Agent skill

Scheduler Skill Creator

by agenvoy in agenvoy/Agenvoy

建立並排程定時觸發的 skill。所有新增定時/週期任務、提醒、排程通知的請求必須走此 skill,禁止直接呼叫 schedules(mode=write)(那是 skill 已存在時的時間綁定工具,不該作為新建排程的入口)。

AGPL-3.0Auto-check passedAgent Workflows

Install Scheduler Skill Creator

skills CLI
$ npx skills add agenvoy/Agenvoy --skill scheduler-skill-creator -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install agenvoy/Agenvoy scheduler-skill-creator --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/agenvoy/Agenvoy.git skills-src && mkdir -p .claude/skills && cp -r skills-src/extensions/skills/scheduler-skill-creator .claude/skills/scheduler-skill-creator && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
scheduler-skill-creator
GitHub stars
439
Token cost
~3k tokens
SKILL.md length
918 words
Files
2 (incl. scripts)
Skills in repo
4
Repo updated
First seen
Licence
AGPL-3.0

At a glance

建立並排程定時觸發的 skill。所有新增定時/週期任務、提醒、排程通知的請求必須走此 skill,禁止直接呼叫 schedules(mode=write)(那是 skill 已存在時的時間綁定工具,不該作為新建排程的入口)。

  • Works in 7 steps: 時間檢查門檻(強制首動作) → 解析需求 → 時間正規化 + 選 tool → …
  • Tasks that involve Scheduled and recurring tasks
  • SKILL.md covers 目的, 成功標準, 步驟 and 命名規則, plus 5 more sections
  • Runs Python scripts from its folder; calls python3; needs OPENAI_API_KEY and DISCORD_BOT_TOKEN

What it does

Scheduler Skill Creator is an agent skill from agenvoy/Agenvoy. 建立並排程定時觸發的 skill。所有新增定時/週期任務、提醒、排程通知的請求必須走此 skill,禁止直接呼叫 schedules(mode=write)(那是 skill 已存在時的時間綁定工具,不該作為新建排程的入口)。 必定觸發的訊息特徵(任一即活化): - 相對延遲:「X 分鐘後」「X 小時後」「稍後」「待會」「等一下」 - 明確時間:「X 點」「下午 X 點」「明天 X 點」「後天」「YYYY-MM-DD HH:MM」 - 週期性:「每 X 分鐘」「每小時」「每天」「每週」「每月」「定時」「固定」 - 提醒 / 通知意圖:「提醒我」「通知我」「告訴我」+ 時間描述 範例觸發訊息:「5 分鐘後提醒我喝水」「每天早上 9 點抓 HN 頭條」「明天下午 3 點開會」「每 5 分鐘查台積電股價」。 不觸發(即使訊息含「觸發」「排程」字眼也不 activate): - 訊息含 [執行已存在 scheduler skill: 標記 → 為 /sched-<name 手動 trigger,當前 agent 直接執行 body - 訊息為一份完整的 SKILL.md body( Title + 任務 + 輸出格式…

Its SKILL.md is about 3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including scripts (for example `scripts/init_scheduler_skill.py`).

It sits in Agent Workflows, covering Scheduled and recurring tasks and Skill authoring. It works with Model Context Protocol. The repository describes itself as: Self-hosted 24/7 personal AI agent that runs on your own machine — memory, schedules, tools and credentials stay local. Single Go binary with MCP. The licence is AGPL-3.0.

When your agent uses it

  • Tasks that involve Scheduled and recurring tasks
  • Tasks that involve Skill authoring

Example prompts

  • “/scheduler-skill-creator”

Requirements

  • Python 3

Workflow steps

7 steps, taken from the step headings in SKILL.md.

  1. 時間檢查門檻(強制首動作)
  2. 解析需求
  3. 時間正規化 + 選 tool
  4. 初始化 skill 目錄(強制走 init 腳本)
  5. 建構 skill 內容(委派 /skill-creator)
  6. 綁定時間
  7. 回報

What it can do on your machine

Read from SKILL.md and the folder at commit c7ba3b0. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • OPENAI_API_KEY
    • DISCORD_BOT_TOKEN
    • CODEX_API_KEY
    • POLYGON_API_KEY
    • STAGING_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Scheduler Skill Creator loads about 3k tokens when it runs. Until then it costs about 213 tokens; SKILL.md has 918 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~213
When it runs · the whole SKILL.md, loaded when a task matches
~3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from agenvoy/Agenvoy at commit c7ba3b0, republished under its AGPL-3.0 licence (© agenvoy). 918 words, ~2,976 tokens.

