AK-Threads-booster skill
A skill set for Threads creators: picks topics, drafts in your voice and forecasts reach from the history of your own posts
- 283 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- The /refresh mode drives a browser signed in to Threads and reads the profile, and with an API token it calls your account
- Scripts write tracker and cache files into the working folder, and an enabled /update runs a git fast-forward in the skill directory
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/ak-threads-boosterDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- The /refresh mode drives a browser signed in to Threads and reads the profile, and with an API token it calls your account
- Scripts write tracker and cache files into the working folder, and an enabled /update runs a git fast-forward in the skill directory
This is third-party code. Review the repository files before installing.
What it does
AK-Threads-booster gives the agent a Threads creator's working loop: topic, draft, pre-publish check, forecast, post-mortem. Every decision rests on your earlier posts, which live in the threads_daily_tracker.json file. The /setup command builds that file from a Threads data export, and /refresh updates it through the Threads API with a token or through an already open browser. The /topics command looks for topics using reactions, questions that keep coming up in comments and recent repeats. The /voice command computes a voice fingerprint from the posts: paragraph length, openings and endings, punctuation. It then builds a brand_voice.md file with a forbidden zone, and /draft writes from it. Before writing, it checks whether the topic is worn out. The skill never changes facts about your life. The /analyze command checks a draft against the algorithm's red lines and signs of AI text, /predict estimates 24-hour reach from similar posts, /review feeds the actual result back into the tracker. The /panel command opens a local panel with trends and top posts without calling a model, and /update checks the repository for a new version.
Who it is for. Creators who post on Threads regularly and want to choose topics from their own data instead of gut feeling. Without a post history the advice is weaker.
Good fit when
- You have many topics, are unsure which to post first and want to compare them against your own stats
- A draft reads smoothly but sounds like a neural network, and you need a voice file with banned phrasing
- Before sending you want to check a post against the algorithm's red lines and see the main weakness
- After publishing you want the result fed back into the tracker so the next forecast gets sharper
- You want an account summary in the browser without spending model tokens
Not a fit when
- You need autoposting: the skill prepares and checks texts but does not publish
- You have no export and no Threads API access and the account is empty, so forecasts would rest on nothing
- You write for other platforms: the rules and psychology in the skill are tuned for Threads
- You expect a guaranteed viral post: the developer states plainly that there are no guarantees
Example request
Run /topics on my tracker and suggest five topics for this week, excluding anything I wrote about in the last three weeksLimitations
- The README and commands are in Traditional Chinese, with an English README.en.md alongside. The agent answers in the language of your request.
- The no-API mode reads your profile through a browser where you are already signed in and breaks when Threads changes its markup.
- Threads belongs to Meta, which Russia has designated an extremist organization; access to the service from Russia depends on your provider.
- /predict gets more accurate with more posts, and estimates on a short history are rough.
- Auto-update is enabled only with your consent and runs only on a clean repository.
How to disable. Remove the skill folder from your agent's skills directory. If you turned on the weekly update check through /update, switch it off in the same place. The working files threads_daily_tracker.json, brand_voice.md and the compiled/ folder sit in your working directory and can be deleted separately.
FAQ
How do I install AK-Threads-booster?
Clone the repository with git clone https://github.com/akseolabs-seo/AK-Threads-booster.git into your agent's skills directory. An agent that reads AGENTS.md or SKILL.md picks the skill up by itself. For Codex there is metadata in agents/openai.yaml.
Where does the skill get my post history?
The /setup command parses a Threads data export and /refresh adds new posts. With a Threads API token the refresh goes through the API; without one the agent opens your profile in a browser where you are already signed in.
Does the skill promise viral posts?
No. The developer calls it a decision system, not a reach guarantee. /predict returns a 24-hour range from similar past posts, and accuracy depends on how big your history is.
What does the /voice command do?
It computes a voice fingerprint with a local script: how you open and end posts, paragraph length, punctuation. The agent then states your beliefs and banned phrasing. The result lands in brand_voice.md, and you edit it by hand in the Manual Refinements section at the bottom.
How does the skill update?
The /update command checks GitHub for a new version. It updates only if the local copy is clean and can fast-forward. With local edits or a conflict the skill stops and reports it.
Discussion
No questions or reviews yet.
Related
SkillsBlackTwist Social Media Skills
Social Media Skills
Fourteen skills for social media content: strategy, calendar, posts, threads, carousels, captions and metrics analysis for LinkedIn, X, Threads and Bluesky
31 PR skills: the agent finds news hooks, writes angles and headlines, fact-checks and keeps watch on coverage.
Four Claude Code skills that take a post for X from gathering material and picking topics to a ready draft
A social content skill: learns your voice, plans content, writes posts and, after confirmation, publishes through your logged-in Chrome
An X (Twitter) research skill: the agent searches posts, reads threads and profiles, and assembles a briefing with source links
A final-pass editing skill that strips templated phrasing and consultant tone from AI drafts in English and Chinese.
README in short
Version 2.0 added an account memory cache that saves tokens, a hint about which growth bottleneck the next post should address, the new /voice command, a local panel and safe updating. The README lists nine commands, the first-run order, the files that appear in the working folder and the repository tree with skills, algorithm knowledge, scripts and templates.
README badge
Original SKILL.md
--- name: ak-threads-booster description: "Threads growth operating system for topic selection, drafting, analysis, prediction, review, and tracker refresh based on the user's own post history." version: "2.0.0" allowed-tools: Read, Glob, Grep --- # 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 1. Do not answer from this file alone when a module exists for the request. 2. Open the matched module and follow its workflow. 3. If the user asks for a combined task, use the smallest valid sequence: