WHAT - Draft and review bugs using the Bug Template; classifies whether an issue should be
Scanned 9/2/2026
Install to Claude Code
Skills Directorynpx -y skills add ulises-jeremias/agent-toolkit --skill bug --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Bug?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/ulises-jeremias-bug)More formats (shields.io, HTML) on the badges page.
---
name: bug
description: WHAT - Draft and review bugs using the Bug Template; classifies whether an issue should be
escalated to incident based on production/user impact.
origin:
type: first-party
---
# Bug (WHAT)
Use for defects that can be handled through the normal development workflow.
## Bug vs incident rule
Route to **`incident`** instead if the problem impacts production or live users now, degrades service, blocks critical business operations, creates client-reported urgency, or needs immediate response outside planning cycles.
## Default guardrails
1. Apply **`output-handshake`** before final output.
2. Capture reproduction steps and environment details.
3. Use **`clickup-cli`** for ClickUp writes only after approval.
## References
- `references/default-template.md` — bug template
- `references/example-search-filter-bug.md` — example bug with environment details, diagnostics, and severity assessment
- `incident` — when to escalate to incident
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', ...
