Stats
Actions
Tags
From pmstack — PM Toolkit for the AI Era
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.
How this skill is triggered — by the user, by Claude, or both
Slash command
/pmstack:pmstack-weeklyThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
A weekly memo that prioritizes **what changed in your thinking** over what shipped.
A weekly memo that prioritizes what changed in your thinking over what shipped.
# 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>
outputs/weekly-<YYYY-Www>.md. Read decisions-log.md and glob outputs/* for the 7-day window.- <date> — weekly: <N decisions> / <M open loops> — outputs/weekly-<YYYY-Www>.md
Direct, calibrated, anti-status-report. State confidence levels. The "changed my mind" forcing function is the whole point — it captures learning, not output.
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.
npx claudepluginhub ryanalberts/pmstack --plugin pmstackCreates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.