Download SKILL.mdSave it as .claude/skills/scheduler-skill-creator/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
scheduler-skill-creator
description
建立並排程定時觸發的 skill。**所有新增定時/週期任務、提醒、排程通知的請求必須走此 skill**,禁止直接呼叫 schedules(mode=write)(那是 skill 已存在時的時間綁定工具,不該作為新建排程的入口)。 必定觸發的訊息特徵(任一即活化): - 相對延遲:「X 分鐘後」「X 小時後」「稍後」「待會」「等一下」 - 明確時間:「X 點」「下午 X 點」「明天 X 點」「後天」「YYYY-MM-DD HH:MM」 - 週期性:「每 X 分鐘」「每小時」「每天」「每週」「每月」「定時」「固定」 - 提醒 / 通知意圖:「提醒我」「通知我」「告訴我」+ 時間描述 範例觸發訊息:「5 分鐘後提醒我喝水」「每天早上 9 點抓 HN 頭條」「明天下午 3 點開會」「每 5 分鐘查台積電股價」。 **不觸發**(即使訊息含「觸發」「排程」字眼也不 activate): - 訊息含 `[執行已存在 scheduler skill:` 標記 → 為 `/sched-<name>` 手動 trigger,當前 agent 直接執行 body - 訊息為一份完整的 SKILL.md body(`# Title` + `## 任務` + `## 輸出格式` 結構),無建立/排程動詞 → 為 skill execution,非 creation - 訊息僅含「執行 skill X」「跑 X」「run skill X」無時間 token → 為 execution 流程:解析訊息抽出「要做什麼」「何時觸發」→ 缺項用 ask_user 補問 → 生成 skill 檔案至 ~/.config/agenvoy/skills/scheduler/<short>-<hash8>/SKILL.md(無 scheduler- 前綴,hash 用於避免命名衝突)→ 呼叫 schedules(mode=write) 綁定時間 → 回報。

本 Skill 為 Agenvoy 內部最佳化版本,依 Agenvoy 的執行環境撰寫(run_command 的 CWD、~/.config/agenvoy/skills/.system/ 安裝位置、edit_skill/schedules/find_edit_tool 等工具、subagent 與排程的觸發路徑),不保證適配其他 AI harness。

Scheduler Skill 建立器

目的

scheduler 採 skill-based 觸發:到時間時,daemon 讀 scheduler/<short>/SKILL.md body 並起 in-process subagent 跑(always-allow)。本 skill 的職責 = 「從使用者意圖建出 skill 並綁定時間」,完整跑完 6 步即完成排程。

重要:scheduler 用 skill 與一般 skill 隔離

比較一般 skillscheduler 用 skill
路徑~/.config/agenvoy/skills/<name>/SKILL.md~/.config/agenvoy/skills/scheduler/<short>-<hash8>/SKILL.md
frontmatter name<name><short>-<hash8> (無前綴)
一般 /<name> 補全出現不出現(scanner 不掃 scheduler/)
呼叫方式/<name> 觸發schedules(mode=write, target=task, skill_name=<short>-<hash8>) / schedules(mode=write, target=cron, skill_name=<short>-<hash8>)

成功標準

  • 生成檔案: ~/.config/agenvoy/skills/scheduler/<short>-<hash8>/SKILL.md,frontmatter name: <short>-<hash8>(無前綴)
  • skill body 描述任務行為、引用具體 tool
  • 呼叫 schedules(mode=write, target=task, time, skill_name=<short>-<hash8>) 或 schedules(mode=write, target=cron, time, skill_name=<short>-<hash8>) 綁定時間成功
  • 回報生成位置、full name(含 hash)、排程類型(one-shot/recurring)、下次觸發時間

步驟

0. 時間檢查門檻(強制首動作)

在呼叫任何其他 tool(特別是 run_command 跑 init script)之前,先檢查使用者訊息是否含明確時間 token。時間 token 定義:

類別Token 範例
相對延遲N 分鐘後/N 小時後/N 秒後/待會/稍後/等一下
絕對時鐘X 點/HH:MM/下午 X 點/晚上 X 點
絕對日期今天/明天/後天/YYYY-MM-DD
週期每 N 分/每小時/每天/每週/每月/定時/固定

