Product
thedaviddias/Front-End-Checklist
A skill your agent uses when auditing e-commerce product pages or implementing structured data for a shop.
Research products, compare offers, or place an authorized order using the user's needs, fit, budget, and deadline.
$ npx skills add asgeirtj/system_prompts_leaks --skill shopping -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install asgeirtj/system_prompts_leaks shopping --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/shopping .claude/skills/shopping && 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 "shopping" agent skill from https://github.com/asgeirtj/system_prompts_leaks/tree/main/OpenAI/dots/skills/shopping into .claude/skills/shopping/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "shopping", 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/shoppingType 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 shopping -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install asgeirtj/system_prompts_leaks shopping --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/shopping .agents/skills/shopping && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "shopping" agent skill from https://github.com/asgeirtj/system_prompts_leaks/tree/main/OpenAI/dots/skills/shopping into .agents/skills/shopping/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "shopping", 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 shopping -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install asgeirtj/system_prompts_leaks shopping --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/shopping .cursor/skills/shopping && 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 "shopping" agent skill from https://github.com/asgeirtj/system_prompts_leaks/tree/main/OpenAI/dots/skills/shopping into .cursor/skills/shopping/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "shopping", 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/shopping--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 shopping -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install asgeirtj/system_prompts_leaks shopping --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/shopping .gemini/skills/shopping && 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 "shopping" agent skill from https://github.com/asgeirtj/system_prompts_leaks/tree/main/OpenAI/dots/skills/shopping into .gemini/skills/shopping/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "shopping", 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 shoppingInstalls 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 shopping -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/shopping .github/skills/shopping && 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 "shopping" agent skill from https://github.com/asgeirtj/system_prompts_leaks/tree/main/OpenAI/dots/skills/shopping into .github/skills/shopping/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "shopping", 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 shopping -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 shopping --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/shopping .opencode/skills/shopping && 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 "shopping" agent skill from https://github.com/asgeirtj/system_prompts_leaks/tree/main/OpenAI/dots/skills/shopping into .opencode/skills/shopping/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "shopping", 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.
shoppingResearch products, compare offers, or place an authorized order using the user's needs, fit, budget, and deadline.
Shopping is an agent skill from asgeirtj/system_prompts_leaks. Research products, compare offers, or place an authorized order using the user's needs, fit, budget, and deadline. Use for purchases and gifts.
Its SKILL.md is about 3.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
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.
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.
No URLs in SKILL.md.
From 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.
Shopping loads about 3.7k tokens when it runs. Until then it costs about 38 tokens; SKILL.md has 2,083 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). 2,083 words, ~3,655 tokens.
.claude/skills/shopping/SKILL.md (or your agent's skills folder).Find the item the user would choose if they had time to do the research.
<confirmation_policy> before buying. Recheck the merchant, exact item or variant, quantity, destination, total including fees, and return terms. Don't add warranties, subscriptions, or unapproved substitutes.<confirmation_policy> for the specific information and destination before entering or sending it. Verify the order and return the confirmation, delivery estimate, and important return deadline. If submission is unclear, check order history before retrying.For browser-based shopping, read and follow the browser tool's documentation if it isn't already loaded. It governs the browser check's current approved, supported, and blocked-site information; supported sign-in and guest paths; blocked-route handling and validated alternatives; handoffs; and browser-work progress. No site label grants purchase or information-sharing authorization.
For shopping, prefer guest checkout when available unless the user explicitly asks to use login; this takes precedence over general browser sign-in guidance. Reuse an existing signed-in session rather than logging out. Otherwise, do as much of the shopping and checkout as possible without logging in. Ask the user to sign in only when it's needed to continue.
Apply those rules to the shopping goal: preserve required items and retailers, and ask before changing them. For an alternative, verify the exact item and variant, stock, total, delivery, and usable checkout path. Only say "in the cart" or "ready to buy" once verified. Say what's verified and what the user must do if login, human verification, or permission is needed. Follow <confirmation_policy> before sharing information or buying. When checkout is verified but a retailer change needs approval: "This site is blocking me, but I have the same item ready at [new retailer] checkout for [total], with [delivery]. Okay to buy it there?"
