analyze
Decision-first analysis for a finished Threads post: style matching, psychology analysis, algorithm alignment, upside drivers, suppression risks, and AI-tone…
Check AK-Threads-Booster for upstream GitHub updates, safely fast-forward the local skill repo, or install an opt-in weekly Codex automation that keeps the skill on the latest version. Trigger words: update skill, check updates, auto update, weekly update, 更新 skill, 自動更新, 每週檢查更新.
$ npx -y skills add akseolabs-seo/AK-Threads-booster --skill update --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/updateContext preview
The summary Claude sees to decide when to auto-load this skill.
Check AK-Threads-Booster for upstream GitHub updates, safely fast-forward the local skill repo, or install an opt-in weekly Codex automation that keeps the skill on the latest version. Trigger words: update skill, check updates, auto update, weekly update, 更新 skill, 自動更新, 每週檢查更新.
name: update description: "Check AK-Threads-Booster for upstream GitHub updates, safely fast-forward the local skill repo, or install an opt-in weekly Codex automation that keeps the skill on the latest version. Trigger words: update skill, check updates, auto update, weekly update, 更新 skill, 自動更新, 每週檢查更新." version: "2.0.0" allowed-tools: Read, Grep, Glob, Bash
Use this module when the user wants to check whether AK-Threads-Booster has a newer version, update the local skill repo, or install an opt-in weekly update checker.
Repository:
https://github.com/akseolabs-seo/AK-Threads-booster
| Intent | Action | |---|---| | Check once / 有沒有新版 | Run one-time check, no apply unless user asks | | Update now / 更新到最新版 | Run safe updater with `--apply --validate` | | Install weekly auto-update / 每週自動檢查更新 | Create a Codex cron automation, only after explicit user request | | Remove weekly auto-update / 取消自動更新 | Find and delete the matching automation |
After any successful one-time update check or update attempt, ask the user once:
要不要順手開啟每週自動檢查 AK-Threads-Booster 更新? 開啟後,每週會自動檢查 GitHub。有新版且本地 repo 乾淨時才會 fast-forward 更新;如果有本地修改、衝突或 local commits,會停下回報,不會覆蓋你的東西。
If the user says yes, install the weekly automation. If the user says no, do not ask again in the same run. Do not install by default.
When the user is in a non-interactive/headless context, do not install automation. Report that auto-update is available and requires explicit opt-in.
Run from the repository root:
python scripts/check_skill_update.py --remote origin --branch main
Interpret:
Run:
python scripts/check_skill_update.py --remote origin --branch main --apply --validate
Afterward, summarize:
If status starts with `blocked_`, do not try another git strategy without the user's explicit instruction.
Only install this when the user explicitly asks for a recurring updater.
In Codex app environments, use the automation tool to create a weekly cron automation:
Check the local AK-Threads-Booster repository against https://github.com/akseolabs-seo/AK-Threads-booster once. Run `python scripts/check_skill_update.py --remote origin --branch main --apply --validate` from the repository root. If the script reports `updated`, summarize pulled commits, changed files, validation results, and current git status. If the script reports `up_to_date`, report that clearly. If the script reports any `blocked_*` status, do not reset, rebase, stash, or overwrite files; report the blocker, dirty files or local commits, and the safest next step. Preserve all local user changes.
If the automation tool is not available, explain that this environment cannot install the recurring job automatically and provide the one-time check command instead.
Before creating a new automation, check existing automations for a matching name or prompt. Prefer updating an existing matching automation over creating a duplicate.
For deletion, delete only a matching AK-Threads update automation. Do not delete unrelated reminders or scheduled jobs.
Keep the final answer short:
AK-Threads-Booster 是這個 skill 的內部代號與安裝 id。 AK-Threads-Booster 是一套給 Threads 創作者用的 AI skill 系統。 它不是要幫你亂寫一堆貼文,而是幫你把「選題、起草、分析、預測、復盤」變成一套有資料依據的工作流,讓你更容易發出值得被分享、收藏、討論的內容。 如果你平常的痛點是這些: 不知道下一篇到底該寫什麼 有很多題目,但分不出哪個更值得先發 文章不是寫不好,只是常常撞題、老梗、沒新鮮度 想讓內容更像自己,不想一看就很 AI
Decision-first analysis for a finished Threads post: style matching, psychology analysis, algorithm alignment, upside drivers, suppression risks, and AI-tone…
Self-contained compound loop: read threads_skill_learnings.log, cluster the misses, propose concrete sub-skill rule edits, and apply them with the user's…
Launch or prepare the optional local visual panel for AK-Threads-Booster. Use when the user asks for a dashboard, visual panel, local UI, data cockpit, or…
Estimate likely 24-hour post performance from the user's historical data. Use after the user writes a post and wants a range estimate, upside view, or…
Refresh threads_daily_tracker.json. Prefer the Threads API when available; fall back to authenticated browser profile scraping when API access is not…
Post-publish feedback loop: collect actual metrics, compare against predictions, update the tracker, refresh style conclusions carefully, and learn from…