How do I install the Pmstack Sprint skill?

Run npx skillmds@latest add ryanalberts/pmstack-sprint 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 Sprint 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 Sprint?

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 Sprint free to use?

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

Who published Pmstack Sprint?

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

Pmstack Sprint by ryanalberts — Agent Skill

Name: Pmstack Sprint
Author: RyanAlberts

Pmstack Sprint

Full PM sprint orchestrator — chains pmstack-prd, pmstack-metrics, pmstack-eval, and pmstack-brief in sequence with explicit user confirmation between each step. Use when the user has a customer signal or feature ask and wants to go end-to-end (problem → spec → metrics → eval design → stakeholder comms) in one guided pass with checkpoints.

RyanAlberts d34d442 2.0 KB Updated Sep 17, 2026

File contents

PM Sprint Orchestrator

Chain pmstack-prd → pmstack-metrics → pmstack-eval → pmstack-brief, with explicit user confirmation after each step.

Procedure

If the user didn't provide a customer signal, ask for one and stop.
Step 1 — PRD. Invoke pmstack-prd with the signal. Write to outputs/prd-<topic-slug>-<date>.md. Show the path. Ask: "Continue to /metrics? (y/n)"
Step 2 — Metrics. Invoke pmstack-metrics, using the PRD as context. Write to outputs/metrics-<topic-slug>-<date>.md. Show the path. Ask: "Continue to /eval? (y/n)"
Step 3 — Eval design. Invoke pmstack-eval, using PRD + metrics as context. Write to outputs/eval-<topic-slug>-<date>.yaml. Show the path. Ask: "Continue to /brief? (y/n)"
Step 4 — Brief. Invoke pmstack-brief, summarizing PRD + metrics + eval for the user's named audience (default exec). Write to outputs/brief-<topic-slug>-<audience>-<date>.md.
Append one line to decisions-log.md: - YYYY-MM-DD — sprint: <topic> — prd, metrics, eval, brief in outputs/.

Hard rules

Run skills in sequence. Each step's output is the next step's input.
Stop and ask for explicit y/n confirmation after each artifact. Do not collapse steps to "save time."
If the user wants to revise a step, edit the artifact in place and ask again.
Do not auto-invoke pmstack-run-eval. The eval YAML is meant to be reviewed by the user before execution.

Anti-patterns

"It looks fine, let me just continue" — no. The user decides, not you.
Combining steps to fewer artifacts — no. Each artifact is a checkpoint and a deliverable.

---name: pmstack-sprintdescription: Full PM sprint orchestrator — chains pmstack-prd, pmstack-metrics, pmstack-eval, and pmstack-brief in sequence with explicit user confirmation between each step. Use when the user has a customer signal or feature ask and wants to go end-to-end (problem → spec → metrics → eval design → stakeholder comms) in one guided pass with checkpoints.---# PM Sprint OrchestratorChain `pmstack-prd` → `pmstack-metrics` → `pmstack-eval` → `pmstack-brief`, with explicit user confirmation after each step.## Procedure1. If the user didn't provide a customer signal, ask for one and stop.2. **Step 1 — PRD.** Invoke pmstack-prd with the signal. Write to `outputs/prd-<topic-slug>-<date>.md`. Show the path. **Ask: "Continue to /metrics? (y/n)"**3. **Step 2 — Metrics.** Invoke pmstack-metrics, using the PRD as context. Write to `outputs/metrics-<topic-slug>-<date>.md`. Show the path. **Ask: "Continue to /eval? (y/n)"**4. **Step 3 — Eval design.** Invoke pmstack-eval, using PRD + metrics as context. Write to `outputs/eval-<topic-slug>-<date>.yaml`. Show the path. **Ask: "Continue to /brief? (y/n)"**5. **Step 4 — Brief.** Invoke pmstack-brief, summarizing PRD + metrics + eval for the user's named audience (default `exec`). Write to `outputs/brief-<topic-slug>-<audience>-<date>.md`.6. Append one line to `decisions-log.md`: `- YYYY-MM-DD — sprint: <topic> — prd, metrics, eval, brief in outputs/`.## Hard rules- Run skills in sequence. Each step's output is the next step's input.- **Stop and ask for explicit y/n confirmation after each artifact.** Do not collapse steps to "save time."- If the user wants to revise a step, edit the artifact in place and ask again.- Do not auto-invoke pmstack-run-eval. The eval YAML is meant to be reviewed by the user before execution.## Anti-patterns- "It looks fine, let me just continue" — no. The user decides, not you.- Combining steps to fewer artifacts — no. Each artifact is a checkpoint and a deliverable.

Frequently asked questions