weaveq/onmyagent/create-automation
- community
Checking that the SKILL.md file is still in the repository.
Create accurate OnMyAgent scheduled or one-time automation proposals from expert or ordinary conversations. Use when the user asks to automate, schedule, repeat, remind, periodically run, or execute a task later, including daily/weekly/monthly intervals and one-time runs.
Install
npx vskill@latest install weaveq/onmyagent/create-automationSKILL.md
Create OnMyAgent Automation
Create a proposal file that OnMyAgent can review with the user and convert into a real automation task. Never claim the task is installed merely because the proposal file exists.
Workflow
- Determine the task goal and the smallest self-contained prompt needed when it runs without the current chat history.
- Determine the schedule. Ask only for required details that cannot be inferred safely.
- Read references/proposal-schema.md.
- Write one JSON file to
automations/proposals/<descriptive-slug>.jsoninside the current session's selected folder. - Tell the user that the proposal is ready for OnMyAgent confirmation. Do not ask them to edit JSON manually.
Context boundary
- Omit
sourceSessionIdandworkspaceDirectory. OnMyAgent injects the trusted source conversation and its selected folder. - Omit
modelunless the user explicitly requests a different model. OnMyAgent otherwise inherits the current conversation model. - Do not copy secrets, tokens, or transient chat text into
prompt. - Refer to files relative to the selected folder whenever possible.
- Make
promptrunnable in a fresh conversation: include the objective, required inputs, expected outputs, and any important safety constraints.
Multiple tasks
Write one proposal file per independently schedulable task. Use distinct titles and filenames. Do not combine tasks with different schedules into one proposal.
Validation
Before finishing, verify that the JSON parses and that every required field matches the schema. If the schedule is ambiguous, ask the user instead of inventing a time or timezone.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingapps/desktop/resources/bundled-skills/create-automation/SKILL.md
Popularity
- Repository stars
- 6
- 7-day trend score
- 0
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/weaveq/onmyagent/create-automation)