plugins/faos-pm/skills/pre-mortem/SKILL.md
<!-- AUTO-GENERATED by export-plugins.py — DO NOT EDIT --> --- name: pre-mortem description: Structured risk analysis that imagines launch failure and works backward to identify threats. Use when preparing for a product launch, major release, or any high-stakes initiative. tags: [risk, launch, planning, product-management] --- # Pre-Mortem A structured risk identification technique: imagine the product **has already failed**, then work backward to identify what went wrong — before it actually
npx skillsauth add frank-luongt/faos-skills-marketplace plugins/faos-pm/skills/pre-mortemInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
A structured risk identification technique: imagine the product has already failed, then work backward to identify what went wrong — before it actually does.
Traditional risk planning asks "what could go wrong?" which triggers optimism bias. Pre-mortems flip the frame: "It failed. Why?" — which activates prospective hindsight and surfaces risks people are reluctant to raise.
Read and reference the following (if available):
Start with this prompt to the team (or yourself):
"Imagine it's 6 months from now. This initiative has failed spectacularly. Customers are unhappy, metrics haven't moved, and leadership is asking what went wrong. What happened?"
Generate 10–15 potential failure causes without filtering. Include:
Categorize every risk into one of three types:
Tigers — Real, evidence-backed risks that require action
Paper Tigers — Concerns that seem scary but are manageable
Elephants — Unspoken risks nobody wants to discuss
For each Tiger, classify urgency:
| Urgency | Definition | Action Required | |---------|-----------|----------------| | Launch-Blocking | Must solve before launch or initiative is at serious risk | Mitigation plan required NOW | | Fast-Follow | Can launch, but must address within 30 days post-launch | Assign owner, set deadline | | Track | Monitor with defined triggers; act if situation changes | Define monitoring metric and threshold |
For each launch-blocking Tiger, produce:
### Tiger: [Risk Description]
**Evidence**: Why we believe this is real
**Impact if unmitigated**: What happens if we ignore it
**Mitigation plan**:
1. [Specific action]
2. [Specific action]
3. [Specific action]
**Owner**: [Name/Role]
**Due date**: [Date — must be before launch]
**Success criteria**: How we know the risk is mitigated
## Pre-Mortem Summary
**Initiative**: [Name]
**Launch date**: [Date]
**Pre-mortem date**: [Today]
**Participants**: [Names/Roles]
---
### Launch-Blocking Tigers (Must Resolve)
| # | Risk | Impact | Mitigation | Owner | Due |
|---|------|--------|------------|-------|-----|
| 1 | [risk] | [impact] | [action] | [who] | [when] |
### Fast-Follow Tigers (Resolve Within 30 Days)
| # | Risk | Impact | Mitigation | Owner | Due |
|---|------|--------|------------|-------|-----|
| 1 | [risk] | [impact] | [action] | [who] | [when] |
### Tracked Risks (Monitor)
| # | Risk | Monitoring Metric | Trigger Threshold | Owner |
|---|------|------------------|-------------------|-------|
| 1 | [risk] | [metric] | [threshold] | [who] |
### Paper Tigers (Acknowledged, No Action)
- [risk] — Why it's manageable: [reason]
### Elephants (Surfaced, Needs Discussion)
- [risk] — Why this matters: [reason]
---
### Decision
- [ ] **GO** — All launch-blocking Tigers mitigated
- [ ] **CONDITIONAL GO** — Launch-blocking Tigers have plans, not yet resolved
- [ ] **NO-GO** — Unresolved launch-blocking Tigers, delay recommended
| Avoid | Why | Instead | |-------|-----|---------| | Skipping Elephants | The unsaid risks are often the most dangerous | Create psychological safety, use anonymous input | | All risks are Tigers | If everything is critical, nothing is | Force classification — most risks are Paper Tigers | | No owners assigned | Unowned risks never get mitigated | Every Tiger needs a named owner and due date | | Running too early | Pre-mortem needs a concrete plan to evaluate | Run after PRD/architecture, before execution | | Running too late | No time to mitigate launch-blocking risks | Run 2–4 weeks before launch, not the day before | | Optimism creep | Team agrees risks exist but "we'll figure it out" | Demand specific mitigation actions, not vague reassurances |
development
<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: grpo-rl-training description: GRPO reinforcement learning training with TRL. Use when applying Group Relative Policy Optimization for reasoning and task-specific model training. --- # GRPO/RL Training with TRL Expert-level guidance for implementing Group Relative Policy Optimization (GRPO) using the Transformer Reinforcement Learning (TRL) library. This skill provides battle-tested patterns, critical insights, and production-r
tools
<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: graphql-architect description: Master modern GraphQL with federation, performance optimization, --- ## Use this skill when - Working on graphql architect tasks or workflows - Needing guidance, best practices, or checklists for graphql architect ## Do not use this skill when - The task is unrelated to graphql architect - You need a different domain or tool outside this scope ## Instructions - Clarify goals, constraints, and
development
<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: grafana-dashboards description: Create and manage production Grafana dashboards for real-time visualization of system and application metrics. Use when building monitoring dashboards, visualizing metrics, or creating operational observability interfaces. --- # Grafana Dashboards Create and manage production-ready Grafana dashboards for comprehensive system observability. ## Do not use this skill when - The task is unrelated
development
<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: gptq description: GPTQ post-training quantization for generative models. Use when quantizing large models to 4-bit with calibration-based weight compression. --- # GPTQ (Generative Pre-trained Transformer Quantization) Post-training quantization method that compresses LLMs to 4-bit with minimal accuracy loss using group-wise quantization. ## When to use GPTQ **Use GPTQ when:** - Need to fit large models (70B+) on limited GPU