Cogni-AI-OU/cogni-ai-agentic-collections - 第 2 页

copilot-cli

Guidance for installing GitHub Copilot CLI on Debian/Ubuntu and executing commands using custom agents. You MUST load this skill when interacting with or installing the copilot-cli command.

原文语言：英语

copilot-docs

Reference and documentation for GitHub Copilot customization and advanced usage. You MUST load this skill when working with Copilot agents, instructions, skills, and configurations.

原文语言：英语

mcp-cli

Interface for MCP (Model Context Protocol) servers via CLI. Use when you need to interact with external tools, APIs, or data sources through MCP servers, list available MCP servers/tools, or call MCP tools from command line.

原文语言：英语

opencode

Manage OpenCode configuration, credentials, and OpenCode Zen API access to list available models and navigate XDG-compliant directory structures. You MUST load this skill when working with OpenCode configuration or listing models.

原文语言：英语

squad-cli

Manage human-led AI agent teams for any project using the Squad CLI. You MUST load this skill when using the squad command.

原文语言：英语

waza-cli

Expert-level guide for using the waza CLI to automate the skill development workflow and run evaluation benchmarks. You MUST load this skill when working with the waza command.

原文语言：英语

waza-docs

Reference and links to the official Microsoft/waza documentation. You MUST load this skill when you need detailed guides, best practices, or reference documentation for the Waza tool.

原文语言：英语

ansible

Execute and manage Ansible playbooks and commands safely, preventing hangs during remote automation. You MUST load this skill when working with the `ansible` command.

原文语言：英语

github-aw-agentics

Expert-level guidance for using, optimizing, and building GitHub Agentic Workflows. Load this skill when the user wants to explore available workflows, understand their internal mechanics, or add new agentic patterns. Focuses on maintenance, automation,…

原文语言：英语

mermaid

Expert guide for creating, optimizing, troubleshooting, and maintaining **stable** Mermaid.js diagrams (v11+). Covers C4, Class, Entity Relationship, Flowchart (with v11.3+ shapes/icons/images), Gantt, GitGraph, Kanban, Mindmap, Pie, Quadrant, Requirement,…

原文语言：英语

software-architecture

Expert-level workflow for software architecture design, covering styles (Monolith, Layered, Microservices, Event-Driven), SOLID principles, design patterns, quality attributes, and architectural decision records.

原文语言：英语

coding

Workflow and guidelines for translating specifications into functional code with precision. Focuses on rapid implementation, syntax accuracy, and strict adherence to defined requirements. You MUST load this skill when acting as a coder focused on writing code…

原文语言：英语

critical-thinking

Engage deep analytical reasoning, follow behavioral guidelines, deconstruct assumptions, apply Socratic questioning, and perform adversarial red-teaming to solve complex problems and validate architectural plans. You MUST load this skill when facing…

原文语言：英语

datadog-docs

Reference, APIs, and programmatic access for Datadog documentation and API. Use for docs retrieval or API interaction with cURL.

原文语言：英语

devops

Core DevOps and Site Reliability Engineering workflow, covering CI/CD, Infrastructure as Code, observability, and deployment strategies.

原文语言：英语

dockerfile

Write, review, and optimize Dockerfiles applying multi-stage builds, non-root constraints, layer caching, and strict image pinning.

原文语言：英语

molecule

How to run and manage Molecule tests for Ansible roles and playbooks. You MUST load this skill when running or managing Molecule tests for Ansible.

原文语言：英语

pulumi-cli

Execute Pulumi CLI commands for stack management, infrastructure deployments, and API interactions. You MUST load this skill when working with the pulumi command.

原文语言：英语

pulumi-docs

Access and fetch Pulumi documentation, registry schemas, and READMEs in markdown format. You MUST load this skill when retrieving Pulumi documentation.

原文语言：英语

development

Workflow and guidelines for full-cycle software development — from requirements gathering and system design through deployment, monitoring, and iteration. Focuses on building and shipping working software that delivers user and business value. You MUST load…

原文语言：英语

npm-cli

Reference and index of documentation pages for npm CLI commands and configurations. You MUST load this skill when interacting with the npm CLI or asking about npm configuration, package.json, or npm scripts.

