Claude Skills by thevibeworks

github.com/thevibeworks

41 skillsA× 31B× 8C× 20 installs65 views

Agent SkillsAAn open-source Agent Skill that provides Claude with up-to-date API reference material, SDK documentation, and best practices for building applications with the Claude API and Claude Managed Agents.ai-agentsjavascripttypescriptVotes: 0GitHub stars: 50
ExamplesAReplaces ordinary greetings with nautical ones.ai-agentsVotes: 0GitHub stars: 50
Cma McpAThings that aren't obvious from the docs and tend to cost debugging time. ---ai-agentsgoshellVotes: 0GitHub stars: 50
LinearAThings that aren't obvious from the docs and tend to cost debugging time. ---ai-agentsgotestingVotes: 0GitHub stars: 50
Roadtrip PlannerBWork top to bottom. Every step has a verification before the next one starts.ai-agentsgobashVotes: 0GitHub stars: 50
SentryBThings that aren't obvious from the docs and tend to cost debugging time. ---ai-agentspythongoVotes: 0GitHub stars: 50
SlackBThings that aren't obvious from the docs and tend to cost debugging time. ---ai-agentsgodebuggingVotes: 0GitHub stars: 50
Analyzing Financial StatementsAThis skill calculates key financial ratios and metrics from financial statement data for investment analysisai-agentsperformanceVotes: 0GitHub stars: 50
Applying Brand GuidelinesAThis skill applies consistent corporate branding and styling to all generated documents including colors, fonts, layouts, and messagingai-agentsgoVotes: 0GitHub stars: 50
Creating Financial ModelsAThis skill provides an advanced financial modeling suite with DCF analysis, sensitivity testing, Monte Carlo simulations, and scenario planning for investment decisionsai-agentsgotestingVotes: 0GitHub stars: 50
AccessAManage Discord channel access — approve pairings, edit allowlists, set DM/group policy. Use when the user asks to pair, approve someone, check who's allowed, or change policy for the Discord channel.ai-agentsrustbashVotes: 0GitHub stars: 50
ConfigureASet up the Discord channel — save the bot token and review access policy. Use when the user pastes a Discord bot token, asks to configure Discord, asks "how do I set this up" or "who can reach me," or wants to check channel status.ai-agentsgobashVotes: 0GitHub stars: 50
Claude Automation RecommenderAAnalyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers). Use when user asks for automation recommendations, wants to optimize their Claude Code setup, mentions improving Claude Code workflows, asks how to first set up Claude Code for a project, or wants to know what Claude Code features they should use.ai-agentstypescriptgoVotes: 0GitHub stars: 50
Cardputer BuddyAIterate on the Cardputer-Adv MicroPython app bundle (Claude Buddy, Snake, Hello) after the device is already provisioned via m5-onboard. Use when the user wants to add a new app, push a single changed .py without re-flashing, watch device serial logs, or run a one-shot REPL command. Trigger on "add an app", "push to the cardputer", "tail the device", "run on the device", or follow-up work after /maker-setup.ai-agentspythonbashVotes: 0GitHub stars: 50
M5 OnboardBEnd-to-end onboarding for a freshly-plugged-in M5Stack ESP32 device (Cardputer, Cardputer-Adv, Core, CoreS3, Stick) — detect on USB, flash UIFlow 2.0 firmware, and install the Claude Buddy MicroPython app bundle. Use whenever the user plugs in or wants to flash/provision/reset an M5Stack or ESP32 board, or says "m5-onboard go".ai-agentspythongoVotes: 0GitHub stars: 50
Example CommandAAn example user-invoked skill that demonstrates frontmatter options and the skills/<name>/SKILL.md layoutai-agentsbashVotes: 0GitHub stars: 50
Build Mcp AppAThis skill should be used when the user wants to build an "MCP app", add "interactive UI" or "widgets" to an MCP server, "render components in chat", build "MCP UI resources", make a tool that shows a "form", "picker", "dashboard" or "confirmation dialog" inline in the conversation, or mentions "apps SDK" in the context of MCP. Use AFTER the build-mcp-server skill has settled the deployment model, or when the user already knows they want UI widgets.ai-agentstypescriptpythonVotes: 0GitHub stars: 50
Build Mcp ServerAThis skill should be used when the user asks to "build an MCP server", "create an MCP", "make an MCP integration", "wrap an API for Claude", "expose tools to Claude", "make an MCP app", or discusses building something with the Model Context Protocol. It is the entry point for MCP server development — it interrogates the user about their use case, determines the right deployment model (remote HTTP, MCPB, local stdio), picks a tool-design pattern, and hands off to specialized skills.ai-agentstypescriptpythonVotes: 0GitHub stars: 50
Build McpbAThis skill should be used when the user wants to "package an MCP server", "bundle an MCP", "make an MCPB", "ship a local MCP server", "distribute a local MCP", discusses ".mcpb files", mentions bundling a Node or Python runtime with their MCP server, or needs an MCP server that interacts with the local filesystem, desktop apps, or OS and must be installable without the user having Node/Python set up.ai-agentstypescriptpythonVotes: 0GitHub stars: 50
Agent DevelopmentAThis skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.ai-agentsgobashVotes: 0GitHub stars: 50
Command DevelopmentAThis skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.ai-agentstypescriptgoVotes: 0GitHub stars: 50
Mcp IntegrationAThis skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context Protocol", "connect external service", mentions "${CLAUDE_PLUGIN_ROOT} with MCP", or discusses MCP server types (SSE, stdio, HTTP, WebSocket). Provides comprehensive guidance for integrating Model Context Protocol servers into Claude Code plugins for external tool and service integration.ai-agentspythongoVotes: 0GitHub stars: 50
