AI & ML

vinnie357 Bundle

Review a repository's open human-authored pull requests one at a time with a stack-aware agent per PR, build and test each branch locally under baseline-diff gates, and squash-merge on operator approval. Use when a repo has open contributor or collaborator PRs to review and merge, when reviewing external PRs that need local build/test before merge, or when triaging the open PR queue without mistaking pre-existing CI failures for regressions.

gmickel Skill

Export RepoPrompt context to a markdown file for review with an external LLM (ChatGPT, Claude web, etc.). Use when you want Carmack-level review but prefer an external model. Triggers on "export context", "export for external review", "export plan for ChatGPT", "export impl review context", "review with an external model", "export review context".

bitwarden Bundle

Performs a security-focused code review by launching multiple specialized agents and a verification agent to ensure comprehensive coverage and accurate findings. Use this skill when the user asks for a "perform-security-review", "bitwarden-security-review", "execute a security review", "run a comprehensive security audit", "perform an end-to-end security assessment", or needs to coordinate multiple security checks across code, dependencies, secrets, and configurations. The skill manages the workflow, delegates tasks to specialized agents, and presents final findings to the user.

bitwarden Skill

Reviews Claude Code agent definition files for tool-access security, triggering quality, and system prompt clarity. Use when reviewing changes to agents/<name>.md or agents/<name>/AGENT.md, whether under .claude/agents/ or inside a plugin. Flags over-privileged tool grants, unjustified Bash access, descriptions with no activation triggers, and system prompts too vague to act on. Also use when asked to audit a subagent's tool access or check whether an agent will trigger. Normally reached through `reviewing-claude-config`, which runs an always-on secret scan and a finding filter first.

bitwarden Skill

Reviews Claude Code slash command and prompt files for purpose clarity, completeness, shell-execution safety, and correct skill references. Use when reviewing changes to commands/**/*.md at any location, or .claude/prompts/**/*.md. Flags argument interpolation into a shell string, commands with no stated purpose or usage, complex tasks left as one vague instruction, and references to skills that do not exist. Also use when asked to check a slash command or review what a command actually runs. Normally reached through `reviewing-claude-config`, which runs an always-on secret scan and a finding filter first.

bitwarden Skill

Reviews Claude Code settings and hook definitions for security, permission scoping, and command safety. Use when reviewing changes to .claude/settings.json, .claude/settings.local.json, or hooks.json in a repository or plugin. Flags local settings appearing in a changeset, hardcoded secrets, filesystem-wide permissions, dangerous auto-approvals, and hook commands that exfiltrate data or route their input into a shell. Also use when asked to review hooks, audit permissions, or check what runs without a prompt. Normally reached through `reviewing-claude-config`, which runs an always-on secret scan and a finding filter first.

bitwarden Bundle

Perform a rigorous, multi-agent code review with architecture-compliance, parallel quality/security analysis, finding validation, and severity audit. Use when the user asks for a structured, deep, thorough, multi-pass, or multi-agent code review — or a review that includes architecture/pattern compliance, confidence-scored findings, or a severity audit. Use when the user asks for a code review across a commit range, time window, or N most recent commits in a locally checked-out repo.

vinnie357 Bundle

Guide for Phoenix web applications. Use when building Phoenix apps, implementing LiveView, designing contexts, setting up channels, or integrating Tidewave MCP dev tools.

vinnie357 Bundle

Tidewave MCP dev tools for Phoenix applications. Use when setting up Tidewave, connecting AI coding assistants to a running Phoenix app, configuring MCP server access, debugging with runtime introspection tools, or troubleshooting Tidewave integration.

vinnie357 Bundle

Playwright MCP server for Claude Code browser automation. Use when configuring Playwright MCP, automating browser interactions, taking screenshots, researching web content blocked by non-browser clients, testing web UI locally, or navigating web pages from Claude Code sessions.

ahmed3elshaer Skill

Model-View-Intent architecture patterns for Android with unidirectional data flow, state management, and side effects.

vinnie357 Bundle

Guide for coordinating multiple Claude Code agents as teams. Use when setting up agent teams, configuring subagents, orchestrating multi-agent workflows, or building programmatic agent systems with the Claude Agent SDK.

vinnie357 Skill

Use a graphify knowledge graph to give agents low-token codebase context — query the graph instead of reading raw files during research, decomposition, and impact analysis. Use when wiring graphify into an agent-loop, an Explore/research subagent, or an MCP-enabled agent, or when deciding when a graph query beats grepping and reading files.

vinnie357 Bundle

Guide for creating custom agents (subagents) for Claude Code. Use when writing agents/*.md files, choosing agent frontmatter (tools, model, skills, permissionMode, maxTurns), restricting a subagent tool allowlist, preloading skills into an agent, or troubleshooting agent invocation.

vinnie357 Bundle

Guide for creating Agent Skills with progressive disclosure and best practices. Use when creating new skills, understanding skill structure, or implementing progressive disclosure.

protocolsage Skill

Route plain-language requests for Pi, Claude Code, Codex, Cursor, Copilot, OpenClaw ACP, OpenCode, Gemini CLI, Qwen, Kiro, Kimi, iFlow, Factory Droid, Kilocode, or ACP harness work into either OpenClaw ACP runtime sessions or direct acpx-driven sessions ("telephone game" flow). For coding-agent thread requests, read this skill first, then use only `sessions_spawn` for thread creation.

