Agent Academy

Agent Academy is a free, source-linked library of skills, prompts, MCP servers and bot templates, organised into courses by profession, for people who hand real work to AI agents: 1,467 live resources, each with its original link, license and safety tags.

Skill

bash-defensive-patterns

Master defensive Bash programming techniques for production-grade scripts. Use when writing robust shell scripts, CI/CD pipelines, or system utilities requiring fault tolerance and safety.

No credentialsDoes not send

https://github.com/wshobson/agents/blob/main/plugins/shell-scripting/skills/bash-defensive-patterns/SKILL.md

Install
npx skills add wshobson/agents --skill bash-defensive-patterns

Original content

Full originalMITSource

Republished in full under its license, with attribution. The source is authoritative.

name: bash-defensive-patterns
description: Master defensive Bash programming techniques for production-grade scripts. Use when writing robust shell scripts, CI/CD pipelines, or system utilities requiring fault tolerance and safety.

Bash Defensive Patterns

Comprehensive guidance for writing production-ready Bash scripts using defensive programming techniques, error handling, and safety best practices to prevent common pitfalls and ensure reliability.

When to Use This Skill

  • Writing production automation scripts
  • Building CI/CD pipeline scripts
  • Creating system administration utilities
  • Developing error-resilient deployment automation
  • Writing scripts that must handle edge cases safely
  • Building maintainable shell script libraries
  • Implementing comprehensive logging and monitoring
  • Creating scripts that must work across different platforms

Detailed patterns and worked examples

Detailed pattern documentation lives in references/details.md. Read that file when the navigation tier above is insufficient.

Best Practices Summary

  1. Always use strict mode - set -Eeuo pipefail
  2. Quote all variables - "$variable" prevents word splitting
  3. Use [[]] conditionals - More robust than [ ]
  4. Implement error trapping - Catch and handle errors gracefully
  5. Validate all inputs - Check file existence, permissions, formats
  6. Use functions for reusability - Prefix with meaningful names
  7. Implement structured logging - Include timestamps and levels
  8. Support dry-run mode - Allow users to preview changes
  9. Handle temporary files safely - Use mktemp, cleanup with trap
  10. Design for idempotency - Scripts should be safe to rerun
  11. Document requirements - List dependencies and minimum versions
  12. Test error paths - Ensure error handling works correctly
  13. Use command -v - Safer than which for checking executables
  14. Prefer printf over echo - More predictable across systems

Related

SkillSoftware engineering

claude-api

Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`,…

Sourcegithub.com/anthropics/skills/blob/main/skills/claude-api/SKILL.md

No credentialsDoes not sendApache-2.0
SkillSoftware engineering

doc-coauthoring

Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar…

Sourcegithub.com/anthropics/skills/blob/main/skills/doc-coauthoring/SKILL.md

No credentialsDoes not sendnot stated
SkillSoftware engineering

mcp-builder

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Sourcegithub.com/anthropics/skills/blob/main/skills/mcp-builder/SKILL.md

No credentialsDoes not sendApache-2.0
SkillSoftware engineering

skill-creator

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Sourcegithub.com/anthropics/skills/blob/main/skills/skill-creator/SKILL.md

No credentialsDoes not sendApache-2.0
SkillSoftware engineering

webapp-testing

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Sourcegithub.com/anthropics/skills/blob/main/skills/webapp-testing/SKILL.md

No credentialsDoes not sendApache-2.0
SkillSoftware engineering

ai-debt-detector

Use after generating code, after accepting AI suggestions, or when reviewing AI-written modules. Also use when code works but feels brittle, when error handling seems thin, when orphaned resources or missing cleanup are suspected, or when the agent claims done but hidden debt may exist. Catches the specific failure patterns AI agents produce that humans would not.

Sourcegithub.com/wshobson/agents/blob/main/plugins/skill-forge-essentials/skills/ai-debt-detector/SKILL.md

No credentialsDoes not sendMIT