Is the Prompt Discipline skill free?

Yes. The skill itself is free from Skillproofdev/prompt-discipline. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Prompt Discipline SkillProof Score?

8.0/10 — installs cleanly 5/5, triggers reliably 4/5, output vs. baseline 6/10, docs & honesty 5/5.

How do I install Prompt Discipline?

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 Prompt Discipline 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.

Prompt Discipline

Diagnose the failure first, then make the smallest fix — no magic-template rewrites.

by SkillProof · Skillproofdev/prompt-discipline

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.0/10
Tested: Jul 11, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Jul 18, 2026 · a9f76bf

Our own skill — tested under the same protocol, disclosed. Bench: 10 flawed prompts x 3 arms (original / plain-Claude rewrite / skill rewrite), n=1 per case. The skill rewrite beat the base rewrite on success (0.90 vs 0.80), format-compliance (0.80 vs 0.70), and added less than half the prompt bloat (+44.5 vs +99.5 words median) — but the margin rests almost entirely on one case (case-06) and the skill still lost case-09, so this is a modest, narrow, unreplicated (n=1) win rather than a decisive one. Protocol test caught real issues in our own repos (dead benchmark links, strict-YAML frontmatter) — fixed and re-verified same day.

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

Installs cleanly 5/5
Triggers reliably 4/5
Output vs. baseline 6/10
Docs & honesty 5/5

What Prompt Discipline does

Prompt Discipline treats a prompt like a bug report: it names the failure mode (ambiguity, missing context, no output contract, conflicting instructions, over-prompting) before touching anything, then applies the smallest fix per finding with an old-to-new rationale instead of a wholesale rewrite. Every response ends with a concrete A/B test plan — pass criteria and revert order — instead of a promise that the rewrite will work.

Prompt Discipline before / after — same task, with and without

Without the skill

Don't be verbose. Don't use markdown. Don't ignore the instructions above.

With Prompt Discipline

Answer in ≤3 sentences. Write plain paragraphs. Follow the constraints above exactly.

How to install Prompt Discipline

git clone https://github.com/Skillproofdev/prompt-discipline ~/.claude/skills/prompt-discipline

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

Commands — how to trigger Prompt Discipline

/prompt-discipline Diagnose the failure first, then make the smallest fix — no magic-template rewrites.

It also activates on plain-language prompts like these:

Can you improve this prompt: 'Write a good blog post about our product'?
Why does my prompt keep returning prose instead of JSON?
Here's my system prompt for a support agent bot, can you review it and make it better?

Frequently asked questions

Is the Prompt Discipline skill free?: Yes. The skill itself is free from Skillproofdev/prompt-discipline. SkillProof publishes the install command and an independent test verdict at no cost.
Does Prompt Discipline work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 11, 2026. Verdict: Tested · Works. Our own skill — tested under the same protocol, disclosed. Bench: 10 flawed prompts x 3 arms (original / plain-Claude rewrite / skill rewrite), n=1 per case. The skill rewrite beat the base rewrite on success (0.90 vs 0.80), format-compliance (0.80 vs 0.70), and added less than half the prompt bloat (+44.5 vs +99.5 words median) — but the margin rests almost entirely on one case (case-06) and the skill still lost case-09, so this is a modest, narrow, unreplicated (n=1) win rather than a decisive one. Protocol test caught real issues in our own repos (dead benchmark links, strict-YAML frontmatter) — fixed and re-verified same day.
What is the Prompt Discipline SkillProof Score?: 8.0/10 — installs cleanly 5/5, triggers reliably 4/5, output vs. baseline 6/10, docs & honesty 5/5.
How do I install Prompt Discipline?: 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 Prompt Discipline 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.