agentleFS
oliver-kriskaoliver-kriska/claude-elixir-phoenix/.claude/skills/promote/SKILL.md

promote

Skill573 starsChanged 4 months agoMITView on GitHub

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.

19 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use research.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • NVIDIASkill

    research

    Before designing a feature, research how comparable libraries solve the problem, check best practices, known pitfalls, and upstream changes. Use when starting a new feature, investigating an unfamiliar area, or the user asks to research something.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

10 rules. 0 are common, 5 are distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 16 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run /promote vX.Y.Z after tagging a release.

    line 13
  2. Very specific:

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

    line 17
  3. Very specific:

    Use Unicode box-drawing: ┌─┐│└┘╞═╡╤╪╧ for borders and separators

    line 49
  4. Very specific:

    Follow the hook → findings → details → CTA structure.

    line 60
  5. Distinctive:

    Write like a builder sharing real numbers, not a marketer

    line 71
  6. Distinctive:

    Never mention API costs or token prices — subscription user, cost per call is irrelevant

    line 73
  7. Very specific:

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

    line 79
  8. Distinctive:

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

    line 93
  9. Distinctive:

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

    line 103
  10. Distinctive:

    When deciding whether a release warrants its own post:

    line 107

“Common” is measured: kept by at least 6 in 10 of the 16 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/promote — Release Promotion Post Generator

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

When to use

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

Output

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

The output file contains three sections:

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

Execution Flow

Step 1: Gather Data

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

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

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).

Step 2: Write the ASCII Card

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

Rules:

  • Exactly 72 characters wide (including borders) — consistent with past posts
  • Use Unicode box-drawing: ┌─┐│└┘╞═╡╤╪╧ for borders and separators
  • Include: version + title, headline stats, before/after table, repo URL
  • The table content comes from Step 1 data — pick the 3-5 most impressive changes
  • VERIFY ALIGNMENT: After writing the table, run a Python script to check every line has the same visual width. Off-by-one errors are the most common problem — em dashes (—) and arrows (→) are single-width but easy to miscount. Every line between the top ┌ and bottom └ borders must be exactly 72 visual characters

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

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

Step 3: Write the Tweet Thread

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

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

  • Tweet 1 (Hook): Version + one compelling sentence about what changed. Include headline stats (files changed, skills, agents). Repo link here — not in a reply. Add #ElixirLang #ClaudeCode hashtags.
  • Tweet 2-3 (Findings): The specific changes with numbers. Use numbered lists. Before/after metrics are the highest-performing content type.
  • Tweet 4-5 (Details/CTA): Additional changes + soft CTA ("Try it and let me know how it feels"). Link to release page.
  • Max 5 tweets — casual readers drop off after 4-6. If you have more content, cut the least impactful items.

Voice and tone:

  • Data-heavy, transparent, no-hype — this is the proven #1 strength
  • Write like a builder sharing real numbers, not a marketer
  • Concrete numbers over adjectives ("32/40 descriptions rewritten" not "improved many descriptions")
  • Never mention API costs or token prices — subscription user, cost per call is irrelevant

Step 4: CodeSnap Command

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

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

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

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

Step 5: Fact-Check

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

## Fact-Check

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

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

Bundling Strategy

When deciding whether a release warrants its own post:

  • Standalone post: Major features, impressive before/after metrics, new capabilities
  • Bundle with next release: Bug fixes, description tweaks, minor config changes
  • Skip entirely: Patch releases with <5 files changed and no user-facing changes

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.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.