oimiragieo/agent-studio - 第 3 页

brand-compliance

Audit content and assets for brand compliance — style guide validation, tone of voice checking, visual identity consistency, brand asset management, and cross-channel coherence.

原文语言：英语

browser-automation

Programmatic web automation using Playwright Python — data extraction, form filling, multi-step workflows, auth session management, screenshot/PDF capture, and anti-detection patterns. Use for scripted automation tasks, not interactive MCP-based browser…

原文语言：英语

build-tools-expert

Build tools expert including Vite, Webpack, and bundler configuration

原文语言：英语

building-secure-contracts

Smart contract and secure API contract security analysis — invariant checking, access control, reentrancy, and integer overflow patterns. Implements Checks-Effects-Interactions pattern, formal invariant verification, and OpenSCV vulnerability taxonomy for…

原文语言：英语

channel-management

Manage Claude Code --channels sessions (start/stop/status/health) via channel-manager.cjs and terminal-tracker.cjs.

原文语言：英语

check-telegram-voice

Check voice message pipeline config — verify Whisper, ElevenLabs/OpenAI TTS keys and dependencies.

原文语言：英语

checklist-generator

Generate context-aware quality checklists for code review and QA using IEEE 1028 base standards plus LLM contextual additions

原文语言：英语

chrome-browser

Browser automation with two integrations - Chrome DevTools MCP (always available, performance tracing) and Claude-in-Chrome extension (authenticated sessions, GIF recording). Use DevTools for testing/debugging, Claude-in-Chrome for authenticated workflows.

原文语言：英语

ci-cd-implementation-rule

Uses GitHub Actions or GitLab CI for CI/CD implementation.

原文语言：英语

claude-api

Build apps with the Claude API or Anthropic SDK. TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`/`claude_agent_sdk`, or user asks to use Claude API, Anthropic SDKs, or Agent SDK. DO NOT TRIGGER when: code imports `openai`/other AI SDK, general…

原文语言：英语

cloud-devops-expert

Cloud and DevOps expert including AWS, GCP, Azure, and Terraform

原文语言：英语

cloud-run

Google Cloud Run deployment, service management, traffic splitting, and log inspection. Use when deploying containerized apps to Cloud Run, managing services, or inspecting Cloud Run logs.

原文语言：英语

cloudflare-workers

Cloudflare Workers edge computing — Durable Objects, KV, R2, D1, Workers AI, AI Gateway

原文语言：英语

code-graph-context

Structural code graph queries via CodeGraphContext MCP (tree-sitter + KuzuDB). Find callers, callees, class hierarchies, dead code, and module dependencies.

原文语言：英语

code-quality-expert

Code quality expert including clean code, style guides, and refactoring

原文语言：英语

code-semantic-search

Semantic code search using Phase 1 vector embeddings and Phase 2 hybrid search.

原文语言：英语

code-structural-search

Use ast-grep for AST-based code pattern matching.

原文语言：英语

codebase-cleaner

Safe codebase cleanup: delete AI slop, consolidate duplicates, update imports — always test-verified before committing

原文语言：英语

command-creator

Creates command files for the Claude Code framework. Commands are user-facing shortcuts that delegate to skills.

原文语言：英语

commit-security-scan

Analyze code changes (commits, PRs, diffs) for security vulnerabilities using STRIDE analysis and CWE mapping

原文语言：英语

commit-validator

Validates commit messages against Conventional Commits specification using programmatic validation. Replaces the git-conventional-commit-messages text file with a tool that provides instant feedback.

原文语言：英语

compaction-detector

Detect Claude Code context compaction events in session JSONL logs. Identifies compaction boundaries, measures token delta before/after, reports compaction events with timestamps and token impact.

原文语言：英语

complexity-assessment

AI-based complexity assessment for task analysis. Use when determining the appropriate workflow, phases, and validation depth for a task.

原文语言：英语

compliance-policy-check

Validate planned changes against local framework rules and policy guardrails before implementation or creation.

原文语言：英语

composer-dependency-management

Rules pertaining to Composer dependency management, promoting best practices for declaring and updating dependencies.

原文语言：英语

comprehensive-type-annotations

Requires detailed type annotations for all Python functions, methods, and class members.

原文语言：英语

comprehensive-unit-testing-with-pytest

Aims for high test coverage using pytest, testing both common and edge cases.

原文语言：英语

configuration-management

Configuration management techniques

原文语言：英语

consensus-voting

Byzantine consensus voting for multi-agent decision making. Implements voting protocols, conflict resolution, and agreement algorithms for reaching consensus among multiple agents.

原文语言：英语

container-expert

Container orchestration expert including Docker, Kubernetes, Helm, and service mesh

原文语言：英语

containerization-rules

Rules for creating and maintaining Dockerfiles.

原文语言：英语

content-analyzer

Use when analyzing published content (blog posts, social media, newsletters) for sentiment, structural quality, hook effectiveness, readability, topic classification, and engagement correlation. Invoke for daily post analysis, content audits, or engagement…

原文语言：英语

content-security-scan

Automated security scanner for external skill/agent content fetched from GitHub or web sources. Runs a 7-step PASS/FAIL security gate against fetched markdown/text content.

原文语言：英语

context-attribution

Estimate per-turn token attribution across 6 categories in Claude Code sessions to show where context budget is spent

原文语言：英语

context-degradation

Token-range severity zones (Green/Yellow/Orange/Red/Critical) with detection checklist, early warning indicators, and corrective routing actions for context window degradation

原文语言：英语

context-driven-development

Context-Driven Development methodology - treating project context as managed artifacts alongside code for consistent AI interactions and team alignment.

原文语言：英语

convex-development-general

Applies general rules for Convex development, emphasizing schema design, validator usage, index-first query patterns, function registration, and correct handling of system fields.

原文语言：英语

cpp

C++ coding standards and best practices.

原文语言：英语

creation-feasibility-gate

Validate whether a proposed new artifact is feasible in the current stack before creator workflows run.

原文语言：英语

cron-decision

Decision framework for agents to determine WHEN and WHETHER to use Claude Code's native cron scheduler (CronCreate/CronList/CronDelete) vs OS cron, GitHub Actions, or simple Task() delegation.

原文语言：英语