Coding & Development

Code review focused exclusively on over-engineering. Finds what to delete: reinvented standard library, unneeded dependencies, speculative abstractions, dead flexibility. One line per finding: location, what to cut, what replaces it. Use when the user says "review for over-engineering", "what can we delete", "is this over-engineered", "simplify review", or invokes /ponytail-review. Complements correctness-focused review, this one only hunts complexity.

Verify completion and success claims with fresh evidence. Use before claiming a task is complete, a fix works, tests pass, or a feature is ready for GO.

Extend this plain site's capabilities — add a collection or a field, add a page layout or template, write a plugin, apply a starter, or run an engine upgrade or a content import. Use for "add a testimonials section", "posts need an author field", "write a plugin that…", "add a landing page", "update the engine", "import my old blog".

Validate feature-level integration after all tasks are implemented. Checks cross-task consistency, full test suite, and overall spec coverage.

Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on source code — never implements, fixes, or refactors anything itself. Use when asked to audit a codebase, find improvement opportunities (bugs, security, performance, test coverage, tech debt, migrations, DX), suggest features or where to take the project next (roadmap, product direction), or generate handoff plans for another agent to implement.

Analyze implementation gap between requirements and existing codebase

Manage .kiro/steering/ as persistent project knowledge

Create custom steering documents for specialized project contexts

Create comprehensive technical design for a specification

Quick spec generation with interactive or automatic mode

Create complete specs (requirements, design, tasks) for all features in roadmap.md using parallel sub-agent dispatch by dependency wave.

Show specification status and progress

Generate implementation tasks for a specification

Initialize a new specification with detailed project description

Implement approved tasks using TDD with subagent dispatch. Runs all pending tasks autonomously or selected tasks manually.

Interactive technical design quality review and validation

Review a task implementation against approved specs, task boundaries, and verification evidence. Use after an implementer finishes a task, after remediation, or before accepting a task as complete.

Generate comprehensive requirements for a specification

Read-only queue dashboard for workspace-aware ship. (gstack)

Convert existing tasks into actionable, dependency-ordered GitHub issues for the feature based on available design artifacts.

Entry point for new work. Determines the best action path or work decomposition (update existing spec, create new spec, mixed decomposition, or no spec needed) and refines ideas through structured dialogue.

开源组件升级监测与执行技能。触发语：「升级开源组件」「扫描开源组件更新」「执行开源组件更新计划」「升级 DeepSeek Harness 等底座依赖」。提供「清单登记 → 周期扫描 → 更新计划 → 一键执行 → 全量门禁 → 发布」完整闭环。任何 AI Coding Agent 克隆本仓库后可直接使用。

Revisa seguridad arquitectónica, identidad, autorización, secretos, APIs, auditoría, fraude y resiliencia antes de implementar.

WorkLoom 发布上线前三链路校验门禁（强制红线，自动调用）。凡是使用 WorkLoom 底座的产品（WorkLoom GEO / HyperReality / 酒店等）交付或更新版本前，必须执行三条主链路全量回归：ASK 问答模式、QUEST 任务模式、自动化任务编排。任一未过 = 禁止发布。触发场景：发布、上线、交付版本、push 前检查、release、发版。