原文语言：英语

tdd

Commands, step-by-step procedures, and mechanical execution for test engineering, testability audits, and the TDD lifecycle. You MUST load this skill when executing test tasks, designing tests, doing TDD, or verifying system behavior.

原文语言：英语

gh-agent-task

GitHub CLI (`gh agent-task`) operations for creating, listing, and viewing preview agent tasks. You MUST load this skill when working with the `gh agent-task` command.

原文语言：英语

gh-api

Advanced GitHub CLI (`gh api`) queries and mutations via REST or GraphQL. You MUST load this skill when working with the `gh api` command.

原文语言：英语

gh-aw-compile

Regenerate and post-process all agentic workflows. You MUST load this skill when gh-aw is updated, workflow .md files change, or when asked to recompile/regenerate workflows.

原文语言：英语

gh-aw-firewall-debug

Debug the AWF firewall by inspecting Docker containers, analyzing Squid access logs, checking iptables rules, and troubleshooting network issues.

原文语言：英语

gh-aw-firewall

Use the AWF (Agentic Workflow Firewall) to run commands with network isolation and domain whitelisting. Provides L7 HTTP/HTTPS egress control for AI agents.

原文语言：英语

gh-aw-new

Create new GitHub Agentic Workflows (gh-aw) from scratch using the CLI extension. You MUST load this skill when creating new Agentic Workflow files.

原文语言：英语

gh-aw

GitHub Agentic Workflows (`gh aw`) operations for repository automation, creating workflows, running coding agents, and auditing workflow runs. You MUST load this skill when working with the `gh aw` command.

原文语言：英语

gh-aw-troubleshooting

Diagnose and fix GitHub Agentic Workflows (gh-aw) failures by analyzing logs for missing tools, permissions, or MCP server configurations.

原文语言：英语

gh-codespace

GitHub CLI (`gh codespace` or `gh cs`) operations for connecting to, managing, creating, or editing GitHub Codespaces. You MUST load this skill when working with the `gh codespace` command.

原文语言：英语

gh-issue

GitHub CLI (`gh issue`) operations for managing, viewing, and editing issues. You MUST load this skill when working with the `gh issue` command.

原文语言：英语

gh-models

GitHub CLI models (`gh models`) operations for running and evaluating AI models. You MUST load this skill when working with the `gh models` command.

原文语言：英语

gh-pr

GitHub CLI (`gh pr`) operations for pull requests, reviews, PR checks, and PR branches. You MUST load this skill when working with the `gh pr` command.

原文语言：英语

gh-run

GitHub CLI (`gh run` and `gh workflow`) operations for workflow runs, jobs, logs, and attempts. You MUST load this skill when working with the `gh run` and the `gh workflow` commands.

原文语言：英语

gh-search

GitHub CLI (`gh search`) operations for searching code, commits, issues, pull requests, and repositories with structured JSON output. You MUST load this skill when working with the `gh search` command.

原文语言：英语

gh

GitHub CLI (`gh`) operations for issues, pull requests, workflow runs, reviews, or API queries, especially in restricted shells where structured output and fallback choice matter. You MUST load this skill when working with the `gh` command and its subcommands.

原文语言：英语

gh-skill

Expert-level guidance on GitHub CLI (`gh skill`) operations for searching, previewing, installing, updating, and publishing agent skills. You MUST load this skill when managing agent skills via the GitHub CLI.

原文语言：英语

github-actions

Diagnose GitHub Actions workflow failures by retrieving run statuses and logs using MCP tools or gh CLI. You MUST load this skill when diagnosing or debugging GitHub Actions workflow failures.

原文语言：英语

github-aw-memory

Guide for persistent memory strategies in agentic workflows. You MUST load this skill when designing workflows that persist state across runs via cache-memory, repo-memory, or comment-memory.

原文语言：英语