Geo Fundamentals
wasp-lang/wasp
Generative Engine Optimization for AI search engines (ChatGPT, Claude, Perplexity).
Review a ChatGPT Space page and its schedules, recommend useful recurring work, and create, update, or remove scheduled automations.
$ npx skills add asgeirtj/system_prompts_leaks --skill manage-schedules -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install asgeirtj/system_prompts_leaks manage-schedules --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/asgeirtj/system_prompts_leaks.git skills-src && mkdir -p .claude/skills && cp -r skills-src/OpenAI/dots/skills/manage-schedules .claude/skills/manage-schedules && rm -rf skills-srcUse ~/.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/
Install the "manage-schedules" agent skill from https://github.com/asgeirtj/system_prompts_leaks/tree/main/OpenAI/dots/skills/manage-schedules into .claude/skills/manage-schedules/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "manage-schedules", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/asgeirtj/system_prompts_leaks/tree/main/OpenAI/dots/skills/manage-schedulesType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add asgeirtj/system_prompts_leaks --skill manage-schedules -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install asgeirtj/system_prompts_leaks manage-schedules --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/asgeirtj/system_prompts_leaks.git skills-src && mkdir -p .agents/skills && cp -r skills-src/OpenAI/dots/skills/manage-schedules .agents/skills/manage-schedules && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "manage-schedules" agent skill from https://github.com/asgeirtj/system_prompts_leaks/tree/main/OpenAI/dots/skills/manage-schedules into .agents/skills/manage-schedules/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "manage-schedules", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add asgeirtj/system_prompts_leaks --skill manage-schedules -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install asgeirtj/system_prompts_leaks manage-schedules --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/asgeirtj/system_prompts_leaks.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/OpenAI/dots/skills/manage-schedules .cursor/skills/manage-schedules && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "manage-schedules" agent skill from https://github.com/asgeirtj/system_prompts_leaks/tree/main/OpenAI/dots/skills/manage-schedules into .cursor/skills/manage-schedules/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "manage-schedules", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/asgeirtj/system_prompts_leaks.git --path OpenAI/dots/skills/manage-schedules--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add asgeirtj/system_prompts_leaks --skill manage-schedules -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install asgeirtj/system_prompts_leaks manage-schedules --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/asgeirtj/system_prompts_leaks.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/OpenAI/dots/skills/manage-schedules .gemini/skills/manage-schedules && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "manage-schedules" agent skill from https://github.com/asgeirtj/system_prompts_leaks/tree/main/OpenAI/dots/skills/manage-schedules into .gemini/skills/manage-schedules/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "manage-schedules", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install asgeirtj/system_prompts_leaks manage-schedulesInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add asgeirtj/system_prompts_leaks --skill manage-schedules -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/asgeirtj/system_prompts_leaks.git skills-src && mkdir -p .github/skills && cp -r skills-src/OpenAI/dots/skills/manage-schedules .github/skills/manage-schedules && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "manage-schedules" agent skill from https://github.com/asgeirtj/system_prompts_leaks/tree/main/OpenAI/dots/skills/manage-schedules into .github/skills/manage-schedules/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "manage-schedules", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add asgeirtj/system_prompts_leaks --skill manage-schedules -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install asgeirtj/system_prompts_leaks manage-schedules --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/asgeirtj/system_prompts_leaks.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/OpenAI/dots/skills/manage-schedules .opencode/skills/manage-schedules && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "manage-schedules" agent skill from https://github.com/asgeirtj/system_prompts_leaks/tree/main/OpenAI/dots/skills/manage-schedules into .opencode/skills/manage-schedules/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "manage-schedules", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
manage-schedulesReview a ChatGPT Space page and its schedules, recommend useful recurring work, and create, update, or remove scheduled automations.
Manage Schedules is an agent skill from asgeirtj/system_prompts_leaks. Review a ChatGPT Space page and its schedules, recommend useful recurring work, and create, update, or remove scheduled automations.
Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It works with OpenAI. The repository describes itself as: Documented system prompts from Anthropic - Claude Fable 5.1, Opus 5.5, Claude Design, Claude Code. OpenAI - ChatGPT GPT-6-Astra, Codex. Google - Gemini 3.8 Flash, 3.1 Pro… The licence is CC0-1.0.
3 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 60d44cc. It shows what the files ask for, not the result of running them.
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.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
chatgpt.comFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Manage Schedules loads about 1.9k tokens when it runs. Until then it costs about 37 tokens; SKILL.md has 1,179 words of instructions outside code blocks.
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.
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); files beside SKILL.md are not scanned.
The full file from asgeirtj/system_prompts_leaks at commit 60d44cc, republished under its CC0-1.0 licence (© asgeirtj). 1,179 words, ~1,914 tokens.
