AGENT SKILL

social-post

Use when creating platform-optimized social posts — Twitter threads, LinkedIn, Instagram, Telegram

License 许可
Apache-2.0
最近更新
2026-10-11
Stars
★ 7
Forks
8

01 前言 Front Matter

name
social-post
arguments
[ { "name": "topic", "required": true, "description": "What to post about" }, { "name": "platform", "required": false, "description": "Target: twitter, linkedin, instagram, telegram, all" } ]
description
Use when creating platform-optimized social posts — Twitter threads, LinkedIn, Instagram, Telegram

03 SKILL.md 正文

Social Post Workflow

Step 1: Core Message

  • Identify the ONE key message / takeaway
  • Who is the audience?
  • What action should they take? (click, share, reply, sign up)

Step 2: Platform Adaptation

Twitter/X Thread

  • Hook tweet: provocative statement or question (<280 chars)
  • Body: 3-7 tweets, each standalone-valuable
  • Last tweet: CTA + link
  • Use line breaks for readability
  • Numbers and lists perform well

LinkedIn

  • Hook: first 2 lines visible before "see more"
  • Professional tone, personal experience angle
  • 1300-1700 chars optimal
  • End with question to drive engagement
  • Relevant hashtags (3-5)

Instagram Caption

  • Hook in first line
  • Story format works best
  • CTAs: "save this", "share with someone who..."
  • 20-30 relevant hashtags (separate from caption)
  • Emoji-friendly format

Telegram

  • Direct, informative tone
  • Markdown formatting (bold, links)
  • Can be longer than other platforms
  • Include media if relevant

Step 3: Output

  • Generate post(s) for requested platform(s)
  • If "all" — adapt same message to each platform's format
  • Include suggested posting time (based on platform best practices)

04 同仓库更多 Skills

KeiSeiLab
KeiSeiLab/KeiSeiKit

wave-audit

3-wave parallel audit — Wave 1 discovery (4 agents), Wave 2 verification (4 agents), Wave 3 cross-optimization (1 synthesizer). Each wave runs agents in parallel. Combines security review, runtime analysis, quality check, and constructor pattern into one unified workflow with evidence grading and Go/No-Go verdict.

Skill与智能体开发
★ 7
KeiSeiLab
KeiSeiLab/KeiSeiKit

vm-provision

End-to-end VPS provisioning — select provider → plan → provision → harden → verify (ssh-check + firewall-diff hard-gate) → handoff. 6 phases, ≥6 AskUserQuestion calls, defensive-only. Stops if either verification primitive fails.

★ 7
KeiSeiLab
KeiSeiLab/KeiSeiKit

visual-explainer

Generate beautiful, self-contained HTML pages that visually explain systems, code changes, plans, and data. Use when the user asks for a diagram, architecture overview, diff review, plan review, project recap, comparison table, or any visual explanation of technical concepts. Also use proactively when you are about to render a complex ASCII table (4+ rows or 3+ columns) — present it as a styled HTML page instead.

数据分析师前端开发
★ 7
KeiSeiLab
KeiSeiLab/KeiSeiKit

video-gen

Use when generating video from frame sequences — FFmpeg extraction, WebP/AVIF conversion, sprite sheets, scroll-synced playback, video encoding/transcoding. Covers the full pipeline from video source to web-ready frame sequence or optimized video.

图像与多媒体
★ 7
KeiSeiLab
KeiSeiLab/KeiSeiKit

test-matrix

Use when a project needs testing BEYOND unit tests — fuzzing, property-based, load, E2E, or mutation. Five-phase hub-and-spoke pipeline composes the right mix per language × critical path × CI target, scaffolds configs + corpus + fixtures, wires CI jobs, and defines the crash/regression triage workflow. Pure-click: every decision except intake is an AskUserQuestion.

测试与质量
★ 7
KeiSeiLab
KeiSeiLab/KeiSeiKit

test-gen

Use when generating tests for untested code — happy path, edge cases, error handling

测试与质量
★ 7