Loading...
Loading...
Found 9 Skills
Interactive planning assistant that helps create focused, well-structured ralph-loop commands through collaborative conversation
Breaks down the design into an atomic, ordered, and verifiable task plan stored in tasks.md. Trigger: /sdd-tasks <change-name>, task plan, break down implementation, task breakdown.
Implement a task with automated LLM-as-Judge verification for critical steps
Create and manage task documents in the docs/todo/ workflow. Use when creating new tasks, updating task status, or moving tasks between workflow stages. Provides complete task lifecycle management with verification.
Execute written implementation plans: first read and critically review the plan, then implement in small batches (default 3 tasks), produce verification evidence per batch and pause for feedback; must stop immediately and ask for help when blocked/tests fail/plan unclear. Trigger words: execute plan, implement plan, batch execution, follow the plan.
Track, stop, resume, verify, and save progress on long-running work. Use when asked to "start a work session", "track this work", "save progress", "stop session", "resume work", "continue where we left off", "verify work", "check if we're done", "validate progress", "let's get to work on something big", or when planning multi-phase implementations, complex refactoring, or tasks spanning multiple sessions.
Execute a task with sub-agent implementation and LLM-as-a-judge verification with automatic retry loop
Validate plans against 10 verification dimensions before execution begins. Uses goal-backward analysis to catch dropped requirements, vague tasks, missing dependencies, and scope overreach. Produces PASS/BLOCK verdict with structured findings. Use for "check plan", "validate plan", "is this plan ready", "review plan before executing", or "/plan-checker". Do NOT use for plan creation (use feature-plan or workflow-orchestrator) or plan lifecycle management (use plan-manager).
Explicit anti-rationalization enforcement for maximum-rigor task execution. Loads all anti-rationalization patterns, gate enforcement, and pressure resistance as a composable modifier on any task. Use when executing critical production changes, security-sensitive code, complex multi-file refactors, or any task where shortcuts could cause harm. Use for "with rigor", "carefully", "maximum verification", or "no shortcuts". Do NOT use for trivial lookups, documentation-only edits, or simple typo fixes where full gate enforcement would be disproportionate overhead.