تشغيل أي مهارة في Manus بنقرة واحدة

pmstack-premortem

النجوم٨

التفرعات١

آخر تحديث٥ مايو ٢٠٢٦ في ١٨:١١

Run a Klein-style pre-mortem on a draft PRD before launch — simulates 3 plausible failure stories 6 months in the future, names leading indicators and mitigations, then offers to mutate the PRD's Risks section. Trigger when the user says "pre-mortem," "what could go wrong," "risk pass," "imagine this fails," "stress test the spec," or asks to harden a PRD before review. Use after /prd, before launch.

التثبيت

التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.

تشغيل في Manus

المصدر

RyanAlberts

RyanAlberts/pmstack

فتح مستودع GitHub عرض مستودعات المنشئ

تنزيل

تشغيل في Manus

المهن ذات الصلةSOC

استنادا إلى تصنيف SOC المهني

متخصصو إدارة المشاريعمهن الأعمال والعمليات المالية·SOC 13-1082

SKILL.md

readonly

name

pmstack-premortem

description

premortem — pre-mortem on a target PRD

Klein's pre-mortem trick: pretend the feature failed 6 months from now and write the post-mortem now, before launch. The only pmstack capability that mutates an existing artifact rather than appending another.

Required structure

For each of 3 failure stories:

### Failure story <N>: <one-line headline>
**What happened:** <2–4 sentences narrating the specific failure>
**Anchored to PRD:** <quote or section reference from the source PRD>
**Leading indicator:** <a metric, signal, or qualitative observation that would have surfaced this BEFORE launch>
**Mitigation:** <one specific action to take before shipping>

The 3 stories must span at least: (a) capability/quality, (b) adoption/UX, (c) operational/cost. Do not stack 3 quality failures.

Hard rules

Stories must be specific, not generic. "Adoption could be lower than expected" fails. "Devs share screenshots of bad code-review suggestions on day 1, the meme spreads, the trial closes sour" passes.
Each leading indicator must be measurable today. No reliance on production traffic that doesn't exist — use a pre-launch proxy.
Confirmation gate is mandatory. After writing the artifact, list the 3 mitigations and ask which to append to the PRD's Risks section. Do not auto-mutate. Wait for explicit selection ("1,3" or "all" or "none").
Anchor every story to the PRD. Quote or section reference required.

Where to write

With filesystem: outputs/premortem-<topic-slug>-<YYYY-MM-DD>.md. On accept, mutate the source PRD's Risks section. Rejected mitigations land in ## Rejected mitigations of the premortem artifact.
Inline (web/mobile): emit the premortem markdown plus a separate "Suggested PRD diff" block the user pastes into their PRD.

Decision-log entry

- <date> — premortem(<topic>): <N>/3 risks accepted — outputs/premortem-<topic>-<date>.md

Tone

Concrete, narrative, blunt about failure modes. PMs systematically under-fill risk sections; this skill is the corrective.

Cold-start behavior

Works the moment one PRD exists. No history required.

المزيد من هذا المستودع

نفس المستودع

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-onboarding

RyanAlberts/pmstack

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."

2026-05-058

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

name

pmstack-premortem

description

premortem — pre-mortem on a target PRD

Required structure

For each of 3 failure stories:

### Failure story <N>: <one-line headline>
**What happened:** <2–4 sentences narrating the specific failure>
**Anchored to PRD:** <quote or section reference from the source PRD>
**Leading indicator:** <a metric, signal, or qualitative observation that would have surfaced this BEFORE launch>
**Mitigation:** <one specific action to take before shipping>

The 3 stories must span at least: (a) capability/quality, (b) adoption/UX, (c) operational/cost. Do not stack 3 quality failures.

Hard rules

Stories must be specific, not generic. "Adoption could be lower than expected" fails. "Devs share screenshots of bad code-review suggestions on day 1, the meme spreads, the trial closes sour" passes.
Each leading indicator must be measurable today. No reliance on production traffic that doesn't exist — use a pre-launch proxy.
Confirmation gate is mandatory. After writing the artifact, list the 3 mitigations and ask which to append to the PRD's Risks section. Do not auto-mutate. Wait for explicit selection ("1,3" or "all" or "none").
Anchor every story to the PRD. Quote or section reference required.

Where to write

With filesystem: outputs/premortem-<topic-slug>-<YYYY-MM-DD>.md. On accept, mutate the source PRD's Risks section. Rejected mitigations land in ## Rejected mitigations of the premortem artifact.
Inline (web/mobile): emit the premortem markdown plus a separate "Suggested PRD diff" block the user pastes into their PRD.

Decision-log entry

- <date> — premortem(<topic>): <N>/3 risks accepted — outputs/premortem-<topic>-<date>.md

Tone

Concrete, narrative, blunt about failure modes. PMs systematically under-fill risk sections; this skill is the corrective.

Cold-start behavior

Works the moment one PRD exists. No history required.