Overview Benchmark Contents Activity Versions 1 Ratings 0
What's inside The instructions your model reads when the skill loads.
SKILL.md 54 lines single file
Twitter Launch Creative
Goal
Turn the user's command into a real publishable X/Twitter text artifact, not a prompt, checklist, or meta instruction.
The output should be suitable for review and direct editing by an operator.
When To Use
Use this skill for:
technical launch posts
product update tweets
founder-style shipping notes
build-in-public updates
concise commentary about AI tools, agents, or software projects
Writing Rules
Write the final post directly.
Keep the main tweet under 280 characters.
Prefer concrete product language over hype.
Avoid fake metrics, unverified benchmarks, invented customer quotes, and absolute claims.
Use Chinese by default unless the user asks for another language.
If the user's request is vague, make conservative assumptions and mention them in safetyNotes.
Workflow
Identify the user's core announcement or message.
Choose a clear angle for the target audience.
Draft one concise X/Twitter post.
Remove hype, fake metrics, and unverifiable claims.
Return the final artifact through finalize_twitter_creative.
Output Contract
Return the final answer by calling finalize_twitter_creative with:
When it activates Automatically, when a task matches.
Use when the user asks for product updates, technical announcements, founder notes, and project launch posts.
Track record Benchmark 0 / 22
test cases passed with the skill
Adoption
Users 0
Times used 0 View activity → Safety and source details
SkillSafety ✓ 3 of 3 passed ✓ Code scan 15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v4 — 8/1/2026
View 15 scanner checks live_secret remote_code_execution reverse_shell data_exfiltration ssrf_metadata agent_snooping anti_refusal destructive_commands obfuscated_unicode unicode_homoglyph opaque_blob suspicious_url tool_overreach trigger_abuse prompt_injection_phrasing
✓ Intent Safe
LLM judge · does the skill do what it claims
✓ Content Clean
LLM judge · policy & harmful-content review
Source Imported License MITImported 8/1/2026Version v1