Retrospective
Facilitate and write up a team retrospective — what went well, what didn't, and owned, time-bound action items. Use when the user says "run a retro", "retrospective", "sprint retro", "project post-completion review", "lessons learned", or wants to turn raw retro notes into a structured summary with follow-ups.
Install
$ agentstack add skill-janellecipriano-pm-skills-retrospective ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-janellecipriano-pm-skills-retrospective) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Retrospective
Help a team reflect productively and leave with a small number of concrete, owned improvements — not a venting session.
When to use
- End of a sprint, milestone, project, or quarter.
- Turning messy retro notes/transcript into a clean writeup.
- Designing a retro format/agenda.
Note: for incidents/outages use postmortem (blameless, root-cause focused) instead.
Inputs to gather
- What's being retro'd and the timeframe; who participated.
- Raw input if any (notes, sticky-note dump, transcript), or run a structured prompt.
Process
- Pick a frame — What went well / What didn't / What to try, or Start–Stop–Continue, or Mad–Sad–Glad.
- Group raw input into themes; don't list every duplicate sticky.
- Keep it blameless — focus on systems and process, not individuals.
- Surface the 2–4 highest-leverage improvements, not a wishlist. Each becomes an action.
- For every action: owner, concrete next step, due date, and where it's tracked.
- Revisit prior retro actions — were they done? Open loops kill trust in retros.
Output format
## Retro — {{team/project}} · {{period}}
### What went well
- {{theme}}
### What didn't / challenges
- {{theme}}
### Action items
| Action | Owner | Due | Status |
| --- | --- | --- | --- |
### Carryover from last retro
- {{item — done? / still open}}Keep actions few and real. A retro with 12 actions has zero.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: janellecipriano
- Source: janellecipriano/pm-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.