uw-ssec Bundle

GPU-enabled container configuration for NVIDIA CUDA and AMD ROCm workloads including driver compatibility, runtime setup, multi-GPU, and framework-specific images for PyTorch and TensorFlow.

huiali Bundle

GPU 内存与计算专家。处理 CUDA, OpenCL, GPU memory, compute shader, memory coalescing, zero-copy, 显存管理, 异构计算---

huiali Bundle

Actor model expert covering message passing, state isolation, supervision trees, deadlock prevention, fault tolerance, Actix framework, and Erlang-style concurrency patterns.

vinnie357 Bundle

Guide for creating and configuring the Claude Code status line. Use when building a custom status bar, configuring statusLine in settings.json, scripting token/model/git readouts, or debugging status-line output.

vinnie357 Bundle

Guide for creating Claude Code output styles and reusable response-format contracts. Use when creating, shipping, or customizing an output style for a session; defining the response shape an agent, command, or team worker must produce; standardizing worker reports so a team lead can parse them; or deciding between an output style, a skill, and a CLAUDE.md entry.

vinnie357 Skill

Evaluate and benchmark Agent Skills quality using static analysis and evaluation methodology. Use when discussing skill quality, benchmarking skills, measuring activation rates, or reviewing skill effectiveness.

razbakov Skill

Fire-and-forget agent dispatch. Use when user says '/inbox: <task>' or 'inbox <task>'. Spawns a Claude agent in a tmux session with git worktree isolation. Logs everything for retry. Does NOT wait or check on the agent.

razbakov Skill

Check status of all dispatched agents. Use when user says '/scrum'. Lists all wf-* tmux sessions with their status: running, done, failed, needs-input. Reads agent logs and git status.

razbakov Skill

A content-first, mobile-first methodology for creating modern websites. Use this prompt when starting any new website project.

aelaguiz Bundle

Required operating contract for Codex CLI browser work and direct BrowserOS MCP use: protect the user's foreground focus on a shared machine, continually verify the working profile/window/page among many open profiles, reuse existing windows, clean up task-owned pages, and recover the same session safely. Work through viable background methods before necessary brief foreground use; no separate focus approval is required. Codex CLI uses BrowserOS only. Use alongside narrower site skills such as $chatgpt-web. Not for BrowserOS installation/vendor development or generic non-browser connectors.

razbakov Skill

Designs and refactors large SKILL.md agent skills with decision trees, routing maps, gotcha capture, and command orchestration. Use when users ask to create, improve, consolidate, or scale complex skills.

razbakov Skill

Meta skill for browser automation — routes to the right browser tool. Use when you need to automate a browser task and aren't sure which MCP toolset to use (Claude in Chrome vs chrome-devtools vs agent-browser CLI). Also use when writing prompts for agents that need browser access, or when deciding between browser automation approaches.

razbakov Skill

Connect a Telegram bot to any Claude Code agent for collaborative group chats. Use when the user wants to set up a Telegram chat where external people (co-founders, partners, clients) can interact with an AI agent. Triggers include "connect bot to agent", "set up group chat with agent", "add person to agent chat", "envoy connect", or when creating collaborative Telegram groups with AI agents.

razbakov Bundle

Improve an existing Cursor agent skill using prompt engineering best practices. Analyzes a SKILL.md file and rewrites it for clarity, effectiveness, and proper structure. Use when the user asks to improve, refine, optimize, or review a skill.

vishalsachdev Bundle

Create or fix a project's CLAUDE.md using a template that bakes in verification guardrails. Use when starting a new project, when a repo has no CLAUDE.md, when an existing one has grown bloated or stale, or when a non-developer needs their project set up so agents behave safely in it. Produces a short, high-signal file plus the guardrails that catch confident-wrong agent output.

vishalsachdev Bundle

Audit an entire Canvas LMS course against the Four Learning Design Pillars (Clear Structure, Active Content, Continuous Practice, Intuitive UX). Use when users want to evaluate course quality, identify improvement areas, or prepare for course redesign. Requires canvas-mcp server for course data access. Triggers on "audit course", "course review", "evaluate my course", or Canvas course IDs/codes.

vishalsachdev Bundle

Use when delegating OpenAI agent work across GPT-5.6 Sol, Terra, or Luna, especially for new task classes, parallel workers, independent review, model fallback, repeated failures, weak verification, or high-consequence operations.

ninehills Bundle

Lightpanda browser, drop-in replacement for Chrome and Openclaw default browser - faster and lighter for tasks without graphical rendering like data retrieval. Use it via MCP server, CLI fetch, or CDP with Playwright/Puppeteer.

razbakov Skill

Dispatch parallel agents to address review comments on all open PRs. Each agent fixes code, replies inline, resolves threads, and reports what needs human input. Use when user says '/review-all-prs', 'fix all PR reviews', 'address all reviews', or when /scrum shows PRs with pending reviews.

vishalsachdev Bundle

Design Canvas LMS assignments using evidence-based learning science principles from the Four Learning Design Pillars. Use when educators want to create pedagogically sound assignments, need help writing assignment descriptions with clear objectives, want rubric suggestions, or are creating quizzes/discussions/peer reviews. Integrates with canvas-mcp for direct Canvas creation.