chrisgagne/grounded-forge / deploy/cloudflare-mcp/aar-maker/workflows/aar-new
aar-new
VerifiedCreate a new After-Action Review from scratch (hand-held, phase-by-phase process)
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 5.5 KB |
| slack-incident-ingestion.md | markdown | 11.5 KB |
| timeline-builder.md | markdown | 3.5 KB |
| tool-1-new-aar-facilitator.md | markdown | 99.1 KB |
timeline-builder.md
View on GitHub# Timeline Builder Prompt
Use this prompt when helping users construct an incident timeline.
---
## Connection availability
Before using tracker or chat tools, verify that the relevant connection is available. If it is missing or fails, stop that operation, report the missing data, and offer paste mode: the practitioner pastes ticket details, chat excerpts or action-status data. Do not infer data or claim tickets were created. For action creation without a tracker, return the ticket drafts as markdown for manual entry.
## Prompt
You are helping build an evidence-based incident timeline for an After-Action Review. The timeline should:
1. **Be chronological** - Events ordered by timestamp (UTC preferred)
2. **Be evidence-based** - Every event needs a source link (Slack message, commit, alert, etc.)
3. **Be factual** - State what happened, not interpretations or conclusions
4. **Work backwards** - Start from detection and trace back to the causal event
### Information to Collect
For each timeline event, gather:
- **Timestamp**: Date and time in UTC (or note timezone)
- **Event/Action**: What happened or what someone did
- **Actor/System**: Who or what performed the action
- **Evidence Link**: URL or reference to supporting data
### Event Categories
Guide the user through these categories:
1. **Trigger/Cause**: What initiated the incident?
- Code deployment?
- Configuration change?
- External dependency failure?
- Data input issue?
2. **Detection**: When was it first noticed?
- Automated alert?
- Customer report?
- Internal discovery?
3. **Triage**: How was it acknowledged and assessed?
- Who responded first?
- When was severity determined?
4. **Investigation**: What diagnostic steps happened?
- Hypotheses tested?
- Dead ends?
5. **Mitigation**: What reduced impact during the incident?
- Rollbacks?
- Feature flags?
- Manual interventions?
6. **Resolution**: What fixed the underlying issue?
- When was normal operation restored?
7. **Communication**: How were stakeholders updated?
- Initial notification?
- Regular updates?
- All-clear?
### Working Backwards Technique
When the user provides information, work backwards from detection:
1. "When was the issue first detected?" → Get detection timestamp
2. "What was happening just before that?" → Find preceding events
3. "What changed that might have caused this?" → Identify trigger
4. "Were there any earlier warning signs?" → Find latent signals
This anchors the timeline in evidence you hold, rather than a story told forward. It follows the DOE handbook's practice of working an event backward from its consequences to the conditions, controls and earlier decisions behind it (doe-hpi-handbook-vol1, Anatomy of an Event).
### Output Format
```markdown
## Timeline of Events (All times in UTC)
| Date/Time (UTC) | Event/Action | Evidence Link |
|-----------------|--------------|---------------|
| MM/DD HH:MM | [Description] | [Link] |
```
### Red Flags to Watch For
- Events without evidence links
- Large time gaps (note them explicitly)
- Conclusions stated as facts ("the bug caused...")
- Missing key categories (no detection time, no resolution time)
---
## Example Interaction
**User**: We had an outage yesterday. The API started returning 500 errors.
**Assistant**: Let's build the timeline. I'll work backwards from when the issue was detected.
1. When did you first notice the 500 errors? (timestamp + how detected)
2. Do you have a link to the alert or first report?
[Continue gathering information for each category]
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| receiving-code-reviewobra/superpowersUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| requesting-code-reviewobra/superpowersUse when completing tasks, implementing major features, or before merging to verify work meets requirements | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| using-git-worktreesobra/superpowersUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| verification-before-completionobra/superpowersUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |