Is the Email Discipline skill free?

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

What is the Email Discipline SkillProof Score?

8.8/10 — installs cleanly 5/5, triggers reliably 4/5, output vs. baseline 8/10, docs & honesty 5/5.

How do I install Email 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 Email 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.

Email Discipline

One ask, one dated CTA, a hard word budget — emails busy people actually answer.

by SkillProof · Skillproofdev/email-discipline

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.8/10
Tested: Jul 11, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 690dd74

Our own skill — tested under the same protocol, disclosed. 12-scenario, two-arm bench (Sonnet baseline vs Sonnet+skill) scored a scripted mechanical layer, ground-truth coverage, and blind paired preference. The skill won decisively on all three layers — mechanical pass 2/12→12/12, ground-truth coverage 84%→99%, blind preference 10-1-1 — while the published verdict discloses one lost scenario (S12, a post-incident update) and one tie (S11), plus a caveat that blind judging was done in-context rather than by an independent judge instance. 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 8/10
Docs & honesty 5/5

What Email Discipline does

Enforces eight checkable rules for one-to-one email — the ask in the first two lines, subject line as the ask, hard word budgets by type, a banned-fluff scan, and exactly one CTA with a real date. Built for cold asks, tricky replies, follow-ups, declines, and escalations — explicitly not marketing campaigns, newsletters, drip sequences, inbox triage, or send/API integration. Benchmarked against a no-skill Sonnet baseline across 12 realistic scenarios with mechanical, content-coverage, and blind-judged layers, plus disclosed losses.

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

Without the skill

Baseline (no skill) follow-up after 9 days of silence on a €24k proposal buried the ask under scene-setting and closed with 'whenever you get a chance' — no date, no forcing function; the baseline also blew its word budget on 10 of 12 bench drafts and vented two grievances in the escalation scenario.

With Email Discipline

With the skill, the same follow-up leads with the ask in the first two lines and closes with one dated CTA — the pattern that took the bench from a 2/12 mechanical pass rate to 12/12, 84% to 99% ground-truth coverage, and a 10-1-1 blind preference, with one disclosed loss on a post-incident update where the baseline's labeled sections scanned marginally better.

How to install Email Discipline

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

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

Commands — how to trigger Email Discipline

/email-discipline One ask, one dated CTA, a hard word budget — emails busy people actually answer.

It also activates on plain-language prompts like these:

Write a follow-up email to a vendor who's gone silent for 9 days on a €24k proposal.
Here's the email thread from my VP with three questions out of order — draft my reply.
I need to decline a colleague's ask to co-lead a project without burning the relationship.

Frequently asked questions

Is the Email Discipline skill free?: Yes. The skill itself is free from Skillproofdev/email-discipline. SkillProof publishes the install command and an independent test verdict at no cost.
Does Email 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. 12-scenario, two-arm bench (Sonnet baseline vs Sonnet+skill) scored a scripted mechanical layer, ground-truth coverage, and blind paired preference. The skill won decisively on all three layers — mechanical pass 2/12→12/12, ground-truth coverage 84%→99%, blind preference 10-1-1 — while the published verdict discloses one lost scenario (S12, a post-incident update) and one tie (S11), plus a caveat that blind judging was done in-context rather than by an independent judge instance. Protocol test caught real issues in our own repos (dead benchmark links, strict-YAML frontmatter) — fixed and re-verified same day.
What is the Email Discipline SkillProof Score?: 8.8/10 — installs cleanly 5/5, triggers reliably 4/5, output vs. baseline 8/10, docs & honesty 5/5.
How do I install Email 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 Email 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.