判定流程(兩個 yes/no 各自獨立檢查;缺項一律走 ask_user tool call):

  1. 任務 token 存在?(訊息含可執行動作描述)
    • 否 → 呼叫 ask_user tool:{"questions":[{"question":"要做什麼?例:抓 HN 頭條 / 提醒我喝水"}]}
  2. 時間 token 存在?(上表任一)
    • 否 → 呼叫 ask_user tool:{"questions":[{"question":"什麼時候執行?例:5 分鐘後 / 每 5 分鐘 / 明天 9 點"}]}

兩項都缺時,同一個 ask_user 的 questions 帶兩題送出。收到回傳的 answers 後,把答案併入原訊息重跑步驟 0;兩者都齊才進步驟 1。

問題一律用 ask_user tool call 送出:ask_user 走 pending.Ask 阻塞等待 reply,harness 開 popup/prompt 收答案,agent 收到結構化 answers 後接著執行。TUI/CLI/Web/Telegram/Discord 都支援;只有 chat completions 端點沒有這個通道。

需要補問的例子:

訊息為何要 ask_user
「說我很棒」「提醒我」「叫我喝水」任務有,時間無
「等等」「之後」「找時間」模糊詞不算明確 token
「下班後」「有空時」無可正規化為 cron/datetime 的時間值

時間以使用者說的為準:沒說就用 ask_user 問,不用預設值(+10m、09:00)或推測補齊。

1. 解析需求

步驟 0 通過後(任務與時間都齊全),抽兩元素:

  • 任務:要做什麼(行為描述)
  • 時間:何時觸發

範例解析:

訊息任務時間
每 5 分鐘提醒我台積電最新股價查台積電股價並提醒每 5 分鐘(recurring)
明天早上 9 點提醒我開會開會提醒明天 09:00(one-shot)
5 分鐘後叫我喝水喝水提醒+5m(one-shot)
每天抓 HN 頭條給我抓 HN 頭條摘要每天(recurring,步驟 0 已要求補問時段)

缺項一律以 ask_user tool call 補齊;questions 是 array,當下所有缺項寫成多題一起送。

2. 時間正規化 + 選 tool
使用者說工具time 參數
X 分鐘後schedules(mode=write, target=task)+Xm
X 小時後schedules(mode=write, target=task)+Xh
今天 X 點(24h)schedules(mode=write, target=task)HH:MM
明天 / 特定日期 X 點schedules(mode=write, target=task)YYYY-MM-DD HH:MM
每 X 分鐘schedules(mode=write, target=cron)*/X * * * *
每小時schedules(mode=write, target=cron)0 * * * *
每天 X 點schedules(mode=write, target=cron)MM HH * * *
每週 N(0=Sun, 1=Mon, ..., 6=Sat)schedules(mode=write, target=cron)MM HH * * N
每月 D 日 X 點schedules(mode=write, target=cron)MM HH D * *

決定走 schedules(mode=write) target=task(一次性)或 target=cron(週期)。

3. 初始化 skill 目錄(強制走 init 腳本)

腳本路徑:run_command 的 CWD 是使用者的工作目錄,不是本 skill 目錄,相對路徑 scripts/... 必定找不到(實測會讓 agent 反覆 glob 找檔案,白燒數輪)。本 skill 只服務 Agenvoy、安裝位置固定,一律用絕對路徑 ~/.config/agenvoy/skills/.system/scheduler-skill-creator/scripts/。

禁止直接用 edit_skill(mode=write)/edit_file(mode=write) 建立 SKILL.md —— LLM 容易寫成 <short>.md 而非 <short>/SKILL.md,或誤加 scheduler- 前綴;也無法自行產生 hash suffix。必須先跑 init 腳本。

用 run_command 執行:

bash
python3 ~/.config/agenvoy/skills/.system/scheduler-skill-creator/scripts/init_scheduler_skill.py <short-name>

<short-name> 由步驟 1 的任務描述推導(kebab-case、不含 scheduler- 前綴、不含 hash)。腳本會:

  • 正規化 short name(lowercase、hyphen-case)
  • 產生 8-char hex random suffix(secrets.token_hex(4)),組成 full name <short>-<hash8>
  • 建立 ~/.config/agenvoy/skills/scheduler/<short>-<hash8>/SKILL.md,寫入含 frontmatter name: <short>-<hash8> 的 TODO 模板

