Loading...
Loading...
Found 10,157 Skills
Create and maintain AGENTS.md / CLAUDE.md snippet indexes that route tasks to the correct dotnet-skills skills and agents (including compressed Vercel-style indexes).
Strategies for managing LLM context windows effectively in AI agents. Use when building agents that handle long conversations, multi-step tasks, tool orchestration, or need to maintain coherence across extended interactions.
An AI Agent Skill that enforces a 'Risk Triage -> Align -> Act' protocol. Triggers when requests contain vague verbs ('optimize', 'improve', 'fix', 'refactor', 'add feature'), missing context (no file paths, unknown dependencies), or high-impact actions (deploy, delete, migrate). Prevents 'silent assumptions' through proactive audit.
Always Auto-invoked skill that creates/updates workspace AGENTS.md to instruct the agent to always search for existing skills before attempting any scientific task.
Use this skill proactively and automatically after completing ANY development work. AI agent summarizes: what was done, what was changed/improved, and suggests future additions/improvements - all concisely in Korean.
Conduct web research and material downloading for each node. Read node-list.txt, launch multiple sub-agents to perform parallel web research on node content, deeply retrieve relevant webpages/articles/blogs/literature, download and save them locally, and output a download.txt file to record the material sources for each node. Suitable for document writing scenarios that require extensive background information, data verification, and reference sources.
[Tooling & Meta] Synchronize and update Claude Code and GitHub Copilot development tool configurations to work similarly. Use when asked to update Claude Code setup, update Copilot setup, sync AI dev tools, add new skills/prompts/agents across both platforms, or ensure Claude and Copilot configurations are aligned. Covers skills, prompts, agents, instructions, workflows, and chat modes.
This skill should be used when performing a code review on local changes on the current branch compared to the main branch. It uses multiple parallel agents to check for bugs, CLAUDE.md compliance, git history context, previous PR comments, and code comment adherence, then scores and filters findings by confidence level.
Use when asked to detect silent failures/weak error handling or explicitly asked to run the silent-failure-hunter subagent.
Use when explicitly asked to run the code-reviewer subagent or when another skill requires the code-reviewer agent card.
CX Workflow - Configuration Management. View and modify configuration fields in config.json, such as developer_id, github_sync mode, code review toggle, agent team mode, auto-formatting, etc. Trigger words: config, settings, modify config, change mode. Only execute when the user explicitly calls /cx-config. Do not trigger automatically.
Uncertainty-aware non-linear reasoning system with recursive subagent orchestration. Triggers for complex reasoning, research, multi-domain synthesis, or when explicit commands `/nlr`, `/reason`, `/think-deep` are used. Integrates think skill (reasoning), agent-core skill (acting), and MCP tools (infranodus, exa, scholar-gateway) in recursive think→act→observe loops. Uses coding sandbox for execution validation and maintains deliberate noisiness via NoisyGraph scaffold. Supports `/compact` mode for abbreviated outputs and `/semantic` mode for rich exploration.