How do I install the Pmstack Weekly skill?

Run npx skillmds@latest add ryanalberts/pmstack-weekly 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 Weekly 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 Weekly?

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 Weekly free to use?

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

Who published Pmstack Weekly?

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

Pmstack Weekly by ryanalberts — Agent Skill

Name: Pmstack Weekly
Author: RyanAlberts

Pmstack Weekly

A Monday-morning self-snapshot for PMs. Three sections only — decisions made, open loops aging out, and one required "thing I changed my mind about." Anti-vanity by design. Trigger when the user says "weekly memo," "weekly recap," "Monday status," "what changed this week," "weekly self-check," or asks to summarize last week's PM activity. Run weekly on schedule, or on demand to catch up.

RyanAlberts 662c212 2.3 KB Updated Sep 17, 2026

File contents

weekly — Monday-morning self-snapshot

A weekly memo that prioritizes what changed in your thinking over what shipped.

Required structure (exactly these three sections)

# weekly — <YYYY-Www>

## Decisions made
<bulleted list, grouped by skill (prd / metrics / eval / brief / competitive / compare / premortem / launch-readiness / lint / eval-drift / other)>
<each line cites the artifact path>

## Open loops aging
- PRD without metrics (>14 days): <path>
- Eval designed but not run (>7 days): <path>
- Brief with broken reference: <path>

## One thing I changed my mind about
<single paragraph; REQUIRED — if user can't name one, the routine writes "none this week" literally>

Hard rules

Three sections only. Do not add a "shipped this week" section — that's vanity.
Open loops cite real file paths, not placeholder text.
"Changed my mind" must contain real content or the literal string "none this week." Silent omission is forbidden — that's what turns this back into a vanity mirror.
Group decisions by skill so the reader sees the shape of the week, not 12 unsorted bullets.

Where to write

With filesystem: outputs/weekly-<YYYY-Www>.md. Read decisions-log.md and glob outputs/* for the 7-day window.
Inline (web/mobile): emit the artifact as markdown with the suggested filename at the top.

Decision-log entry

- <date> — weekly: <N decisions> / <M open loops> — outputs/weekly-<YYYY-Www>.md

Tone

Direct, calibrated, anti-status-report. State confidence levels. The "changed my mind" forcing function is the whole point — it captures learning, not output.

Cold-start behavior

If the last 7 days are empty, write a one-section "no activity yet" memo and prompt the PM to seed by running another skill. If decisions-log.md has at least one entry in the window, the "Decisions made" section is meaningful from week 1.

---name: pmstack-weeklydescription: A Monday-morning self-snapshot for PMs. Three sections only — decisions made, open loops aging out, and one required "thing I changed my mind about." Anti-vanity by design. Trigger when the user says "weekly memo," "weekly recap," "Monday status," "what changed this week," "weekly self-check," or asks to summarize last week's PM activity. Run weekly on schedule, or on demand to catch up.---# weekly — Monday-morning self-snapshotA weekly memo that prioritizes **what changed in your thinking** over what shipped.## Required structure (exactly these three sections)```# weekly — <YYYY-Www>## Decisions made<bulleted list, grouped by skill (prd / metrics / eval / brief / competitive / compare / premortem / launch-readiness / lint / eval-drift / other)><each line cites the artifact path>## Open loops aging- PRD without metrics (>14 days): <path>- Eval designed but not run (>7 days): <path>- Brief with broken reference: <path>## One thing I changed my mind about<single paragraph; REQUIRED — if user can't name one, the routine writes "none this week" literally>```## Hard rules- **Three sections only.** Do not add a "shipped this week" section — that's vanity.- **Open loops cite real file paths**, not placeholder text.- **"Changed my mind" must contain real content or the literal string "none this week."** Silent omission is forbidden — that's what turns this back into a vanity mirror.- **Group decisions by skill** so the reader sees the shape of the week, not 12 unsorted bullets.## Where to write- With filesystem: `outputs/weekly-<YYYY-Www>.md`. Read `decisions-log.md` and glob `outputs/*` for the 7-day window.- Inline (web/mobile): emit the artifact as markdown with the suggested filename at the top.## Decision-log entry`- <date> — weekly: <N decisions> / <M open loops> — outputs/weekly-<YYYY-Www>.md`## ToneDirect, calibrated, anti-status-report. State confidence levels. The "changed my mind" forcing function is the whole point — it captures learning, not output.## Cold-start behaviorIf the last 7 days are empty, write a one-section "no activity yet" memo and prompt the PM to seed by running another skill. If `decisions-log.md` has at least one entry in the window, the "Decisions made" section is meaningful from week 1.

Frequently asked questions