捕捉 full name:stdout 會印一行 [OK] skill name: <short>-<hash8>,完整字串(含 hash)是後續步驟 4/5 要用的 skill_name。極罕見 hash 碰撞時印 [ERROR] collision exit 1,重跑一次即可。

重綁定既有 skill 的時間(user 說「把那個 X 改成 Y」):不再跑 init 腳本,直接用既存 full name 進步驟 5;既存 full name 可從先前回報訊息找,或 find_files(mode=list) 列出 ~/.config/agenvoy/skills/scheduler/ 選擇。

4. 建構 skill 內容(委派 /skill-creator)

目錄與名稱在步驟 3 已經定案,這一步只做內容。呼叫 /skill-creator,用它的「編輯現有 Skill」路徑填內容,不要在這裡自己重寫一套設計流程。

/skill-creator 編輯現有 skill:~/.config/agenvoy/skills/scheduler/<short>-<hash8>/
任務:<步驟 1 收集到的行為細節>

交給 /skill-creator 的部分(照它的步驟走):

它的步驟在這裡的作用
一:透過具體範例理解已由步驟 1 完成,把結果直接給它,不要再問一次
二:規劃可重用內容決定要不要 scripts/
二點五:工具/Skill 搭配探索讀 ## Skills → find_edit_tool(mode=search) → 都沒有才寫 scripts/*.py
四:編輯edit_skill(mode=patch) 取代模板的 [TODO: ...]

這裡的額外約束(/skill-creator 不知道排程的規則,必須由你把關):

  • 不准跑 init_skill.py(它會用自己的命名規則在 skills/ 底下另開一個目錄)。目錄已存在,走「編輯現有 Skill」路徑
  • 不准改名、不准搬位置 —— 名稱固定 <short>-<hash8>,位置固定 ~/.config/agenvoy/skills/scheduler/<short>-<hash8>/
  • 不准跑步驟五(打包) —— 排程 skill 不外流
  • body 引用的 skill/tool 必須確認存在:skill 以 system prompt 的 ## Skills 清單為準(那份清單已在 context 裡,不要用 run_skill activate 驗證 —— 每次 activate 都是一輪往返加一整份 SKILL.md 進 context);tool 名稱以 find_edit_tool(mode=search) 的回傳為準。觸發時 subagent 找不到會直接 abort,使用者拿不到結果也看不到原因
  • scripts/ 寫進 scheduler/<short>-<hash8>/scripts/,不用 edit_tool 產全域工具

必填欄位:

  • description: ← 步驟 1 的「一句話描述」
  • ## 任務 ← 步驟 1 的「行為細節」,引用已確認存在的 skill/tool
  • ## 輸出格式 ← 期望輸出形式

禁止在 skill body 內加任何「推送到 channel」「呼叫 http_request 給 Discord」「呼叫 MCP discord tool」之類的 notify 指令 —— scheduler 觸發後 runtime 自動把輸出送回原 caller channel(Discord 來源送回原頻道、CLI/HTTP 來源送回 action.log)。Skill body 只需專注產出任務結果文字。

Show full SKILL.md (378 more words)Show less
5. 綁定時間

依步驟 2 結果呼叫,skill_name 用步驟 3 stdout 印出的完整 <short>-<hash8>:

schedules(mode=write)(target="task", time="<time_value>", skill_name="<short>-<hash8>")
# 或
schedules(mode=write)(target="cron", time="<cron_expression>", skill_name="<short>-<hash8>")

skill_name 不加 scheduler- 前綴(內部會直查 ~/.config/agenvoy/skills/scheduler/<short>-<hash8>/SKILL.md 確認存在)。session_id 內部自動取 caller e.SessionID,不必傳。

成功會回 ID: <hash> 等資訊。失敗(skill 不存在、cron 表達式錯誤、time 已過)就 abort 本流程,向使用者回報原因。

6. 回報

簡短告知:

  • skill 已建立: ~/.config/agenvoy/skills/scheduler/<short>-<hash8>/SKILL.md
  • skill name: <short>-<hash8>(無前綴,hash 自動產生避免命名衝突)
  • 排程: schedules(mode=write) 的回應內容(含下次觸發時間、ID)

