Is the Agentic Coach skill free?

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

What is the Agentic Coach SkillProof Score?

9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.

How do I install Agentic Coach?

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 Agentic Coach 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.

Agentic Coach

Scores a vague prompt on 6 dimensions and asks Socratic questions instead of silently rewriting and running it.

by cgbarlow · cgbarlow/skills

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 9.2/10
Tested: Jul 15, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · a99c410

Gave it the vague prompt 'build a login system': default (no-skill) behavior would proceed straight to implementation with assumed defaults, while following the skill body produced a scored 6-dimension assessment, three concrete clarifying questions (app type, auth method, compliance needs), and an explicit hold on execution -- the stop-and-ask gate it advertises is real, not just a description claim.

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

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 8/10
Docs & honesty 5/5

What Agentic Coach does

Interactive prompt-engineering coach that scores a user's prompt across clarity, structure, agentic readiness, completeness, executability, and learning value, asks clarifying questions, offers 5 transformation styles (quick fix, full agentic, learning mode, domain-specific, iterative), and always stops for an explicit Execute/Modify/Regenerate/Learn/Save decision before anything runs. Triggers when a user wants help improving a prompt or learning prompt-engineering principles rather than getting an instant rewrite.

How to install Agentic Coach

git clone https://github.com/cgbarlow/skills
mkdir -p ~/.claude/skills
cp -r skills/skills/agentic-coach ~/.claude/skills/agentic-coach

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

Commands — how to trigger Agentic Coach

/agentic-coach Scores a vague prompt on 6 dimensions and asks Socratic questions instead of silently rewriting and running it.

It also activates on plain-language prompts like these:

Coach me through improving this vague prompt instead of rewriting it.
Teach me the principles behind writing good agentic prompts.
Assess my prompt and walk me through making it more executable.

Frequently asked questions

Is the Agentic Coach skill free?: Yes. The skill itself is free from cgbarlow/skills. SkillProof publishes the install command and an independent test verdict at no cost.
Does Agentic Coach work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 15, 2026. Verdict: Tested · Works. Gave it the vague prompt 'build a login system': default (no-skill) behavior would proceed straight to implementation with assumed defaults, while following the skill body produced a scored 6-dimension assessment, three concrete clarifying questions (app type, auth method, compliance needs), and an explicit hold on execution -- the stop-and-ask gate it advertises is real, not just a description claim.
What is the Agentic Coach SkillProof Score?: 9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.
How do I install Agentic Coach?: 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 Agentic Coach 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.