Interactive brainstorming with documented thought evolution, multi-perspective analysis, and iterative refinement. Serial execution with no agent delegation.
Clean up merged and stale branches from local and remote repositories. Use when branch list is cluttered or after merging PRs.
Создание git-ветки по стандарту именования с привязкой к analysis chain. Используй при начале работы над задачей — автоматически формирует имя ветки из номера анализа NNNN.
Assess branch readiness for PR submission: full review methodology plus the checks only a local checkout allows
Check the current branch name against convention (type/short-description) and rename it if it drifted.
git ブランチ単位で実装内容を可視化する。対象ブランチとマージ先ブランチの差分を分析し、 変更モジュール・ライブラリ増減・データ/ドメインモデルと直接の関連範囲を Mermaid / D2 / HTML（ノード数で自動選定、--format で明示指定可）の構成図として docs/branch-diagrams/ に出力する。--models…
Crée une nouvelle branche Git à partir de la dernière version de main, avec un préfixe conventionnel feat/ (nouvelle fonctionnalité) ou fix/ (correction de bug).
Compute break-even units, break-even revenue, contribution margin, and margin of safety with the deterministic break-even engine.
Model break-even under multiple scenarios — sensitivity to price, volume, and cost — with CVP graph spec and runway-impact analysis.
Detect breaking changes in Claude Code updates by comparing current API surface against changelog. Maps impacts to specific plugin files.
Demolish bloated code and re-derive it clean, cutting every surface the rebuilt contract does not name.
Protocolo de respuesta ante brechas de seguridad de datos personales. Guía el proceso desde la detección hasta la notificación a la AEPD (72 horas, art.
Full team execution with Lead/Worker/Reviewer agents running all Plans.md tasks end-to-end. Use when running the complete breezing flow with parallel workers.
Publish content to brewpage.app — text, markdown, JSON, file, or multi-file site. Asks namespace and password, returns public URL.
Scans a website to find broken links (404s, 500s). Crawls internal pages, identifies broken outbound links, and reports source pages for easy fixing.
Broken links, 404 errors, dead links, redirect chains, link checker, fix links. Scans the user's codebase for broken internal/external links, redirect chains, mixed-content…
Crawl a domain or sitemap to find broken links (4xx/5xx), orphan pages, and soft-404s — with a prioritised remediation register.
Browse Power Automate environments and flows interactively. Use when the user wants to browse, list, or explore their flows and environments.
Drive a real browser against a URL — capture full-page screenshots, inspect computed styles / ARIA / cursor / overflow per selector, and exercise interactions (open menus, hover…
Extract structured data via stored browser-templates or one-shot DOM queries, with mandatory AIDefence PII + prompt-injection gates before content reaches the model
Fill a web form by mapping field-name → value, with optional template lookup from browser-templates for known forms
Execute a natural-language browser intent via page-agent (browser_act) when the target is easier to describe than to select — degrades gracefully when page-agent or an…
Drive an authentication flow once, sanitize cookies through AIDefence, and vault a reusable cookie handle in browser-cookies for future sessions
Collaborative headed browser session for UI work. Launch Playwright Chromium visible to the user, handle auth, then interactively drive the browser while the user watches and…
Open a named, traced browser session into an RVF cognitive container with a ruvector trajectory recording every action
Replay a recorded session trajectory against the same URL or a mutated variant; uses browser-selectors embedding similarity to recover from DOM drift
Visual + DOM diff between two recorded sessions at matching trajectory step ids; used for visual regression and replay verification
One-shot chained shortcut — fires `/loop 15mins /atmux:bruh you are sentinel, make all teams work, unblock everyone`.
Deep quality review of the Build a Sentence question bank. Use when checking question quality, finding bad questions, auditing the bank, or before deploying.
bucho mode: Direct Claude Code (implementer) and Codex (advisor) via tmux to execute development tasks. Manage the full task lifecycle from birth to user approval.
