Percerno Skillsbeta
← everything it can do · marketing

Post Mortem TEXT

Generates a structured retrospective report for a specific business decision, scoring actual outcomes against pre-committed success and kill criteria. It also revisits original dissent and assumptions to extract process lessons and forward actions.

0 uses this weeksource alirezarezvanilicence MIT
Not measured yet. Every skill is tested against the bare model on its own example requests; results appear here.
Security scan: clean · 2026-10-24 · 1 files · ran in sandbox
no network calls, shell tricks, credential access or instruction tampering found in its files.

Try asking

Say it in your own words; the assistant finds this recipe by itself. Examples:

“Kør en post-mortem på beslutningen om at ændre prissætningen, da 90-dagesperioden er udløbet.”
“Churn-raten har ramt kill-kriteriet for den nye onboarding; lav en retrospektiv rapport.”
“Analyser resultatet af beslutningen om at droppe den gamle API-support i forhold til vores oprindelige succeskriterier.”
“Run a post-mortem on the Q3 pricing strategy change now that the 90-day window has closed.”
“The churn rate hit the kill threshold for the new onboarding flow; generate the retrospective report.”
“Analyze the outcome of the decision to drop the legacy API support against our original success metrics.”
Try this skill from Claude, ChatGPT or a chat on your own page. Free plan, no credit card.Get started free

Good for

post-mortemretrospectivedecision-reviewstrategic-analysisperformance-scoringdissent-reviewassumption-auditbusiness-operations

Not for

Do not use this skill for initial decision-making, brainstorming, or creating new execution plans, as those are handled by 'decide' or 'execute' skills. It is not suitable for real-time operational monitoring or daily status updates, which require different reporting tools. Avoid using it if the decision has not yet been executed or if pre-committed success metrics were not defined at the time of the decision.

Details

When it is the right choice

Use this skill when a strategic decision reaches its 90-day review checkpoint or when a predefined kill criterion has been triggered. It is appropriate for evaluating whether a past decision was a win, loss, or mixed result based on data collected after execution. It is also used to formally close the strategic sprint loop by documenting lessons learned and updating organizational memory.

The full recipe the assistant reads

/c-level-agents:post-mortem — Honest Retrospective

Command: /c-level-agents:post-mortem <decision-path>

Closes the strategic sprint loop. Scores a decision against the success and kill criteria written before the decision (not retro-fitted) and revisits the preserved dissent. This is the rigor that compounds over time.

Pipeline Position

/c-level-agents:office-hours  →  /c-level-agents:brief  →  /c-level-agents:boardroom  →  /c-level-agents:decide  →  /c-level-agents:execute  →  /c-level-agents:post-mortem
                                                                                       ↑ you are here

When to Run

  • At the 90-day checkpoint (auto-scheduled by /c-level-agents:decide)
  • When a kill criterion triggers
  • After a major decision is reversed
  • Quarterly on all decisions of the past quarter

Inputs

  • The decision record (output of /c-level-agents:decide)
  • The execution plan (output of /c-level-agents:execute)
  • Actual outcomes (metrics, events, customer signals)

Output: Post-Mortem Record

Saved to ~/.claude/postmortems/YYYY-MM-DD-<slug>.md:

# Post-Mortem: <decision title>
**Decision date:** YYYY-MM-DD
**Post-mortem date:** YYYY-MM-DD
**Status:** WIN / PARTIAL / LOSS / MIXED

## Outcome Scoring (against pre-committed criteria)

| Success Criterion | Threshold | Actual | Met? |
|---|---|---|---|
| <metric 1> | <threshold> | <actual> | ✅ / ❌ |
| <metric 2> | <threshold> | <actual> | ✅ / ❌ |

| Kill Criterion | Threshold | Actual | Triggered? |
|---|---|---|---|
| <metric> | <threshold> | <actual> | ✅ / ❌ |

**Overall:** WIN / PARTIAL / LOSS / MIXED

## What We Got Right
- <factor 1>
- <factor 2>

## What We Got Wrong
- <factor 1>
- <factor 2>

## Preserved Dissent — Revisited
[Original dissent from the boardroom memo, scored:]

- **<dissenter>:** <original concern>
  - **Did it materialize?** YES / NO / PARTIAL
  - **Cost if YES:** <quantified impact>
  - **Lesson:** <one sentence>

## Assumption Audit
[Original brief's assumptions, scored:]

- **Assumption 1:** <text>
  - **Held?** YES / NO / PARTIAL
  - **Why:** <explanation>

## Process Lessons
- **Phase 2 isolation worked?** YES / NO
- **Devil's advocate concerns played out?** YES / NO / PARTIAL
- **Cadence was right?** YES / TOO LOOSE / TOO TIGHT

## Forward Actions
- [ ] <change to operating system or routing logic>
- [ ] <new decision to make based on this learning>
- [ ] <update company-context.md>

## Status
- WIN → archive, log lesson
- LOSS → schedule follow-up boardroom: `/c-level-agents:brief` for the next call

Why Pre-Committed Criteria Matter

The biggest temptation in post-mortems is retroactive justification: "we always knew X, that's why we did Y." Pre-committed criteria, signed at /c-level-agents:decide time, eliminate that move. The numbers either matched or they didn't.

Why Revisit Dissent

The dissent column from /c-level-agents:boardroom is the single most useful piece of organizational memory. Most of the time, the dissenter was directionally right. Revisiting and scoring it builds calibration over years.

Routing

  • /c-level-agents:brief — if the post-mortem surfaces a new decision
  • /c-level-agents:freeze — if the post-mortem reveals a process gap that needs cooldown enforcement
  • Updates to company-context.md via cs-onboard

Related

Version: 1.0.0

Files in this skill (2)
  • LICENSE
  • SKILL.md
Where it comes from

Vendored from alirezarezvani/claude-skills, commit 27cfcd0fb0a4, path c-level-agents/skills/post-mortem, licence MIT. The upstream licence file ships inside the skill.