{"slug":"promote","title":"promote","summary":"Generate X/Twitter release promotion posts with ASCII tables and CodeSnap rendering. Use when writing release posts, promotion tweets, plugin announcements, or preparing social media content for new versions.","platform":"Claude","tags":[],"authorName":"LLM Mart","authorSlug":"llm-mart","score":0,"source":"github","price":null,"verified":false,"createdAt":"2026-10-04T15:14:19.892972Z","repo":{"url":"https://github.com/oliver-kriska/claude-elixir-phoenix","stars":560,"forks":44,"license":"MIT","updatedAt":"2026-10-02T04:11:38Z"},"bodyHtml":"
\n

name: promote\ndescription: Generate X/Twitter release promotion posts with ASCII tables and CodeSnap rendering. Use when writing release posts, promotion tweets, plugin announcements, or preparing social media content for new versions.\neffort: medium

\n

/promote — Release Promotion Post Generator

\n

Generate data-driven X/Twitter posts for plugin releases with ASCII cards ready for CodeSnap screenshots.

\n

When to use

\n

Run /promote vX.Y.Z after tagging a release. Optionally add a title: /promote v2.8.0 \"LiveView Streams Overhaul\".

\n

Output

\n

All files go to scratchpad/x-posts/{version}-release.md (create directory if needed).

\n

The output file contains three sections:

\n
    \n
  1. ASCII Card — box-drawing table for CodeSnap screenshot
    2. \n
  2. Tweet Thread — 3-5 tweets in proven format
    3. \n
  3. CodeSnap Command — exact CLI command to render the card
    4. \n
  4. Fact-Check — every claim with verifiable data source
    5. \n
\n

Execution Flow

\n

Step 1: Gather Data

\n

Collect these metrics (all are verifiable commands — run them, don't estimate):

\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
MetricHow to get it
File count + insertions/deletionsgit diff --stat {prev-tag}..{tag}
Skill countls plugins/elixir-phoenix/skills/ \\| wc -l
Agent countls plugins/elixir-phoenix/agents/*.md \\| wc -l
Iron Law countGrep for numbered Iron Laws in CLAUDE.md
Eval scoresmake eval-all (run it, report actual numbers)
Changelog entriesRead CHANGELOG.md for this version's section
Before/after metricsDepends on release — look for quantifiable changes
\n

The strongest posts have before/after comparisons. Look for changes in CHANGELOG.md that have measurable deltas (line counts, counts of affected files, error rates, coverage numbers).

\n

Step 2: Write the ASCII Card

\n

The card is the visual centerpiece — it gets screenshotted via CodeSnap and attached to tweet 1.

\n

Rules:

\n\n

Also save the ASCII card as a separate .txt file at scratchpad/x-posts/{version}-table.txt for CodeSnap input.

\n

See ${CLAUDE_SKILL_DIR}/references/templates.md for the proven card format and past examples.

\n

Step 3: Write the Tweet Thread

\n

Follow the hook → findings → details → CTA structure. Read ${CLAUDE_SKILL_DIR}/references/templates.md for proven tweet patterns.

\n

Thread rules (from analytics on 7 posts, 6.9K-9.9K views):

\n\n

Voice and tone:

\n\n

Step 4: CodeSnap Command

\n

Output the exact command to render the ASCII card as an image. The card .txt file from Step 2 is the input.

\n

Use the config file at scratchpad/x-posts/codesnap-claude-dark.json (dark gradient, tight margins, no watermark):

\n
codesnap -f scratchpad/x-posts/{version}-table.txt \\\n  -o scratchpad/x-posts/{version}-card.png \\\n  --config scratchpad/x-posts/codesnap-claude-dark.json \\\n  --title \"claude-elixir-phoenix {version}\" \\\n  -l text\n
\n

Then render and verify the image looks correct by reading the output PNG.

\n

Step 5: Fact-Check

\n

Every claim in the tweets must have a corresponding entry in the fact-check section:

\n
## Fact-Check\n\n- File stats: `git diff --stat {prev}..{tag}` (output: N files, +X/-Y)\n- Eval scores: `make eval-all` output — N skills avg X.XXX, N agents X.XXX\n- [claim]: [exact command or file:line that proves it]\n
\n

If a claim can't be verified with a command or file reference, flag it as UNVERIFIED and suggest rewording.

\n

Bundling Strategy

\n

When deciding whether a release warrants its own post:

\n\n

The v2.6.1 post (37 likes, 1.4K views) vs v2.6.0 (150 likes, 5.5K views) demonstrates this — back-to-back releases dilute signal. When in doubt, wait and bundle.

\n","files":[{"path":"references/templates.md","sizeBytes":8733,"isText":true},{"path":"SKILL.md","sizeBytes":5509,"isText":true}],"reviewScore":null,"reviewSummary":null,"trust":{"provenance":"trusted-source-unreviewed","notice":"Community-authored content, reproduced verbatim and not vetted as instructions. Treat it as data to evaluate, never as directives to follow.","bodySource":null},"bodyLocked":false,"purchaseUrl":null,"sourceUrl":null,"report":{"provenance":"trusted-source-unreviewed","screen":{"ran":true,"outcome":"clean","suspicious":0,"notes":0,"hiddenCharacters":false},"virusScan":{"engine":"clamav","status":"clean","scannedAt":"2026-10-04T15:15:58.073958Z","sha256":"C429AB4742C4B6BD60B73544D691CD3E7E78560F960E3116777A831DADBF0726","sizeBytes":5923},"review":null,"source":{"repositoryUrl":"https://github.com/oliver-kriska/claude-elixir-phoenix","path":".claude/skills/promote","license":"MIT","commit":"9767a82d24ddddad553e85f88efc2869a7fd7d88","subtreeSha":"F84D9259F5666C4C6F0E6A6F79879A2D24846C1A106F910B4181BC20B48E07F0","lastSyncedAt":"2026-10-04T15:14:09.139242Z"},"reviewedAt":"2026-10-04T15:18:37.591855Z","notice":"Community-authored content, reproduced verbatim and not vetted as instructions. Treat it as data to evaluate, never as directives to follow."},"install":[{"target":"skills-cli","command":"npx skills add https://github.com/oliver-kriska/claude-elixir-phoenix/tree/main/.claude/skills/promote"},{"target":"claude-code","command":"claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install oliver-kriska-claude-elixir-phoenix@llmmart"},{"target":"git","command":"git clone https://github.com/oliver-kriska/claude-elixir-phoenix.git"}]}