How do I install the Pmstack Onboarding skill?

Run npx skillmds@latest add ryanalberts/pmstack-onboarding in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Pmstack Onboarding safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Pmstack Onboarding?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Pmstack Onboarding free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Pmstack Onboarding?

RyanAlberts (@ryanalberts) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Pmstack Onboarding by ryanalberts — Agent Skill

Name: Pmstack Onboarding
Author: RyanAlberts

Pmstack Onboarding

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."

RyanAlberts 0991080 3.3 KB Updated Sep 17, 2026

File contents

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.

---name: pmstack-onboardingdescription: 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."---# pmstack-onboarding — interactive tutorialA 9-step walkthrough of pmstack's full capability set. Every step is runnable, has an example input, and produces a real artifact.## ProcedureFor 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:1. **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."2. **`/prd`** — translate the signal into a PRD.3. **`/competitive`** — scan the market.4. **`/premortem`** — stress-test the PRD with 3 failure stories.5. **`/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/`.6. **`/sprint`** — chain metrics → eval → run-eval → brief.7. **`/transcript-review`** — Anthropic's Step 6 ritual: diagnose every failed eval trial as *model mistake / grader mistake / task-spec error*.8. **`/launch-readiness` + `/lint`** — gate routines before shipping.9. **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 entryAppend one line *only at the end of the tutorial*: `- <date> — onboarding: tutorial completed — outputs/onboarding-tutorial/`.## ToneFriendly, concise, anti-jargon. State each capability's value in plain English before the technical details. The user may not be technical.## Cold-start behaviorIf `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.

Frequently asked questions