命名規則

項目規則範例
short name(輸入 init script)lowercase / hyphen-case,無 scheduler- 前綴、無 hashdaily-hn-digest、tsmc-stock-watch
hash suffixinit script 產生的 8-char hex randoma3f9b2c1
full name(檔案/frontmatter/schedules(mode=write) skill_name 用)<short>-<hash8>tsmc-stock-watch-a3f9b2c1
目錄~/.config/agenvoy/skills/scheduler/<short>-<hash8>/.../tsmc-stock-watch-a3f9b2c1/

禁止在任何環節加 scheduler- 前綴。scheduler 已表達於目錄路徑,加前綴只會造成 scheduler/scheduler-foo-<hash>/ 之類的重複命名。

禁止自行產生/猜測 hash suffix。Hash 必須由 init script 用 secrets.token_hex(4) 隨機生成,LLM 從 stdout 抓 [OK] skill name: 那行的值即可。

輸出路由(runtime 自動處理)

scheduler 觸發後,runtime 會把 subagent 產出的最終文字自動送回 caller 端:

Caller session prefix路由行為
dc-*(Discord)自動 ChannelMessageSend 回原頻道(含 - <skill 短名> 標籤)
cli-*/http-*/TUI 觸發留在 session history/action.log,由 caller 端工具讀取

所以 skill body 不需要、也禁止寫「推送到 channel」「呼叫 http_request 發 Discord webhook」「呼叫 MCP discord tool」之類的 notify 指令。寫了會在觸發時造成多餘的 token 與認證錯誤(subagent 沒 DISCORD_BOT_TOKEN 互動環境)。

Secret/API Key(skill body 引用 token 時必看)

被觸發的 scheduler skill 跑在獨立 subagent,不持有任何明文 secret。若 body 內呼叫的 tool(如 http_request、自製 api_tool、script_tool)需要 API token:

  • 命名格式:{品牌}_API_KEY(SCREAMING_SNAKE_CASE),例 OPENAI_API_KEY、CODEX_API_KEY、POLYGON_API_KEY、STAGING_API_KEY
  • 儲存位置:macOS keychain 中 service = agenvoy、account = key 名,組合識別 agenvoy.{key}(例 agenvoy.OPENAI_API_KEY)
  • 取值方式:
    • api_tool:auth.env: "<KEY_NAME>"(schema 只記 key 名,無 agenvoy. 前綴)
    • script_tool:讀 OS keychain(service agenvoy)—— macOS security find-generic-password -s agenvoy -a <KEY_NAME> -w;Linux secret-tool lookup service agenvoy account <KEY_NAME>(key 名同樣不帶前綴)
    • skill body 純文字:直接引用 tool,不在 SKILL.md 寫明文 token、不寫 export ENV=value 之類指令
  • 缺 key 處置:若觸發時 keychain 無對應 key,subagent 會在 tool 端拿到 401/空值錯誤;skill body 不負責「補登」,請使用者預先用 store_secret 落地

禁止在 scheduler skill 的 SKILL.md frontmatter/body 任何位置寫死 token 值或要求使用者在 cron 觸發時互動輸入 — subagent 無對話環境,不可能收 plaintext。

時間敏感性提醒(寫入 skill body 時注意)

被觸發的 skill 跑在獨立 subagent session,沒有當下對話上下文。skill body 必須:

  • 不依賴「使用者剛才說了什麼」
  • 不假設特定變數已被定義
  • 引用具體 tool 名稱與參數(自包含可重現)
  • cron 觸發時反覆執行,邏輯應 idempotent 或自帶 dedup

完整範例

使用者:「每 5 分鐘提醒我台積電最新股價」

步驟 1 解析:任務 = 查 2330.TW 股價;時間 = 每 5 分鐘 → recurring。兩者皆有,不問。

步驟 2 正規化:schedules(mode=write)(target="cron", time="*/5 * * * *", ...)

步驟 3 run_command python3 ~/.config/agenvoy/skills/.system/scheduler-skill-creator/scripts/init_scheduler_skill.py tsmc-stock-watch

stdout:

[OK] created   : /Users/.../skills/scheduler/tsmc-stock-watch-a3f9b2c1/SKILL.md
[OK] skill name: tsmc-stock-watch-a3f9b2c1
...