.claude/skills/manage-schedules/SKILL.md (or your agent's skills folder).This skill often starts from a page action with an autofilled prompt such as "Manage the schedules for this page." Treat this as a request to assess the page's scheduling needs and lead the setup; the user need not describe an automation upfront. Use the page in context. If no page ID is available, use the page tools to find a recent relevant page. If the target is still unclear, ask the user which page they mean or do not use this skill, they may not be doing something related to pages.
A page is a persistent document the user can edit and return to. It can have multiple schedules, each doing different work—for example, refreshing figures, summarizing new activity, or maintaining a task list. A page can include rich content, like files and embedded visualizations.
A page may also contain a native agent_instructions block. These are shared guidelines for agents working on the page. Every scheduled run will read the current page and its Agent Instructions. Keep each automation's specific job in its prompt and its timing in its schedule; the page instructions don't need to describe or manage every automation.
Users may also put requests for automated work in Agent Instructions. Use those requests to help create or adjust schedules that match what they want. For example, for "Every day, update this page according to my requests," use the Agent Instructions to identify the work and create or update the appropriate daily automation.
Read the page with read_page and its existing schedules with list_page_automations. Use the returned page and schedule, along with the existing conversation context to holistically understand the goal of the page and schedules.
Starting from your understanding above in the "establish" phase, plan and execute an update to the page and schedules that will result in a coherent, useful, page, using your knowledge, tools and the user's connecting plugins.
The cases below use "sparse schedules" to mean no schedules yet, or existing schedules that don't fully cover the user's goals:
a. Sparse page, sparse schedules, default/unclear intent
The user may have a sparse page when they start this management workflow. Using your knowledge of page features (in the pages plugin), your tools, and the users connected plugins, you should engage the user in an interactive conversation using request_user_input or request_user_input_async to help them build a page and an associated set of schedules for that page.
For example (not exhaustive):
Todo List
Weekly Tracker
Be curious, offer a useful starting point, and get to delight quickly by making useful edits. Work through a first pass of the recurring work with the user to help build out the page. The goal is a great starting document and schedule.
b. Sparse page, sparse schedules, clear intent
The user may have a sparse page and sparse schedules, but very clear intent! In some cases, this clear intent is coming from a template they pressed.
In this case, follow their clear intent to build the page and schedules they want. Clarify if needed using request_user_input or request_user_input_async , but generally try to get them to their goal. If there are features of pages that they'd benefit from, use them while building, but don't override intent.
c. Existing page, sparse schedules, default/unclear intent
Work within the existing page and suggest schedules that complement it. You can still suggest helpful features and make edits that support the user's goal, but sometimes the page is already in good shape and only needs a schedule.
d. Existing page, sparse schedules, clear intent
Work within the page and set-up what the user wants.
e. Existing page, existing schedules, any intent
For schedules that already cover the work, focus on the adjustments needed to accomplish the user's goals. For gaps in coverage, follow the clear or unclear intent paths above. Keep useful schedules and deliberate choices like paused status unless the requested change calls for adjusting them. If the page and schedules already serve the user's goals, leave them as they are and briefly explain that no changes are needed.
f. Other
Focus on working with the user to build a page and schedules that will accomplish their goal, be curious, ask questions, and then get them there.
After you've determined the user's needs, made some edits, or planned, then it's time to apply the schedules.
a. Apply the page and schedule changes
Use the Pages plugin's tools and skills to make the page updates you've planned with the user: $pages:write-page for writing and editing, $pages:organize-space for structure, and $pages:maintain-space for updates from sources. Preserve unrelated content and keep existing Agent Instructions unless the user wants to change them. You can also use visualizations and page tools.
Use automations.create for a new schedule and automations.update to change an existing one. When updating a hosted schedule, use the exact automation_id returned by list_page_automations as the jawbone_id. Work with the schedule that covers the user's goal; an existing schedule doesn't prevent adding another that does different work.
You can remove schedules that are no longer relevant or have been replaced. If removal isn't available, use automations.update with is_enabled: false. Keep schedules that still serve a distinct purpose.
b. Write the schedule prompt(s)
Give each schedule enough context to do its job in a new run. Include the full page URL, https://chatgpt.com/space/{page_id}, using the page's exact ID. Describe the work, sources and plugin capabilities to use, how results should update the page—for example, updating an existing section or adding a dated entry—and what user content or state to preserve. Ask it to read the current page and its Agent Instructions.
Check that the scheduled run can use the selected sources and tools. If you've done a first pass with the user, use what you learned to refine the prompt. Preserve the timing the user requested or accepted; otherwise choose a reasonable time in their known timezone.
c. Attach the schedule to the page
After creating a hosted schedule, call attach_automation_to_page with the page ID, the returned automation ID, and automation_role: "task". Omit controller_automation_id.
If the runtime only supports create_local, use it and link the schedule when local page attachments are supported. If linking isn't available or fails, keep the schedule you created and tell the user they can find it in their schedules.
d. Confirm what's set up
Briefly tell the user what changed, what was removed or disabled, and when the active schedules will run. Link to the page and mention anything that's still missing. If you completed a first pass during setup, distinguish that work from future scheduled runs.
