Point your robot at a GitHub issue and let it start beeping and booping—fetches details, assesses complexity, guides to PR
Automates GitHub issue resolution workflow from branch to PR with verification
/plugin marketplace add oalders/kitchen-sink/plugin install oalders-kitchen-sink@oalders/kitchen-sinkThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Automates the workflow for fixing GitHub issues on branches named fix-NNN. Extracts issue number, fetches details with gh, assesses complexity, guides through resolution with appropriate skills, and creates PR that closes the issue.
Use this skill when:
Issue number resolution:
fix-978 -> 978)Don't use when:
digraph fix_issue {
"Extract issue # from branch" [shape=box];
"Fetch issue with gh" [shape=box];
"Assess complexity" [shape=box];
"Non-trivial?" [shape=diamond];
"Suggest brainstorming" [shape=box];
"Multi-step with independent tasks?" [shape=diamond];
"Use subagent-driven-development" [shape=box];
"Implement fix" [shape=box];
"Verify with verification-before-completion" [shape=box];
"Create PR closing issue" [shape=box];
"Extract issue # from branch" -> "Fetch issue with gh";
"Fetch issue with gh" -> "Assess complexity";
"Assess complexity" -> "Non-trivial?";
"Non-trivial?" -> "Suggest brainstorming" [label="yes"];
"Non-trivial?" -> "Multi-step with independent tasks?" [label="no"];
"Suggest brainstorming" -> "Multi-step with independent tasks?";
"Multi-step with independent tasks?" -> "Use subagent-driven-development" [label="yes"];
"Multi-step with independent tasks?" -> "Implement fix" [label="no"];
"Use subagent-driven-development" -> "Verify with verification-before-completion";
"Implement fix" -> "Verify with verification-before-completion";
"Verify with verification-before-completion" -> "Create PR closing issue";
}
Get issue number: Use provided number, or parse from branch name (fix-978 -> 978)
Fetch issue:
gh issue view 978
Assess complexity:
| Trivial | Non-trivial |
|---|---|
| Single file | Multiple files |
| < 10 lines | > 10 lines |
| Obvious fix | Requires decisions |
| No tests needed | Tests required |
When in doubt, treat as non-trivial
For non-trivial issues:
superpowers:brainstorming if user agreesChoose implementation approach:
superpowers:subagent-driven-developmentsuperpowers:writing-plans firstVerify fix:
superpowers:verification-before-completionCreate PR:
gh pr create --title "Fix: [issue title]" \
--body "Closes #978
## Changes
- [What changed]
## Testing
- [How verified]"
| Mistake | Fix |
|---|---|
| Skip fetching issue | Always fetch - may have updates |
| Jump into complex fix | Suggest brainstorming for non-trivial |
| Skip verification | Always verify before PR |
| Wrong issue # in PR | Double-check branch name parsing |
| "I'll just fix it quickly" for big changes | Use proper workflow |
superpowers:verification-before-completion before PRsuperpowers:brainstormingsuperpowers:subagent-driven-developmentsuperpowers:writing-plansThis skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.