Is the Agent Development skill free?

Yes. The skill itself is free from troykelly/claude-skills. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Agent Development SkillProof Score?

8.0/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 2/5.

How do I install Agent Development?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Agent Development with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Agent Development

Reference guide for writing Claude Code subagent .md files: frontmatter, triggering examples, system prompts.

by troykelly · troykelly/claude-skills

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.0/10
Tested: Jul 16, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 075a5df

The written guidance produces a genuinely well-structured agent file (multi-line description with <example>/<commentary> blocks, second-person system prompt, least-privilege tools) versus a naive hand-written baseline missing all of that - but the one bundled tool, validate-agent.sh, chokes on that exact recommended multi-line-description format (single-line grep extraction) and exits early on its own set -e + ((warning_count++)) bug, and the second promised script, scripts/test-agent-trigger.sh, isn't in the repo at all.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 4/5
Triggers reliably 5/5
Output vs. baseline 9/10
Docs & honesty 2/5

What Agent Development does

Documents the full agent file format for Claude Code plugins - required frontmatter fields (name, description, model, color, tools), how to write triggering <example> blocks in the description, and a system-prompt template (responsibilities/process/output/edge cases). Triggers when a user wants to create, write, or fix a subagent, its frontmatter, or its triggering description.

How to install Agent Development

git clone https://github.com/troykelly/claude-skills
mkdir -p ~/.claude/skills
cp -r claude-skills/external/skills/agent-development ~/.claude/skills/agent-development

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Agent Development

/agent-development Reference guide for writing Claude Code subagent .md files: frontmatter, triggering examples, system prompts.

It also activates on plain-language prompts like these:

Write a subagent file for a dedicated code-review specialist
Help me fix the frontmatter on my custom Claude Code subagent
Draft triggering example blocks for my new agent's description

Frequently asked questions

Is the Agent Development skill free?: Yes. The skill itself is free from troykelly/claude-skills. SkillProof publishes the install command and an independent test verdict at no cost.
Does Agent Development work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 16, 2026. Verdict: Tested · Works. The written guidance produces a genuinely well-structured agent file (multi-line description with <example>/<commentary> blocks, second-person system prompt, least-privilege tools) versus a naive hand-written baseline missing all of that - but the one bundled tool, validate-agent.sh, chokes on that exact recommended multi-line-description format (single-line grep extraction) and exits early on its own set -e + ((warning_count++)) bug, and the second promised script, scripts/test-agent-trigger.sh, isn't in the repo at all.
What is the Agent Development SkillProof Score?: 8.0/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 2/5.
How do I install Agent Development?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Agent Development with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.