Skip to content
Agentmart
Submit a tool

tweet-today

Draft specific Twitter/X posts from a concrete work receipt, lesson, opinion, code detail, or user draft.

Skill by kriscard

IndexedMIT★ 14
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/kriscard-tweet-today

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Draft specific Twitter/X posts from a concrete work receipt, lesson, opinion, code detail, or user draft. Use when the user asks what to tweet or a receipt workflow requests social options.

Use cases: writing, productivity

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/tweet-today

What's inside

Skill name
tweet-today
Description
Draft specific Twitter/X posts from a concrete work receipt, lesson, opinion, code detail, or user draft. Use when the user asks what to tweet or a receipt workflow requests social options.
License
MIT
Instructions
65 lines in SKILL.md · view on GitHub

Files (2)

  • SKILL.md
  • twitter-voice.md · references/

SKILL.md (first lines)

# Tweet Today

Produce at least three distinct single-post options grounded in real evidence. Use `blog` for an essay and `standup` for a team update.

## 1. Find receipts

Use the nearest source: current conversation, user draft, supplied daily summary, or structured receipt from another workflow. A receipt is a shipped change, fixed bug, observed detail, tested tool, decision, mistake, screenshot, or changed opinion.

If the source lacks a subject, stance, or concrete proof, ask only for the missing piece. Request permission before inspecting notes or Git.

Complete when the evidence supports three genuinely different signals rather than three phrasings of one claim.

## 2. Run the public-safety gate

Remove or generalize credentials, private URLs and repository names, customer data, unreleased metrics, internal architecture, config values, copied logs, and private backlinks. Keep receipt IDs and vault links as private workflow metadata.

For code, retain only the minimal public-safe lines and replace sensitive values with unmistakable placeholders.

Complete when every retained fact is publishable and traceable to the source.

## 3. Choose three signals

Choose evidence-backed categories such as shipped work, learned lesson, UI detail, programming judgment, product trade-off, agent workflow, or tiny code example. Name why each signal is distinct.

Useful frames:

- I thought X; evidence Y changed it to Z.
- I did X; the reusable lesson was Y.
- X works poorly under condition Y; Z handled it better.
- The visible bug was X; the underlying cause was Y.

## 4. Draft

Write one option per signal, each within the current platform limit unless the user requests a longer format. Make one point, keep claims proportional to evidence, and use a tiny snippet only when it communicates better than prose.

Load `references/twitter-voice.md` for the final voice pass. A candidate fails when it could be posted unchanged by a generic developer account; repair it with a sharper receipt, named detail, or actual opinion.

Complete when every option is safe, source-grounded, distinct, and recognizable as the user's voice.

## 5. Present the choice

```markdown
Recommended:
> [strongest option]

Why this one: [specificity, evidence, or voice reason]

Other options:
1. **[signal]** — [post]
2. **[signal]** — [post]
```

Return clarification questions instead of generic filler when evidence remains thin. Drafting does not imply posting or publication.

## Completion gate

The result is complete when at least three distinct candidates pass safety and voice checks, the recommendation is justified in one sentence, and no private workflow metadata appears in post text.

## References

| Priority | Load when | Reference |
| --- | --- | --- |
| 1 | Finalizing candidates in the user's voice or deciding whether a code/image-led post fits | `references/twitter-voice.md` |

From kriscard/Skills, MIT.

More from kriscard/Skills

Signals

Stars
14
Forks
0
Open issues
0
Last commit (this folder)
Oct 7, 2026 (21 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from kriscard

Cite this page

tweet-today skill. Agent Mart. https://agentmart.dev/skills/kriscard-tweet-today (last updated 2026-10-24)