From GSD Core
Debugs issues using a scientific method with subagent isolation, persistent state across context resets, and optional diagnose-only mode.
How this skill is triggered — by the user, by Claude, or both
Slash command
/gsd-core:gsd-debug [list | status <slug> | continue <slug> | --diagnose] [issue description][list | status <slug> | continue <slug> | --diagnose] [issue description]This skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
<objective>
Orchestrator role: Gather symptoms, spawn gsd-debugger agent, handle checkpoints, spawn continuations.
Flags:
--diagnose — Diagnose only. Returns a Root Cause Report without applying a fix.Subcommands: list · status <slug> · continue <slug>
<available_agent_types> Valid GSD subagent types (use exact names — do not fall back to 'general-purpose'):
<execution_context> @~/.claude/gsd-core/workflows/debug.md </execution_context>
User's input: $ARGUMENTSParse subcommands and flags from $ARGUMENTS BEFORE the active-session check:
--diagnose: SUBCMD=debug, diagnose_only=true, strip --diagnose from descriptionCheck for active sessions (used for non-list/status/continue flows):
ls .planning/debug/*.md 2>/dev/null | grep -v resolved | head -5
Execute end-to-end.
npx claudepluginhub open-gsd/gsd-coreOrchestrates persistent, hypothesis-driven debugging sessions across conversations, delegating analysis to subagents and tracking in debug files.
Systematic debugging loop that spawns fresh subagents to investigate and fix bugs. Automatically activated for debugging, error investigation, and root cause analysis.
Runs parallel AI agent investigations on a bug/issue and produces a consolidated debug report. Use for debugging, error analysis, or problem diagnosis.