Loading...
Loading...
Found 156 Skills
Get Shit Done (GSD) orchestrator. Runs the full project pipeline from idea to implementation to documentation: setup → PRD → task list → implementation → decisions doc. Use when the user wants to build something end-to-end, says "let's GSD", "build this from scratch", "get shit done", or wants to run the full development workflow. Coordinates gsdl-setup-project, gsdl-create-prd, gsdl-create-plan, gsdl-execute-plan, and gsdl-document-decisions skills. Spawns subagents per parent task during implementation to preserve context. Accepts an optional project name or source URL: /gsdl [project-name] OR /gsdl [linear|notion|slite] [url] OR /gsdl [url].
Aggressively clean up a codebase by removing AI slop, dead code, weak types, defensive over-engineering, duplication, and legacy cruft. Orchestrates 8 specialized subagents in parallel to deduplicate code, consolidate types, kill unused code, untangle circular dependencies, strengthen weak types, remove unnecessary try/catch, delete deprecated/legacy paths, and strip unhelpful comments. Use when the user asks to 'clean up the codebase', 'remove slop', 'improve code quality', 'remove dead code', 'kill AI slop', 'tighten types', 'remove legacy code', 'deduplicate code', 'DRY this up', 'untangle dependencies', or wants a thorough code quality pass. Also use when the user mentions code smells, technical debt cleanup, or refactoring for clarity — even if they don't use the word 'slop'.
Use when creating specialized subagents for Claude Code plugins or the Task tool - covers description writing for auto-delegation, tool selection, prompt structure, and testing agents
Guide for creating effective skills. This command should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations. Use when creating new skills, editing existing skills, or verifying skills work before deployment - applies TDD to process documentation by testing with subagents before writing, iterating until bulletproof against rationalization
Static source-code vulnerability scan. Reads a target directory (and THREAT_MODEL.md if present), spawns parallel review subagents per focus area, and writes VULN-FINDINGS.json + .md for /triage to consume. Read-only — no building, running, or network. For execution-verified crashes, use vuln-pipeline instead. Use when asked to "scan for vulns", "review this code for security issues", "find bugs in <dir>", or as the step between /threat-model and /triage.
Guide for creating AI subagents with isolated context for complex multi-step workflows. Use when users want to create a subagent, specialized agent, verifier, debugger, or orchestrator that requires isolated context and deep specialization. Works with any agent that supports subagent delegation. Triggers on "create subagent", "new agent", "specialized assistant", "create verifier".
Central authority for Claude Code subagents (sub-agents). Covers agent file format, YAML frontmatter, tool access configuration, model selection (inherit, sonnet, haiku, opus), automatic delegation, agent lifecycle, resumption, command-line usage (/agents), Agent SDK programmatic agents, priority resolution, and built-in agents (Plan subagent). Assists with creating agents, configuring agent tools, understanding agent behavior, and troubleshooting agent issues. Delegates 100% to docs-management skill for official documentation.
Structured checkpoint format for requesting human input. When an agent needs a decision, it must stop, present context, show options, and wait. Activate when delegating to subagents, running background tasks, or hitting any decision point that requires human judgment.
Execute a single task from a Jira task plan using a structured pipeline of specialist subagents: planning, testing, refactoring, implementation, documentation, code-quality review, architecture review, security audit, and requirements verification. The user must specify which task number to execute. Use when the user says "execute task 3", "work on task 2", "implement task 1", "start task 5 for PROJECT-1234", or "run task N". Also triggered by the orchestrating-jira-workflow skill as Phase 5 of the end-to-end pipeline (called once per task). Requires that the task plan exists at docs/<TICKET_KEY>-tasks.md. Executes ONLY the specified task — never continues to the next one without explicit user approval.
Umbrella skill for agent work discipline across development, analysis, and documentation: inspect the repo before restructuring, keep durable truth in repo artifacts instead of chat memory, co-evolve specs/design/steering/user docs with code, apply sound coding patterns, verify work honestly, avoid shortcuts, work efficiently with subagents without hallucinating, and keep moving through the next concrete work item when the human is away. References cover coding patterns, AI-authored code review, and artifact co-evolution. Trigger when the user asks for workflow discipline, coding patterns, doc/artifact maintenance, code review of AI-authored code, project hygiene, execution guardrails, repo normalization, or when a task risks drifting across architecture, storage, specs, continuity, or tooling boundaries.
This skill should be used when the user asks to "optimize CLAUDE.md", "create a new skill", "write a custom agent", "configure hooks", "manage context window", "set up MCP servers", "scaffold a skill package", "analyze token budget", "create subagents", "configure permissions", "set up worktrees", or "integrate Claude Code with editors". Use for Claude Code CLI mastery, skill authoring, context engineering, hooks automation, subagent creation, and development workflow optimization.
RED-GREEN-REFACTOR testing for agents: dispatch subagents with known inputs, capture verbatim outputs, verify against expectations. Use when creating, modifying, or validating agents and skills. Use for "test agent", "validate agent", "verify agent works", or pre-deployment checks. Do NOT use for feature requests, simple prompt edits without behavioral impact, or agents with no structured output to verify.