预算调整审核 — 审核预算调整申请，判断是否批准及批准条件。 适用情形：部门提交预算调整申请（追加或削减）后， 财务部审核调整理由、业务影响和资金来源，输出批准/不批准/附条件批准结论。 核心：调整合理性评估 + 资金来源判断 + 审批层级建议。
预算执行分析 — 分析各科目预算执行进度，识别重大偏差并归因。 适用情形：月度/季度预算执行分析时执行，从 [ERP]/[BK] 获取预算和实际数据， 按科目/部门/产品线分析预算执行偏差，区分"合理偏差"和"须改善偏差"。 核心：执行率分析 + 偏差归因 + 预测调整 + 改善建议。
预算执行监控 — 实时追踪各成本中心的预算执行情况，识别超预算风险。 适用情形：每月固定时间点（如月初 5 日）执行，生成全公司预算执行报告， 识别超预算/执行率异常的部门/科目，供管理层决策。 核心：实际 vs 预算 vs 承诺额三维度分析，输出执行率排名和预警清单。
Wallet-aware grilling — interview me about a plan one question at a time, with each branch of the decision tree framed as a USDC cost impact
Use when the user asks to "check pacing", "am I over/under-spending", "is this campaign on track to hit budget", or "why did spend spike/stall mid-flight"; returns a…
Patterns for finding bugs — anti-patterns from the playbook, edge cases, regression triggers, and common failure modes in agentic systems.
Fix a bug by first consulting the app's documentation to understand structure, then investigating the code to identify and resolve the issue.
Build or extend the Zaravan customer experience panel — sign in / sign up / reset, /account overview, profile, saved addresses, order history and order detail.
Builds new Claude Code agents with consistent structure, enforced standards, and project-aware configuration.
Turn a skill or raw data into an AI-optimized "second brain" skill — a lean SKILL.md map backed by atomized, tagged references and JSON navigation maps.
SPM Build-Check fuer brain-ios. Prueft ob BrainCore kompiliert, listet Warnungen und Fehler strukturiert auf.
Build the Convex project from source. Use when a contributor wants to compile, test, or package Convex.
Coordinate cross-cutting changes, incremental features, and multi-package modifications across the Reactive Agents monorepo.
Build an interactive HTML dashboard with charts, filters, and tables. Use when creating an executive overview with KPI cards, turning query results into a shareable self-contained…
Create, improve, validate, or export publication-quality coursework figures, including Word/A4-ready plots.
Autonomously build a complete Power Automate flow from a description. Use when you need to generate a full flow definition and create it.
Scaffolds a GitHub Actions workflow — a YAML file under `.github/workflows/` — with top-level least-priv `permissions:`, SHA-pinned `uses:`, per-job `timeout-minutes`,…
Build or update the code review knowledge graph. Run this first to initialize, or let hooks keep it updated automatically.
Hilft einem anleitenden Volljuristen, einen praxisbereichsspezifischen Leitfaden zu erstellen, der das Verhalten der studierendengerichteten Skills konfiguriert – Intake- — from…
Use when the user wants to "scaffold a help skill", "add a /
:help command", or "build a plugin index skill", or wants to give a plugin an orientation surface that lists…
Builds a Claude Code hook (event-driven quality gate) with a script and the corresponding settings.json hooks entry.
Создать премиальный лендинг продукта. Sticky-scroll layout — продукт справа, фичи слева. Nude/old-money палитра, Satoshi font, плавные анимации.
Build UI like any website. Use when the user wants to clone, copy, or build something "like" an element on another site (e.g.
Scaffolds a top-level Makefile for repository workflow orchestration — strict-shell header, safety `MAKEFLAGS`, `.PHONY` coverage, self-documenting `help` from `## description`…
Generate musical phrases, chord progressions, beats, jingles, and short pieces via local algorithmic synthesis. Sample-free, license-clean, fully offline.
Scaffold a root-level RESOLVER.md — a dual routing table (filing for writes, context for reads) plus an AGENTS.md pointer and a trigger-eval sidecar at `.resolver/evals.yml`.
Build an interactive HTML review gallery with all generated posts for team review.
Create a Claude Code rule under `.claude/rules/` — a markdown instruction file with optional `paths:` frontmatter for path-scoping.
Generate non-pitched sound effects (UI, impacts, sweeps, foley, ambient textures, retro 8-bit) via local algorithmic synthesis. Outputs 44.1 kHz WAV to Assets/GeneratedSFX/.
Scaffolds a primitive-pair — a matched `build-
` and `check-` skill sharing a single distilled principles doc under `_shared/references/`, plus one…