抓出 full name tsmc-stock-watch-a3f9b2c1。

步驟 4 edit_skill(mode=patch) 填入(frontmatter name 用 full name):

markdown
---
name: tsmc-stock-watch-a3f9b2c1
description: 每 5 分鐘抓取台積電 2330.TW 即時股價並提醒。
---

# Tsmc Stock Watch

## 任務

透過 `search_web` 找到 `2330.TW` 最新報價來源,再用 `fetch_page` 讀取結果。

## 輸出格式

`台積電 2330.TW: NT$<price> (<change>% 從昨收)` 一行。

步驟 5 schedules(mode=write)(target="cron", time="*/5 * * * *", skill_name="tsmc-stock-watch-a3f9b2c1")

步驟 6 回報:「已排程每 5 分鐘觸發 tsmc-stock-watch-a3f9b2c1。下次觸發 HH:MM。」

不做的事

  • 不用 edit_skill(mode=write)/edit_file(mode=write) 直接建立 SKILL.md —— 必須走 init_scheduler_skill.py,避免結構錯誤(<name>.md vs <name>/SKILL.md)
  • 不在 short name、frontmatter、skill_name 任何位置加 scheduler- 前綴
  • 不留 [TODO: ...] 佔位符在最終 skill —— 步驟 4 須把所有 TODO 替換為具體內容
  • 時間以使用者說的為準;沒說就用 ask_user 問,不用預設值或推測補齊
  • 不跳過步驟 5 的 schedules(mode=write) —— skill 建立但沒綁時間 = 排程不會觸發
  • 不在 body 引用未經 find_edit_tool(mode=search) 確認存在的 tool name —— 觸發時 subagent 找不到 tool 會直接 abort,使用者拿不到結果也看不到錯誤原因
  • 不用 edit_tool 產全域 script_*/api_* 工具 —— 排程要的腳本寫進自己的 scripts/(步驟 4),全域工具是 tool generate 的職責,兩者不混用
  • 不讓步驟 4 委派出去的 /skill-creator 跑 init_skill.py 或 package_skill.py —— 前者會用它自己的命名規則在 skills/ 底下另開目錄(排程綁的是 scheduler/<short>-<hash8>,綁不到就不會觸發),後者產出的 .skill 排程用不到

© agenvoy, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (scripts) in extensions/skills/scheduler-skill-creator of agenvoy/Agenvoy.

  • SKILL.md
  • scripts/init_scheduler_skill.py

Open the folder on GitHubat commit c7ba3b0

Compare with similar skills

Scheduler Skill Creator next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Scheduler Skill Creator compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Scheduler Skill Creator this skillagenvoy/Agenvoy439—~3kAutomated safety check: PassAGPL-3.0
Toolifycoreyhaines31/makerskills851—~2.9kAutomated safety check: NotesMIT
Skill Seekers Builderyusufkaraaslan/Skill_Seekers15k—~760Automated safety check: PassMIT
PicoClaw Agentsipeed/picoclaw30k—~7.2kAutomated safety check: NotesMIT
Mistral Vibe Plugin Creatormistralai/mistral-vibe5.1k—~3.1kAutomated safety check: PassApache-2.0
Workflow Schema Tuningbreaking-brake/cc-wf-studio5.4k—~1.3kAutomated safety check: PassCustom licence

Similar skills

  • Toolify

    coreyhaines31/makerskills

    When you want to integrate an external tool, API, MCP server, or service into a project — the wizard walks you through auth, config, env vars, client wrapper code, example usage, and an optional…

    851 GitHub stars~2.9k tokensUpdated 2 days ago
    Agent WorkflowsAuto-check: notes
  • Skill Seekers Builder

    yusufkaraaslan/Skill_Seekers

    Detects the type of a knowledge source and uses the Skill Seekers MCP tools to turn docs, repos, PDFs or videos into packaged AI skills.

    15k GitHub stars~760 tokensUpdated 10 days ago
    Agent WorkflowsAuto-check passed
  • PicoClaw Agent

    sipeed/picoclaw

    Answers questions about running and changing PicoClaw, from onboarding and model selection to MCP server setup, skill loading and scheduled jobs.

    30k GitHub stars~7.2k tokensUpdated yesterday
    Agent WorkflowsAuto-check: notes
  • Mistral Vibe Plugin Creator

    mistralai/mistral-vibe

    Official

    Shows how to build a Vibe plugin package in the Agent Plugins 1.0 format, with a plugin.json manifest and optional skills, MCP servers, hooks and other components.

