/.
/sprint — chain metrics → eval → run-eval → brief.
/transcript-review — Anthropic's Step 6 ritual: diagnose every failed eval trial as model mistake / grader mistake / task-spec error.
/launch-readiness + /lint — gate routines before shipping.
Schedule the recurring routines — /weekly, /eval-drift, /lint on /loop 7d.

After step 9, print a final recap table mapping each capability to "when you'd use it" and prompt the user to run a real /prd on a quote they have lying around.

Hard rules

Wait for explicit user advance between steps. Never auto-run all 9.
Tutorial artifacts go to outputs/onboarding-tutorial/ (not the user's real outputs/).
Surface-aware. If the user is on claude.ai web/desktop (no filesystem), emit each artifact inline as a markdown block they can copy. Tell them this up front.
If a comparison-example file is missing, fall back to a one-paragraph inline description.

Where to write

Filesystem: outputs/onboarding-tutorial/<artifact-name>.md.
Inline (web/desktop): markdown blocks in the conversation. Suggest a filename at the top of each block so the user knows what to call it if they save it.

Decision-log entry

Append one line only at the end of the tutorial: - <date> — onboarding: tutorial completed — outputs/onboarding-tutorial/.

Tone

Friendly, concise, anti-jargon. State each capability's value in plain English before the technical details. The user may not be technical.

Cold-start behavior

If outputs/ is empty (this is most users on first run), the tutorial fills it as it goes. If outputs/ already has content, the tutorial still writes to outputs/onboarding-tutorial/ — never overwriting prior work.