Converts natural-language descriptions or UI spec files into optimized Google Stitch prompts. Use when creating, refining, or validating design directives for Google Stitch. Follows Stitch best practices with short, directive prompts focused on screens, structure, and visual hierarchy.

Guides decision-making for WPF control authoring including UserControl vs Control vs FrameworkElement selection. Use when creating new controls or evaluating Style/Template/Trigger alternatives.

>

Review test cases for Authorization Endpoint. Covers response_type=code, request parameters (scope, client_id, redirect_uri, state, nonce, prompt, display, max_age), and authorization response per OIDC Core 1.0 Section 3.1.2.

Validate authorization failures including IDOR, privilege escalation, and missing access controls. Test by attempting unauthorized access with lower-privileged credentials. Use when testing CWE-639 (IDOR), CWE-269 (Improper Privilege Management), CWE-862 (Missing Authorization), CWE-863 (Incorrect Authorization), CWE-284 (Improper Access Control), CWE-285 (Improper Authorization), or CWE-425 (Direct Request / Forced Browsing) findings.

用于自动生成 Neptune ACL 申请报文并直接发起申请。支持多环境（BOE, Online-CN, i18n-BD）、多区域选择、源/目标集群指定，并自动处理非 BOE 环境下的 Pre-release 申请。

Auto-generated skill for analysis. Triggers on: analyze this brd, analyze the brd.

Autonomous multi-agent coding with git worktree isolation, QA validation, and memory. Use for complex features requiring autonomous implementation.

>

name: auto-debug

Automatically deploy oh-my-gemini to npm and GitHub

System prompt for automated PR description generation. Used by the runtime module.

Generate comprehensive documentation from codebase analysis - creates README sections, API docs, migration guides, and examples from code

Generate planning documents (기획서) automatically from mockups/MVP sites and project artifacts. This skill orchestrates the entire document generation workflow including crawling, analysis, section generation, validation, and final PPT creation.

Automate detection and removal of duplicate files/functions in TypeScript, JavaScript, and Python projects. Safely refactor imports, validate with tests, and deploy changes with zero risk of breaking the system.

Fix a reported bug end-to-end: reproduce it, add a regression test, implement the minimal fix, create a new git branch, commit using Conventional Commits, push, and open a GitHub PR (prefer gh CLI). Use when the user asks to fix a bug and wants a PR created.

This project migrated from static MODEL_CONFIG to database-backed model storage. Models live in Convex DB, accessed via hooks on client, static helpers on server.

Run linters/formatters on changed files and apply safe, mechanical fixes. Use in Flow 3 and Flow 4.

Merge an existing PR after rebasing, running review-pass, ensuring CI passes, and addressing review comments.

Enable parallel agent execution for multi-domain features with git worktree isolation

Automate version updates and releases for any project type (Node.js, Python, Rust, Unity, Unreal, etc.). Detect project type, update version files, generate CHANGELOG, and handle git operations with cross-platform support.

Error rate monitoring, SLO detection, and notification webhooks for automated rollback triggers. Use when setting up automated deployment rollback, monitoring error rates, configuring SLO thresholds, implementing deployment safety nets, setting up alerting webhooks, or when user mentions automated rollback, error rate monitoring, SLO violations, deployment safety, or rollback automation.

Show current auto session status, progress, and any pending gates. Activates for: auto status, auto status, session status, check auto.

Auto-generated skill from cross-repo pattern - Pattern detected in 19 repositories

Pattern for automated testing with GitHub issue creation and Claude Code auto-fixing. Creates Test → Fail → Issue → Fix → Repeat cycle until tests pass.

Automatically apply improvements to skills and the ecosystem based on system-reviewer findings and best-practices-learner insights. Workflow for automated improvement identification, priority assessment, safe application, validation, and rollback capability. Use when applying systematic improvements, automating enhancement cycles, bulk updating multiple skills, or implementing ecosystem-wide improvements.

auto-validate

Programmatic asset compliance validation using vision analysis and Northcote scorecard. Eliminates manual validation loops—upload image, receive scored JSON with correction prompts in 30 seconds.

自动为当前项目生成或更新 VitePress 文档网站。

Autogenerate constraint checking code from constraints (C-*) that specify system limits, timeouts, dependencies, or environmental requirements. Use when C-* includes technical constraints like timeouts, API limits, or compliance requirements.

Autogenerate formula implementations from formula specifications (F-*). Converts mathematical formulas, calculations, and algorithms into production code with tests. Use when F-* includes formula specifications.

Autogenerate production code from disambiguated business rules (BR-*). Converts BR-* specifications into validators, constants, and logic. Use when requirements have been disambiguated into BR-*, C-*, F-* format.

Autogenerate validation functions from business rules (BR-*) that specify formats, patterns, ranges, or constraints. Use when BR-* includes validation specifications like regex patterns, min/max values, or allowed values.

Comprehensive test automation setup. Test Architecture

Automated IT helper for detecting and fixing code issues. Use when code fails tests, linting, type-checking, or has security vulnerabilities. Enforces strict quality gates before accepting fixes.

Generates standardized quality control reports by aggregating metrics from FastQC, alignment, and other tools using MultiQC. Use when summarizing QC metrics across samples, creating shareable quality reports, or building automated QC pipelines.

Develop and execute automated tests to validate pilot scripts, workflows, and systems. Use when verifying code reliability, performing regression checks, or enforcing quality gates before deployment of pilot deliverables.

How the devbox automatically updates llm-agents (claude-code) via GitHub Actions and systemd timers. Use when debugging update failures or understanding the update flow.

**When this skill is active, I MUST follow these rules:**

Controls Chrome browser: takes screenshots, clicks buttons, fills forms, downloads images, inspects pages, captures network requests, checks console errors, debugs API issues. Use when: 'screenshot', 'click', 'fill form', 'download image', 'check browser', 'look at screen', 'capture page', 'check for errors', 'debug network', 'API failing', 'console errors'. Provides MCP tool discovery for 70 tabz_* browser automation tools.

- **Standalone for Contacts:** Use this skill for Contacts-specific operations (querying, CRUD, groups).

- Standalone for Reminders; reuse `automating-mac-apps` for permissions, shell helpers, and ObjC debugging patterns.

Automates terminal sessions in tmux windows using MCP tools. Use when launching background processes, monitoring builds/servers, sending commands to debuggers (pdb/gdb), interacting with CLI prompts, using interactive commands or commands that require sudo, or orchestrating parallel tasks across multiple terminal sessions.

Design workflow automations using Zapier, Make, n8n, and other automation tools

Best practices for writing reliable browser automation scripts with Intuned. Use when writing, reviewing, or editing automation code, scraping scripts, or browser-based workflows. Provides guidance on selectors, waiting strategies, anti-detection, performance optimization, and SDK patterns.

Professional workflow builder that generates complete, production-ready JSON for any automation platform.

Analyze codebases and generate Claude Code automation infrastructure including commands, scripts, and templates for systematic task execution. Use when the user wants to create reusable automation workflows, generate .claude/commands files, create supporting bash/python scripts, build markdown templates for structured outputs, or establish multi-step task execution frameworks that work across projects.

Expert automation platform error debugger for Power Automate, n8n, Make, Zapier and other workflow platforms. Analyzes JSON flow definitions with error messages, researches official documentation, and generates complete fixed JSON ready for copy-paste. Triggers when user provides error JSON files, workflow JSON with errors, error messages, debug requests, or failing automation content. Returns structured debug report with root cause analysis and working fixed JSON.