Assistant UiBThings that aren't obvious from the docs and tend to cost debugging time. If you're Claude driving setup for a user, walk the **Setup checklist** and use the rest for reference when something looks off. ---ai-agentsrustgoVotes: 0GitHub stars: 50
Chat SdkAThings that aren't obvious from the docs and tend to cost debugging time. ---ai-agentsrustgoVotes: 0GitHub stars: 50
Knowledge WikiAFollow these steps in order when the user asks you to set up or run this cookbook. Confirm each step's output before moving to the next.ai-agentspythongoVotes: 0GitHub stars: 50
MiningAWhere diamonds spawn in Minecraft 1.20.ai-agentsgoVotes: 0GitHub stars: 50
EdgartoolsAHow to pull SEC EDGAR data with the edgartools Python package — company lookup, filings, XBRL financial statements, and filing sections like Item 1A risk factors. Use whenever a task involves SEC filings, 10-K/10-Q data, or company financials.ai-agentspythongoVotes: 0GitHub stars: 50
Incident Triage RunbookAThe SRE team's runbook for triaging production latency and error-rate incidents. Use this whenever investigating an incident, a latency spike, elevated error rates, or when asked "what caused X" about a production service.ai-agentsgoapiVotes: 0GitHub stars: 50
Math OlympiadA1. **Strip thinking before verifying** — a verifier that sees the reasoning is biased toward agreement. Fresh context, cleaned proof only. 2. **"Does this prove RH?"** — if your theorem's specialization to ζ is a famous open problem, you have a gap. Most reliable red flag. 3. **Short proof → extract the general lemma** — try 2×2 counterexamples. If general form is false, find what's special about THIS instance. 4. **Same gap twice → step back** — the case split may be obscuring a unifieai-agentspythongoVotes: 0GitHub stars: 50
Session ReportAGenerate an explorable HTML report of Claude Code session usage (tokens, cache, subagents, skills, expensive prompts) from ~/.claude/projects transcripts.ai-agentsgonodeVotes: 0GitHub stars: 50
LinearBThings that aren't obvious from the docs and tend to cost debugging time. ---ai-agentsrustgoVotes: 0GitHub stars: 50
Mcp Server TypescriptBThings that aren't obvious from the docs and tend to cost debugging time. ---ai-agentstypescriptrustVotes: 0GitHub stars: 50
Roadtrip PlannerCWork top to bottom. Every step has a verification before the next one starts.ai-agentsgoshellVotes: 0GitHub stars: 50
SentryAThings that aren't obvious from the docs and tend to cost debugging time. Use the checklist at the bottom when walking someone through the quickstart. ---ai-agentspythongoVotes: 0GitHub stars: 50
SlackBThings that aren't obvious from the docs and tend to cost debugging time. ---ai-agentsrustgoVotes: 0GitHub stars: 50
OpenshellCSet up NVIDIA OpenShell as the self-hosted sandbox for Claude Managed Agents, step by step. Covers the host check, installing OpenShell, creating the agent and environment, running a first session, confirming the policy held, and changing policy.yaml for your own agent. Use when someone asks to set up, run, adapt, or debug this quickstart, or asks where the OpenShell policy reference is.ai-agentsgoshellVotes: 0GitHub stars: 50
Hn DigestAGenerate HN digests in org-mode format. Use when curating Hacker News stories, creating digests, or converting between JSON/org/HTML formats.ai-agentspythongoVotes: 0GitHub stars: 16
Cctrace InsightsAAnswer usage questions over the user's cctrace trace store — "how is my prompt caching doing this week", "where did my quota / money go", "which session is the heavy one", "am I getting the most out of my Claude subscription", "usage report for the last N days". cctrace computes the windowed wire facts (`cctrace insights --json`): runs/tokens/estimated cost by day, project, client and model, the cache read/write split, the heaviest sessions, and the account-quota percentages the client polled...ai-agentsgobashVotes: 0GitHub stars: 9
Cctrace TitleAName cctrace sessions with human titles by fanning the work out across Claude Code subagents. Use whenever the user wants to title, name, label, or rename their cctrace traces / sessions — "title my sessions", "name the untitled traces", "give these runs proper names", "title everything in the store", "rename this session". cctrace extracts each session's spine (the human's prompts + the agent's final answers, no tool calls, no sub-agent context); this skill turns those digests into titles an...ai-agentsbashVotes: 0GitHub stars: 9
CctraceATrace, inspect, and replay Claude Code's HTTP traffic with cctrace — a TLS-intercepting tracer with a live web UI. Use this skill whenever the user wants to see what Claude Code sends over the wire (system prompts, tools, token usage, cache hits, cost, usage limits, errors), debug a Claude Code session ("why did it do that", "what did the agent see", "why is my cache hit rate low", "how much did that session cost"), capture API traffic for a bug report, replay or share a captured session, wor...ai-agentspythonrustVotes: 0GitHub stars: 9
Cctrace DoctorADiagnose a traced agent session's CONTEXT: what the model's window is made of, what in it is dead weight, duplicated, or harness noise, and what to change so the next session spends its attention on the task. Use when the user asks "what is eating my context", "why is this session so heavy", "context doctor", "audit the context", "what's duplicated in the window", "is my CLAUDE.md too big", "which tools/MCP servers cost me tokens", "context health", "doctor this session", or wants a context r...ai-agentsgobashVotes: 0GitHub stars: 9