lazy-bug
CommunityOne-skill-per-invocation bug dispatcher
System Documentation
What problem does it solve?
Stateless dispatcher — infers bug state from filesystem via bug-state.py, and invokes exactly ONE sub-skill per invocation to progress the current bug. Drives docs/bugs/ (NOT docs/features/). The __mark_fixed__ special action performs the archive-on-fix flow: writes/verifies FIXED.md receipt (kind: fixed, gated by the completion-integrity gate), sets SPEC Status: Fixed + Fixed: and Fix commit: header lines, git mv to docs/bugs/_archive/, repoints inbound root-relative references, and commits. Receipt is FIXED.md (kind: fixed); Won't-fix bugs are receipt-EXEMPT. No research/Gemini steps, no stub-spec step, no realign step — N/A to bugs. Status vocab: Open | Investigating | In-progress | Fixed | Won't-fix.
Core Features & Use Cases
- Thin LLM wrapper around bug-state.py to determine next action
- Dispatches exactly one sub-skill per invocation, progressing from OPEN/INVESTIGATING through SPEC/PHASES to FIXED or WON'T-FIX
- Manages sentinel files and status bookends, and supports the archive-on-fix flow
- Enforces no plan mode; surfaces terminal states and operator-resolvable blocks for manual intervention
Quick Start
Invoke the lazy-bug skill to progress the current bug by dispatching exactly one sub-skill per invocation.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: lazy-bug Download link: https://github.com/jacobrocks1212/claude-config/archive/main.zip#lazy-bug Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 510,000+ vetted skills library on demand.