WHAT - Draft and review incident reports and RCA notes using Incident Management guidance;
Scanned 9/2/2026
Install to Claude Code
npx -y skills add ulises-jeremias/agent-toolkit --skill incident --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Incident?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/ulises-jeremias-incident-b3911dcd)More formats (shields.io, HTML) on the badges page.
---
name: incident
description: WHAT - Draft and review incident reports and RCA notes using Incident Management guidance;
includes detection, impact, timeline, RCA, resolution, and follow-ups.
origin:
type: first-party
---
# Incident (WHAT)
Use for unplanned events that disrupt or degrade production systems, live users, or critical operations.
## Default guardrails
1. Apply **`output-handshake`** before final output.
2. Capture immediate mitigation separately from root cause and follow-up actions.
3. Use **`meeting-minutes`** if a validation or post-incident meeting needs minutes.
4. Create/link follow-up bugs or tasks only after approval.
## References
- `references/default-template.md`
- `references/example-payment-outage.md` — example incident with full timeline, RCA, and action items
- `bug`
- `meeting-minutes`
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...