Loading...
Loading...
Found 98 Skills
Spawn specialized sub-agents with context handoff for complex multi-phase tasks. Enables expertise delegation within a session with automatic context merging and depth limiting to prevent infinite loops.
Launch an intelligent sub-agent with automatic model selection based on task complexity, specialized agent matching, Zero-shot CoT reasoning, and mandatory self-critique verification
Research codebase comprehensively using parallel sub-agents to answer user questions. Use when the user asks to "research the codebase", "understand how X works", or "investigate Y".
Review a single file or all files in a folder for data inconsistencies, reference errors, typos, and unclear terminology using parallel sub-agents
Launch a sub-agent judge to evaluate results produced in the current conversation
The complete AI web agency toolkit. One skill to run a full client website project — from intake to design to build to deploy. Orchestrates sub-skills and sub-agents for fast, high-quality delivery.
Enforces complete execution, mode-aware delivery, compact sub-agent communication, independent agent-review gating, validation, and reporting for implementation, bugfix, hardening, documentation, specification, architecture, design, review, and post-mortem tasks. Use whenever work must be completed, reviewed, validated, or documented through an explicit execution mode instead of handled ad hoc.
2-layer parallel agent hierarchy. Layer 1 deploys 3-50+ agents, each with independent context. Layer 2 adds 2+ sub-agents per member. No upper limit on either layer.
Explore a codebase for architectural friction, discover refactoring opportunities, and propose module-deepening refactors as GitHub issue RFCs. Uses friction-driven exploration and parallel sub-agents to design multiple interface alternatives. Use when user wants to improve architecture, find refactoring opportunities, consolidate coupled modules, reduce complexity, make code more testable, or review codebase health.
Parallel adversarial review protocol that launches two independent blind judge sub-agents simultaneously to review the same target, synthesizes their findings, applies fixes, and re-judges until both pass or escalates after 2 iterations. Trigger: When user says "judgment day", "judgment-day", "review adversarial", "dual review", "doble review", "juzgar", "que lo juzguen".
Plan-then-execute implementation against SPEC.md. Native single-thread loop, no sub-agents. On test or build failure, auto-invokes the backprop skill before retrying — a failed verification always considers whether a new §V invariant would prevent recurrence. Triggers when the user asks to build, implement, execute the spec, or tackle a specific §T task (`build §T.3`, `build --next`, `implement next task`, `run the build`). Expects SPEC.md to exist; if not, defers to the spec skill.
Launch a meta-judge then a judge sub-agent to evaluate results produced in the current conversation