Bugkiller Manual

SkillProductivity

Gives your agent shared definitions for roles, safety rules, and delivery steps when working on a scoped bug fix.

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Then ask your AI: use the Bugkiller Manual skill

About this skill

Reference manual for the 2718lab Bugkiller evidence, safety, role, and delivery vocabulary. Use only for scoped DevKit guidance; it does not create tasks, agents, worktrees, or commits.

What this skill tells your AI

The instructions your AI receives, as published by 2718labs/2718lab-devkit in skills/bugkiller/SKILL.md and read by ahel’s review.

Read roles, workflow, and safety when a bounded repair needs their definitions.

The manual separates a candidate change, independent verification, and final acceptance. It is not a dispatcher or an agent profile; route selection and lifecycle actions remain explicit host/MCP responsibilities.

Signals

GitHub stars
99
Last commit
Sep 2026
Advanced
Item type
skill
Key
bugkiller
Source
github.com/2718labs/2718lab-devkit