Menu
Skills dans ce dépôt
SkillsMP a collecté 508 skills depuis oimiragieo/agent-studio. Ouvrez un skill pour examiner sa source et ses détails.
oimiragieo/agent-studioAffichage de 40 skills collectés sur 508.
Audit content and assets for brand compliance — style guide validation, tone of voice checking, visual identity consistency, brand asset management, and cross-channel coherence.
Langue du texte source : anglais
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…
Langue du texte source : anglais
Build tools expert including Vite, Webpack, and bundler configuration
Langue du texte source : anglais
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…
Langue du texte source : anglais
Manage Claude Code --channels sessions (start/stop/status/health) via channel-manager.cjs and terminal-tracker.cjs.
Langue du texte source : anglais
Check voice message pipeline config — verify Whisper, ElevenLabs/OpenAI TTS keys and dependencies.
Langue du texte source : anglais
Generate context-aware quality checklists for code review and QA using IEEE 1028 base standards plus LLM contextual additions
Langue du texte source : anglais
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.
Langue du texte source : anglais
Uses GitHub Actions or GitLab CI for CI/CD implementation.
Langue du texte source : anglais
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…
Langue du texte source : anglais
Cloud and DevOps expert including AWS, GCP, Azure, and Terraform
Langue du texte source : anglais
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.
Langue du texte source : anglais
Cloudflare Workers edge computing — Durable Objects, KV, R2, D1, Workers AI, AI Gateway
Langue du texte source : anglais
Structural code graph queries via CodeGraphContext MCP (tree-sitter + KuzuDB). Find callers, callees, class hierarchies, dead code, and module dependencies.
Langue du texte source : anglais
Code quality expert including clean code, style guides, and refactoring
Langue du texte source : anglais
Semantic code search using Phase 1 vector embeddings and Phase 2 hybrid search.
Langue du texte source : anglais
Use ast-grep for AST-based code pattern matching.
Langue du texte source : anglais
Safe codebase cleanup: delete AI slop, consolidate duplicates, update imports — always test-verified before committing
Langue du texte source : anglais
Creates command files for the Claude Code framework. Commands are user-facing shortcuts that delegate to skills.
Langue du texte source : anglais
Analyze code changes (commits, PRs, diffs) for security vulnerabilities using STRIDE analysis and CWE mapping
Langue du texte source : anglais
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.
Langue du texte source : anglais
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.
Langue du texte source : anglais
AI-based complexity assessment for task analysis. Use when determining the appropriate workflow, phases, and validation depth for a task.
Langue du texte source : anglais
Validate planned changes against local framework rules and policy guardrails before implementation or creation.
Langue du texte source : anglais
Rules pertaining to Composer dependency management, promoting best practices for declaring and updating dependencies.
Langue du texte source : anglais
Requires detailed type annotations for all Python functions, methods, and class members.
Langue du texte source : anglais
Aims for high test coverage using pytest, testing both common and edge cases.
Langue du texte source : anglais
Configuration management techniques
Langue du texte source : anglais
Byzantine consensus voting for multi-agent decision making. Implements voting protocols, conflict resolution, and agreement algorithms for reaching consensus among multiple agents.
Langue du texte source : anglais
Container orchestration expert including Docker, Kubernetes, Helm, and service mesh
Langue du texte source : anglais
Rules for creating and maintaining Dockerfiles.
Langue du texte source : anglais
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…
Langue du texte source : anglais
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.
Langue du texte source : anglais
Estimate per-turn token attribution across 6 categories in Claude Code sessions to show where context budget is spent
Langue du texte source : anglais
Token-range severity zones (Green/Yellow/Orange/Red/Critical) with detection checklist, early warning indicators, and corrective routing actions for context window degradation
Langue du texte source : anglais
Context-Driven Development methodology - treating project context as managed artifacts alongside code for consistent AI interactions and team alignment.
Langue du texte source : anglais
Applies general rules for Convex development, emphasizing schema design, validator usage, index-first query patterns, function registration, and correct handling of system fields.
Langue du texte source : anglais
C++ coding standards and best practices.
Langue du texte source : anglais
Validate whether a proposed new artifact is feasible in the current stack before creator workflows run.
Langue du texte source : anglais
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.
Langue du texte source : anglais