team-shinchan

Use when you have a large-scale, multi-phase project requiring orchestrated execution.

Use when you need persistent looping until a task is fully complete.

Deterministic adversarial code review for high-stakes scope — independent per-dimension review, a non-skippable per-finding refutation, completeness + interaction critics, and a deterministic 3-lens rubric judge panel. Opt-in main-loop Workflow tier.

Use when the user wants to review accumulated skill feedback, verdict trends, or improvement candidates collected during Stage 4 retrospectives. Trigger on "show skill feedback", "스킬 피드백 보여줘", or finding which skills need /writing-skills work.

Deterministic competitive code tournament — N builders independently solve one task and return patches, an Action-Kamen judge scores them head-to-head, the winner is picked by score and applied. Opt-in main-loop Workflow tier.

Deterministic adversarial debate for high-stakes or irreversible decisions — mandatory refutation plus a scored judge panel. Opt-in main-loop Workflow tier.

Default-on interview option-quality panel — N diverse generators produce structure-free options, a SelfCheckGPT majority-vote consensus filters hallucinations, a SteerConf cautious-confidence judge scores survivors, and a deterministic top-K is returned. Workflow tier; the single fierce-* skill that is ON by default.

Deterministic loop-until-done for high-stakes long-running tasks — a worker/verifier loop the script bounds by iteration cap, token budget, and stagnation, closed by an Action-Kamen gate. Opt-in main-loop Workflow tier.

Use when you need code review, verification, or quality checks on your work.

Use when you want to start a new task with the integrated workflow.

Use when you need to validate workflow state schema or error handling.

Use when claiming a task is complete, before commits, or before PR creation.

Use when you need to validate cross-references, stage matrix, or debate consistency.

Use when you need to resume an interrupted workflow from where it left off.

Use when you want multiple agents to debate and find optimal solutions.

Use when you need deep analysis of code, bugs, performance, or architecture issues.

Use when you need micro-task execution with per-task two-stage review.

Use when you need web research, documentation lookup, or knowledge gathering.

Use when you need backend development for APIs, databases, servers, or endpoints.

Use when you need to view agent evaluation history or detect performance regressions.

Use when you need guidance on Team-Shinchan agents, skills, or memory system.

Use when you need quick code implementation for features, bug fixes, or utilities.

Use when you need to complete tasks quickly with parallel agent execution.

Use when you need to analyze changes and ensure verify-* skill coverage.

Use when you want autonomous completion from requirements to verification without intervention.

Use when you need to compare design mockups against implementation for UI fidelity.

Use when you need to check the current plugin version, latest published release, and what changed between them.

Use when you need to diagnose the health of a team-shinchan project setup. Runs 7 deterministic checks (workflow state, hooks config, core scripts, runtime files, test directory) and reports PASS/WARN/FAIL per check with remediation hints.

Use when you need to detect or remove AI slop from text — filler openers, hedge stacks, redundant qualifiers, and emoji clusters. Scans stdin or a file and optionally rewrites clean output.

Use when you need to run plugin consistency checks or drift detection.

Use when you need to analyze work tracker data for agent metrics or session stats.

Use when you need structured problem exploration before writing requirements.

Use when you need to view or manage workflow turn budgets and limits.

Use when you need deep codebase exploration to find code, patterns, or references.

Use when you need DevOps work like CI/CD, Docker, deployment, or pipelines.

Use when you need to delete specific outdated or incorrect memories.

Use when you need frontend development for UI components, React, CSS, or styling.

Use when you need to analyze cascade impact of changing a component.

Use when you want to manually add new learnings or rules to memory.

Use when you need to view or manage learned memories and preferences.