Is the Promote skill free?

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

What is the Promote SkillProof Score?

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

How do I install Promote?

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 Promote 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.

Promote

Turns a git release diff into a data-verified X/Twitter thread plus 72-char ASCII card

by oliver-kriska · oliver-kriska/claude-elixir-phoenix

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.8/10
Tested: Jul 21, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · eef0214

Cloned the repo and ran the skill's own data commands: git diff --stat v2.14.3..v3.0.0 gave 1134 files/+140567/-598, ls counted 51 skills and 26 agents. Built the v3.0.0 ASCII card and ran the skill's embedded Python alignment verifier, which caught 4 rows at 73 chars (the exact off-by-one it warns about); after trimming, all 20 lines verified at 72. Baseline was a generic emoji hype tweet with zero verifiable numbers; the skill artifact carried 5 command-backed metrics, a before/after table, an anti-hype thread, and a fact-check flagging the un-runnable eval-all claim as UNVERIFIED. Could not execute codesnap (not installed) or make eval-all, but the primary deliverable (post markdown + verified card) was produced end to end.

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 4/5

What Promote does

Generates X/Twitter release-promotion posts from real repository data: a box-drawing ASCII card (verified to exactly 72 chars wide via an included Python script), a hook-findings-CTA tweet thread with concrete before/after numbers, a CodeSnap render command, and a fact-check section tying every claim to a git command or file reference. Triggers when writing release posts, promotion tweets, plugin announcements, or social content for a new version.

How to install Promote

git clone --depth 1 https://github.com/oliver-kriska/claude-elixir-phoenix.git /tmp/promote-src
mkdir -p ~/.claude/skills
cp -R /tmp/promote-src/.claude/skills/promote ~/.claude/skills/promote
# Ships SKILL.md + references/templates.md. Core output (post .md + verified ASCII card .txt) needs only git.
# Optional Step 4 PNG render needs the `codesnap` CLI and a scratchpad/x-posts/codesnap-claude-dark.json config (neither is in the repo — create/install yourself, or skip the render).
# Step 1 `make eval-all` only runs inside the repo's Elixir toolchain; outside it, mark eval scores UNVERIFIED.
# Data commands (git diff --stat, ls plugins/.../skills) assume you run it from within a claude-elixir-phoenix-style repo.

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

Commands — how to trigger Promote

/promote Turns a git release diff into a data-verified X/Twitter thread plus 72-char ASCII card

It also activates on plain-language prompts like these:

Write a release announcement tweet for v2.0
Draft a promotion post for this new plugin
Create social media content for our release

Frequently asked questions

Is the Promote skill free?: Yes. The skill itself is free from oliver-kriska/claude-elixir-phoenix. SkillProof publishes the install command and an independent test verdict at no cost.
Does Promote work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 21, 2026. Verdict: Tested · Works. Cloned the repo and ran the skill's own data commands: git diff --stat v2.14.3..v3.0.0 gave 1134 files/+140567/-598, ls counted 51 skills and 26 agents. Built the v3.0.0 ASCII card and ran the skill's embedded Python alignment verifier, which caught 4 rows at 73 chars (the exact off-by-one it warns about); after trimming, all 20 lines verified at 72. Baseline was a generic emoji hype tweet with zero verifiable numbers; the skill artifact carried 5 command-backed metrics, a before/after table, an anti-hype thread, and a fact-check flagging the un-runnable eval-all claim as UNVERIFIED. Could not execute codesnap (not installed) or make eval-all, but the primary deliverable (post markdown + verified card) was produced end to end.
What is the Promote SkillProof Score?: 8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.
How do I install Promote?: 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 Promote 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.