Trending Agent Skills
1084 skills24-hour trending
Provision Microsoft Entra Agent Identity Blueprints, BlueprintPrincipals, and per-instance Agent Identities via Microsoft Graph, and configure OAuth 2.0 token exchange (fmi_path, OBO, cross-tenant) including the Microsoft Entra SDK for AgentID sidecar.
Assess and improve the reliability of Azure Functions and Azure App Service, including zone redundancy, storage redundancy, health probes, and multi-region failover.
Generates ultra-compressed commit messages in Conventional Commits format, preserving intent and reasoning.
Deploy Python (Flask/Django/FastAPI) code to Azure App Service Linux.
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens while preserving all technical substance, code, URLs, and structure.
Author a HyperFrames slideshow with discrete slides, fragment reveals, branching, hotspot navigation, and presenter mode with speaker notes.
The remotion-markup skill provides best practices for writing Remotion React markup, covering animation, media, timing, and effects.
Wind MCP skill for authoritative financial data, covering A-shares, HK, US stocks, funds, bonds, macro indicators, and more via local CLI.
cavecrew is a decision guide for delegating to three caveman-style subagents with compressed output to save main context.
Assess whether source code is ready to deploy to Azure — the check BEFORE infrastructure work, evaluating build health, app completeness, dependencies, and deployment feasibility.
Import Figma designs into HyperFrames compositions, including rendered assets, brand tokens, components, and motion.
Search and read current Remotion documentation to get accurate API information.
The caveman-review skill generates ultra-compressed code review comments, each one line with location, problem, and fix.
Create, enhance, and upgrade Google ADK agent projects using agents-cli scaffold commands, with prototype-first workflow and multiple deployment targets.
Provides a quick reference for ADK (Agent Development Kit) Python API patterns, code examples, and reference recipes for writing agent code, adding tools, creating callbacks, and state management.
The google-agents-cli-workflow skill provides a complete workflow for building, evaluating, deploying, publishing, and monitoring agents using ADK.
Publish ADK agents to Gemini Enterprise using the agents-cli publish gemini-enterprise command, and manage agents and MCP servers in Agent Registry.
Configure observability for deployed ADK agents, including Cloud Trace, prompt-response logging, BigQuery Agent Analytics, and third-party integrations.
Run evaluations, write datasets, analyze failures, and optimize ADK agents with agents-cli, covering metrics, dataset schema, and LLM judging.
Deploy ADK agents to Agent Runtime, Cloud Run, or GKE using agents-cli, covering CI/CD, secrets, and troubleshooting.
Structure Remotion markup in a specific way so that Remotion Studio can recognize the code structure and make it interactive.
The caveman-help skill provides a quick-reference card for all caveman modes, skills, and commands, displayed one-shot without persistence.
Upgrade Remotion and related packages, ensuring version consistency and Mediabunny compatibility.
Remotion Maps provides multiple map animation techniques, including static maps, Mapbox, MapLibre, MapTiler, and CesiumJS.
The caveman-stats skill shows real token usage and estimated savings for the current session, reading directly from the Claude Code session log and triggered by /caveman-stats.
Build apps with Remotion, from simple forms to complex video editors, with various rendering options.
Turn ideas into fully formed designs and specs through collaborative dialogue before any creative work begins.
caveman-explore is a read-only repository explorer that quickly locates code and returns compact path:line citations.
Review a Caveman learn report, apply cost-lowering fixes with per-edit consent, and report savings with attribution.
Automate browser interactions, test web pages, and work with Playwright tests via a command-line interface.
Turn Caveman's report-only repository observations into an operator-chosen optimization candidate with a paired baseline/candidate evaluation.
Safe refactor skill: restructure code while preserving behavior, guided by verification boundaries.
Diagnose ambiguous failures before editing, rank hypotheses by evidence, and report cause with proof.
Discover every LLM workflow in the current repository and label it, so Caveman Cloud groups spend by what the code actually does.
Fix bugs and small behavior changes at the narrowest responsible layer, ensuring regression proof and relevant tests pass.
Prove existing work meets acceptance conditions without expanding scope, for validation-only tasks, completion checks, focused gate runs, and last-mile proof.
Build feature work leanly, avoiding overengineering with a clear scope and stop condition.
Review Caveman Cloud evidence read-only: costs, Cave Score, Cave Plan, workflows, traces, latency, errors, compression, and verified savings.
Inspect Caveman Cloud's eval-gated experiment lifecycle and block unsafe execution.
Wire the current repository through the Caveman Cloud gateway to measure every LLM request — cost, tokens, latency — with zero behavior change.
Implement reversible compatibility-safe transitions for schema, data, API, protocol, configuration, or dependency migrations requiring rollback and preservation proof.
Cloudflare Workers official CLI for developing, deploying, and managing Workers and their bound services.
Systematic debugging skill: investigate root cause before proposing fixes, follow four phases, avoid symptom fixes.
Reviews and authors Cloudflare Workers code against production best practices, covering configuration, request handling, architecture, observability, code patterns, and security.
Manage GitHub issues locally as Markdown files for triaging, searching, editing, and creating without leaving your editor or terminal.
Create and review Cloudflare Durable Objects for stateful coordination, RPC methods, SQLite storage, alarms, and WebSockets.