seokan-jeong/team-shinchan

team-shinchan-start

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

Langue du texte source : anglais

team-shinchan-autopilot

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

Langue du texte source : anglais

team-shinchan-backend

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

Langue du texte source : anglais

team-shinchan-bigproject

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

Langue du texte source : anglais

team-shinchan-devops

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

Langue du texte source : anglais

team-shinchan-frontend

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

Langue du texte source : anglais

team-shinchan-implement

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

Langue du texte source : anglais

team-shinchan-micro-execute

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

Langue du texte source : anglais

team-shinchan-ralph

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

Langue du texte source : anglais

team-shinchan-ultrawork

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

Langue du texte source : anglais

team-shinchan-fierce-review

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.

Langue du texte source : anglais

team-shinchan-skill-feedback

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.

Langue du texte source : anglais

team-shinchan-fierce-compete

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.

Langue du texte source : anglais

team-shinchan-fierce-debate

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

Langue du texte source : anglais

team-shinchan-fierce-option-panel

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.…

Langue du texte source : anglais

team-shinchan-fierce-ralph

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.

Langue du texte source : anglais

team-shinchan-review

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

Langue du texte source : anglais

team-shinchan-verify-workflow

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

Langue du texte source : anglais

team-shinchan-verification-before-completion

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

Langue du texte source : anglais

team-shinchan-verify-consistency

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

Langue du texte source : anglais

team-shinchan-resume

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

Langue du texte source : anglais

team-shinchan-debate

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

Langue du texte source : anglais

team-shinchan-analyze

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

Langue du texte source : anglais

team-shinchan-research

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

Langue du texte source : anglais

team-shinchan-eval

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

Langue du texte source : anglais

team-shinchan-help

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

Langue du texte source : anglais

team-shinchan-manage-skills

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

Langue du texte source : anglais

team-shinchan-design-review

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

Langue du texte source : anglais

team-shinchan-version

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

Langue du texte source : anglais

team-shinchan-doctor

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.

Langue du texte source : anglais

team-shinchan-simplify

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.

Langue du texte source : anglais

team-shinchanlint-harness

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

Langue du texte source : anglais

team-shinchananalytics

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

Langue du texte source : anglais

team-shinchanbrainstorm

Use when you need structured problem exploration before writing requirements.

Langue du texte source : anglais

team-shinchanbudget

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

Langue du texte source : anglais

team-shinchandeepsearch

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

Langue du texte source : anglais

team-shinchanforget

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

Langue du texte source : anglais

impact-analysis

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

Langue du texte source : anglais

team-shinchanlearn

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

Langue du texte source : anglais

team-shinchanmemories

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

Langue du texte source : anglais