Is the Agent System Prompt Architect skill free?

Yes. The skill itself is free from CR-730/agent-system-prompt-architect-skill. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Agent System Prompt Architect SkillProof Score?

8.4/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 3/5.

How do I install Agent System Prompt Architect?

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 System Prompt Architect 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 System Prompt Architect

Turns rough agent requirements into a layered, deployable system prompt.

by CR-730 · CR-730/agent-system-prompt-architect-skill

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.4/10
Tested: Jul 15, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 1419e60

Same expense-tracker system-prompt task: the skill version added concrete tool-call decision criteria and a mandatory disambiguate-before-delete procedure that the baseline only covered as a vague 'confirm before deleting' rule — a real, checkable uplift. The README's headline 0.917-vs-0.554 benchmark number lives in a gitignored evals-workspace/ folder not present in the repo, so it can't actually be verified.

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 3/5

What Agent System Prompt Architect does

Drafts system prompts for other agent projects using a fixed layered architecture (role, scope, tools, output contract, safety, failure handling), with explicit rules for stripping backend/schema jargon out of the agent-facing text. Triggers when a user wants to design, review, or revise a system prompt for an agent, not for generic copywriting or one-off chat prompts.

How to install Agent System Prompt Architect

git clone https://github.com/CR-730/agent-system-prompt-architect-skill.git
cd agent-system-prompt-architect-skill
mkdir -p ~/.claude/skills
cp -r skills/agent-system-prompt-architect ~/.claude/skills/agent-system-prompt-architect

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

Commands — how to trigger Agent System Prompt Architect

/agent-system-prompt-architect Turns rough agent requirements into a layered, deployable system prompt.

It also activates on plain-language prompts like these:

Draft a deployable system prompt for an expense-tracking agent
Review this agent's system prompt and tighten the failure handling section
Strip the backend jargon out of this agent prompt before we deploy it

Frequently asked questions

Is the Agent System Prompt Architect skill free?: Yes. The skill itself is free from CR-730/agent-system-prompt-architect-skill. SkillProof publishes the install command and an independent test verdict at no cost.
Does Agent System Prompt Architect work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 15, 2026. Verdict: Tested · Works. Same expense-tracker system-prompt task: the skill version added concrete tool-call decision criteria and a mandatory disambiguate-before-delete procedure that the baseline only covered as a vague 'confirm before deleting' rule — a real, checkable uplift. The README's headline 0.917-vs-0.554 benchmark number lives in a gitignored evals-workspace/ folder not present in the repo, so it can't actually be verified.
What is the Agent System Prompt Architect SkillProof Score?: 8.4/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 3/5.
How do I install Agent System Prompt Architect?: 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 System Prompt Architect 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.