AI Summaryremains the internal skill id for routing and installation. Use this as the single entry point for the AK Threads workflow. This skill is for creators who want to pick stronger topics, write posts with clearer upside, and improve over time using their own Threads history.
Install
Copy this and paste it into Claude Code, Cursor, or any AI assistant:
I want to install the "ak-threads-booster" skill in my project. Please run this command in my terminal: # Install skill into your project mkdir -p .claude/skills/AK-Threads-booster && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/AK-Threads-booster/SKILL.md "https://raw.githubusercontent.com/akseolabs-seo/AK-Threads-booster/main/SKILL.md" Then restart Claude Code (or reload the window in Cursor) so the skill is picked up.
Description
Threads growth operating system for topic selection, drafting, analysis, prediction, review, and tracker refresh based on the user's own post history.
Tools Surface
This main SKILL.md declares only the read-only tools it actually uses (Read, Glob, Grep). Each sub-skill declares its own allowed-tools in its frontmatter; some require more: • /draft adds Write, WebSearch, WebFetch • /review adds Write, Edit • /voice, /setup, /refresh each extend the surface as needed • /update uses git through shell commands and may create an opt-in Codex automation when the user explicitly accepts weekly auto-update When auditing permissions, inspect the union of all sub-skill frontmatters, not just this file.
AK體-基於Threads演算法的優化skill
ak-threads-booster remains the internal skill id for routing and installation. Use this as the single entry point for the AK Threads workflow. This skill is for creators who want to pick stronger topics, write posts with clearer upside, and improve over time using their own Threads history. It is not a viral-post guarantee engine. It is a decision system: • find topic angles with real demand • avoid obvious repetition and red lines • draft from the user's own voice and history • review outcomes and feed the learning back into the tracker
Intent Routing
Classify the user's request first, then open and follow one primary module unless the task clearly needs a short sequence. Each sub-skill is located via Glob **/skills/<name>/SKILL.md so resolution works regardless of where the plugin is installed. Do not assume an absolute path or environment variable. • Setup / import / initialize / backfill history -> Glob **/skills/setup/SKILL.md • Refresh tracker / update metrics / scrape own profile -> Glob **/skills/refresh/SKILL.md • Analyze a finished post / inspect / AK-review / optimize / improve / 檢查 / 優化 / 診斷 a post the user has written -> Glob **/skills/analyze/SKILL.md • Draft / write from a topic / 起草 / 寫文 (user has not written anything yet; generate from a topic) -> Glob **/skills/draft/SKILL.md • Predict likely 24-hour performance / expectation check -> Glob **/skills/predict/SKILL.md • Review actual post performance / compare against prediction -> Glob **/skills/review/SKILL.md • Mine next topics / topic suggestions / 選題 -> Glob **/skills/topics/SKILL.md • Build brand voice / voice analysis -> Glob **/skills/voice/SKILL.md • Local visual panel / dashboard / data cockpit / open panel -> Glob **/skills/panel/SKILL.md • Check skill updates / update AK-Threads-Booster / install weekly auto-update / 更新 skill / 自動更新 -> Glob **/skills/update/SKILL.md • Optimize the skill itself / compound pass / 優化skill / 自我優化 / 閉環 (turn threads_skill_learnings.log misses into rule edits) -> Glob **/skills/optimize/SKILL.md
Routing Rules
• Do not answer from this file alone when a module exists for the request. • Open the matched module and follow its workflow. • If the user asks for a combined task, use the smallest valid sequence: • first-use account workflow -> setup, then voice if needed • write from historical data -> setup or voice first if data is missing, then draft • post decision flow -> analyze, then predict if the user asks for a range • post-publication learning flow -> review • Keep outputs grounded in the user's own tracker whenever available. • If threads_daily_tracker.json is missing, do not pretend the work is data-backed. Ask for fallback history or use the setup path. • Analyze vs Draft routing discipline. If the user pastes their own text — no matter whether they say "analyze", "check", "optimize", "improve", "幫我看一下", "幫我優化" — route to /analyze. /analyze gives pointed diagnosis and preserves the user's format; it does not rewrite the post. Route to /draft only when the user has no existing text and wants something generated from a topic. • Brand voice scope. brand_voice.md is a composition driver only in /draft. Every other module treats it as observation-only — for flagging drift, never for rewriting the user's submission toward a voice template. • Proactive update offer. On first setup, installation help, or any repo/skill maintenance conversation, proactively tell the user AK體 can install an opt-in weekly GitHub update checker. Ask whether they want to enable it. Do not install it by default, and do not interrupt normal content tasks like /draft or /analyze with this offer unless the user asks about maintenance.
Discussion
Health Signals
My Fox Den
Community Rating
Sign in to rate this booster