    5.1k GitHub stars~3.1k tokensUpdated 2 days ago
    Agent WorkflowsAuto-check passed
  • Workflow Schema Tuning

    breaking-brake/cc-wf-studio

    Guides edits to cc-wf-studio's workflow schema so AI agents generate better workflows, treating schema text as prompt engineering rather than validation.

    5.4k GitHub stars~1.3k tokensUpdated 4 days ago
    Agent WorkflowsAuto-check passed
  • Skill Authoring

    uvwt/agentdock

    创建、设计、修改、重构和验证 AgentDock Skill 时使用;负责 Agent Skills 兼容的 SKILL.md、可移植核心、引用、辅助脚本、测试、安全边界和本地真实验证。

    1.2k GitHub stars~1.5k tokensUpdated today
    Agent WorkflowsAuto-check: notes

More from agenvoy/Agenvoy

  • Skill Creator

    agenvoy/Agenvoy

    Create, edit, improve, or audit AgentSkills. An agent skill from agenvoy/Agenvoy.

    439 GitHub stars~3k tokensUpdated today
    Auto-check passed
  • Extension Install

    agenvoy/Agenvoy

    Install an Agenvoy extension from pkg.agenvoy.com registry (browse/pick) or local tarball into ~/.config/agenvoy/tools/.extension/<type/<name@<version/.

    439 GitHub stars~2.9k tokensUpdated today
    Auto-check: notes
  • Extension Upload

    agenvoy/Agenvoy

    Package a script tool under ~/.config/agenvoy/tools/script/ into a tar.gz and publish to pkg.agenvoy.com registry.

    439 GitHub stars~6.1k tokensUpdated today
    Auto-check passed

Categories

Questions about Scheduler Skill Creator

What does Scheduler Skill Creator do?

建立並排程定時觸發的 skill。所有新增定時/週期任務、提醒、排程通知的請求必須走此 skill,禁止直接呼叫 schedules(mode=write)(那是 skill 已存在時的時間綁定工具,不該作為新建排程的入口)。. Scheduler Skill Creator is an agent skill from agenvoy/Agenvoy.

When should I use Scheduler Skill Creator?

Scheduler Skill Creator fits situations like: tasks that involve Scheduled and recurring tasks; tasks that involve Skill authoring.

How do I install Scheduler Skill Creator in Claude Code?

Run `npx skills add agenvoy/Agenvoy --skill scheduler-skill-creator -a claude-code`. Or copy the skill folder (extensions/skills/scheduler-skill-creator in agenvoy/Agenvoy) into .claude/skills/scheduler-skill-creator in your project. Claude Code loads it when a task matches its description.

How do I install Scheduler Skill Creator in Codex?

Run `npx skills add agenvoy/Agenvoy --skill scheduler-skill-creator -a codex`. Or copy the skill folder (extensions/skills/scheduler-skill-creator in agenvoy/Agenvoy) into .agents/skills/scheduler-skill-creator in your project. Codex loads it when a task matches its description.

Can I use Scheduler Skill Creator in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add agenvoy/Agenvoy --skill scheduler-skill-creator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/scheduler-skill-creator, .gemini/skills/scheduler-skill-creator, .github/skills/scheduler-skill-creator and .opencode/skills/scheduler-skill-creator in your project.

What does Scheduler Skill Creator need to run?

Going by SKILL.md and its folder, Scheduler Skill Creator needs Python for the scripts in its folder, the command-line tools its instructions call (python3) and credentials named OPENAI_API_KEY, DISCORD_BOT_TOKEN, CODEX_API_KEY and POLYGON_API_KEY. Our summary lists: Python 3.

Does Scheduler Skill Creator access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Scheduler Skill Creator safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Scheduler Skill Creator use?

Scheduler Skill Creator is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Scheduler Skill Creator use?

About 3k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Scheduler Skill Creator?

Skills that share tags, products or a category with Scheduler Skill Creator: Toolify (coreyhaines31/makerskills, 851 stars), Skill Seekers Builder (yusufkaraaslan/Skill_Seekers, 15k stars), PicoClaw Agent (sipeed/picoclaw, 30k stars) and Mistral Vibe Plugin Creator (mistralai/mistral-vibe, 5.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Scheduler Skill Creator?

agenvoy (a GitHub organization) maintains it in agenvoy/Agenvoy, which has 439 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on October 10, 2026.

Source: agenvoy/Agenvoy on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.