leather-changelog
Skill29 starsChanged 36 days agoMITView on GitHub
Generate product changelog entries, X/Twitter posts, and Slack announcements for Leather wallet releases. Use when creating release communications including changelog entries for app.leather.io/changelog, announcement tweets (single or threads), and community Slack posts. Inputs may include verbal feature descriptions, Linear projects, or GitHub PRs.
In this repository7 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- feature-mapSkill
- monorepo-navigationSkill
- new-issueSkill
- testing-patternsSkill
- triage-issueSkill
- write-extension-e2eSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 37
Use scripts/sanity-changelog.js to upload changelog entries to Sanity CMS as drafts.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Leather Release Communications
Generate consistent, on-brand release communications for Leather wallet across changelog entries, X posts, and Slack announcements.
Process
- Gather context — Review provided feature description, Linear project, or GitHub PRs
- Identify the "why" — Determine the user problem being solved or improvement being delivered
- Read format references — See
references/voice-and-formats.mdfor voice guidelines and templates - Generate outputs — Create requested formats (changelog, X post, Slack, or all three)
Output Summary
| Format | Purpose | Length |
| Changelog | Permanent product record at app.leather.io/changelog | 50-150 words |
| X single | Quick announcement for smaller features | 280 chars max |
| X thread | Major releases needing context | 3-5 tweets |
| Slack | Community announcement | 100-200 words |
Voice Principles
- Lead with impact — Start with why this matters to users, not what changed technically
- Understated confidence — Let the product speak; avoid hype words ("excited", "thrilled", "game-changing")
- One idea per sentence — Short, declarative statements
- Show don't tell — Concrete benefits over abstract claims
See references/voice-and-formats.md for detailed guidelines and examples.
Sanity CMS Integration
Use scripts/sanity-changelog.js to upload changelog entries to Sanity CMS as drafts.
Setup
export SANITY_PROJECT_ID="your-project-id"
export SANITY_DATASET="production" # optional, defaults to "production"
export SANITY_API_TOKEN="your-write-token"Usage
# Test upload without creating (dry run)
node scripts/sanity-changelog.js --title "Feature title" --body changelog.md --dry-run
# Create draft in Sanity
node scripts/sanity-changelog.js --title "Feature title" --body changelog.md
# With custom slug and publication date
node scripts/sanity-changelog.js \
--title "Feature title" \
--body changelog.md \
--slug "custom-slug" \
--published-at "2025-01-15T10:00:00Z"Markdown Support
The script converts markdown to Sanity Portable Text:
- Paragraphs (separated by blank lines)
## Headingsand### Headings→ h2 blocks**bold**,*italic*,`code`inline formatting
Options
| Option | Description |
--title, -t | Changelog entry title (required) |
--body, -b | Path to markdown file (required) |
--slug, -s | URL slug (auto-generated if not provided) |
--published-at | ISO datetime (default: now) |
--hero-image | Sanity asset ID for hero image |
--dry-run | Test without creating document |
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
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.