© asgeirtj, CC0-1.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in OpenAI/dots/skills/manage-schedules of asgeirtj/system_prompts_leaks.
Open the folder on GitHubat commit 60d44cc
Manage Schedules 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Manage Schedules this skillasgeirtj/system_prompts_leaks | 69k | — | ~1.9k | Automated safety check: Pass | CC0-1.0 | |
| Geo Fundamentalswasp-lang/wasp | 19k | 9 repos | ~861 | Automated safety check: Pass | MIT | |
| AI SDKvercel-labs/ai-facts | 168 | 20 repos | ~1.2k | Automated safety check: Pass | None | |
| AI Image Generation and Editingzhayujie/CowAgent | 47k | — | ~1.3k | Automated safety check: Pass | MIT | |
| PR Design DocOpenHands/OpenHands | 91k | — | ~2.4k | Automated safety check: Pass | MIT | |
| SEO GeoReScienceLab/opc-skills | 1.8k | 4 repos | ~2.1k | Automated safety check: Pass | Apache-2.0 |
wasp-lang/wasp
Generative Engine Optimization for AI search engines (ChatGPT, Claude, Perplexity).
vercel-labs/ai-facts
Answer questions about the AI SDK and help build AI-powered features.
zhayujie/CowAgent
Generates or edits images from text prompts through a Python script that picks an image backend based on which API keys are configured.
OpenHands/OpenHands
For a non-trivial pull request, write a self-contained HTML design doc under the temporary .pr/ directory and link a visibility-appropriate preview in the PR description, so maintainers grasp the…
ReScienceLab/opc-skills
SEO & GEO (Generative Engine Optimization) for websites. An agent skill from ReScienceLab/opc-skills.
alibaba/open-code-review
Runs the ocr command-line tool to review Git changes, a commit or a branch comparison with an AI model, returning line-level comments and optionally applying fixes.
asgeirtj/system_prompts_leaks
Shows one digest of coding-agent sessions across your connected machines and lets you open, read, steer, approve, stop and close them, over Herdr, tmux or MSP.
asgeirtj/system_prompts_leaks
Diagnoses a Muse Code installation's own failures from binary and session evidence, instead of treating the report as an ordinary repository bug.
asgeirtj/system_prompts_leaks
A skill your agent uses whenever the user wants to create, read, edit, or manipulate Word documents (.docx) or Word templates (.dotx).
asgeirtj/system_prompts_leaks
Runs a goal as a project in which the agent coordinates separate agent threads, judging when to split the work, and interviews you first when nothing can be verified.
asgeirtj/system_prompts_leaks
Creates and validates a new native Muse plugin package in the current workspace, limited to five capability families, and leaves installation to you.
asgeirtj/system_prompts_leaks
A skill your agent uses when the user's prompt requires (1) researching a topic across multiple sources, comparing options or alternatives, analyzing trends or history, understanding markets or…
Works with
Review a ChatGPT Space page and its schedules, recommend useful recurring work, and create, update, or remove scheduled automations. Manage Schedules is an agent skill from asgeirtj/system_prompts_leaks. Review a ChatGPT Space page and its schedules, recommend useful recurring work, and create, update, or remove scheduled automations.
Run `npx skills add asgeirtj/system_prompts_leaks --skill manage-schedules -a claude-code`. Or copy the skill folder (OpenAI/dots/skills/manage-schedules in asgeirtj/system_prompts_leaks) into .claude/skills/manage-schedules in your project. Claude Code loads it when a task matches its description.
Run `npx skills add asgeirtj/system_prompts_leaks --skill manage-schedules -a codex`. Or copy the skill folder (OpenAI/dots/skills/manage-schedules in asgeirtj/system_prompts_leaks) into .agents/skills/manage-schedules in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add asgeirtj/system_prompts_leaks --skill manage-schedules -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/manage-schedules, .gemini/skills/manage-schedules, .github/skills/manage-schedules and .opencode/skills/manage-schedules in your project.
SKILL.md names no scripts, command-line tools or credentials: Manage Schedules is instructions for the agent only.
SKILL.md names 1 domain. In commands or code: chatgpt.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
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. Review the folder before installing.
Manage Schedules is published under the CC0-1.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.9k tokens (SKILL.md is roughly 7.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Manage Schedules: Geo Fundamentals (wasp-lang/wasp, 19k stars), AI SDK (vercel-labs/ai-facts, 168 stars), AI Image Generation and Editing (zhayujie/CowAgent, 47k stars) and PR Design Doc (OpenHands/OpenHands, 91k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
asgeirtj (a GitHub user) maintains it in asgeirtj/system_prompts_leaks, which has 69,280 GitHub stars. The repository holds 128 skills in this directory. The repository was last updated on October 10, 2026.
Source: asgeirtj/system_prompts_leaks on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.