1. A rain jacket for an upcoming trip
User: "Find me a rain jacket for next week's trip."
Action: Compare the measurements with a jacket they returned (ex: that you have evidence of in gmail history), then verify availability, delivery, and returns. Link the exact item, size chart, and return policy.
Guidance: Use purchases and returns to understand the fit; don't assume an order means it worked. An estimated delivery date isn't a guarantee.
dot:
"I'd get this [jacket](LINK_URL) in medium. The shop estimates it could arrive in time on Tuesday."2. A birthday gift with a budget
User: "Find Priya a ceramic birthday gift under $75."
Action: Find an option within budget; verify delivery and whether a gift receipt is available. Link the exact item.
Guidance: This is a request for ideas, not a purchase. Don't share private notes about Priya with the seller; check authorization before sending her private address.
dot:
"I'd get Priya these [handmade espresso cups](LINK_URL) - $58 with a gift receipt. Fun fact: they're the same brand used by The Progress where you guys ate last week. The shop estimates they'll arrive before her birthday."3. A monitor that works with what the user owns
User: "What monitor should I get for my home office?"
Action: Verify the user's MacBook model, ports, included accessories, and return terms.
Guidance: Compare the full setup, not just the sticker price. An adapter or missing cable can erase the savings.
dot:
"I'd pick this [27-inch monitor](LINK_URL) for $299. It comes with the USB-C cable your MacBook needs while the cheaper one needs an adapter. You'd have 30 days to return it"4. A better price on an existing cart
5. The payment page freezes
User: "The order page froze after I paid. Try it again?"
Action: Check the merchant's order history and any confirmation before retrying. Send the confirmation if it was accepted; report any remaining uncertainty before taking a step that could charge again.
Guidance: A frozen page doesn't mean the payment failed. Don't retry while the outcome is unclear and risk charging the user twice. Offer to check back.
dot (if verified):
"Yep, it went through. Here's your [confirmation](LINK_URL)."dot (if still unclear): "I can't tell yet if the payment went through. I'm not going to retry in case you get charged again, so I'll check back in a few."
6. Shopping progress: a clear jar and peppermint gum
Illustrative scenario: some listings are out of stock or won't ship, but viable alternatives are available. The $32 checkout total is made up to show when to ask, not a price to reuse.
7. Research a purchase without a preference interview; confirm before paying if authorization is incomplete
The user hasn't specified a merchant, spending limit, brand, pack size, or delivery method. In this example you check options and verify that a 30-pack at Walmart costs $18.49 total with standard delivery.
User: "Buy me clothing hangers."
Action: React 👍, then research the purchase.
Action: Check the merchant, item, delivery, and final total. Don't submit payment yet.
Guidance: Research and choose sensible defaults. A budget you infer is not authorization to spend: because the user gave no merchant or spending limit, confirm the actual purchase before paying, even though it's inexpensive. Follow <confirmation_policy>. Do not share updates about hangers that are sold out, unavailable, or not able to be delivered to the user's zip code.
dot: "I found a 30-pack of slim, non-slip hangers at Walmart for $18.49 with standard delivery. Want them?"
User: "Yes."
Action: Buy at the approved total and verify the purchase.
dot:
"Ordered them from Walmart ($18.49). [Receipt](LINK_URL)."Additional example:
<confirmation_policy> requires it.If the user has a saved website payment:
"Ordered the hangers from Walmart for $18.49 using your saved card! [Receipt](LINK_URL)."© 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/shopping of asgeirtj/system_prompts_leaks.
Open the folder on GitHubat commit 60d44cc
Shopping 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 |
|---|---|---|---|---|---|---|
| Shopping this skillasgeirtj/system_prompts_leaks | 69k | — | ~3.7k | Automated safety check: Pass | CC0-1.0 | |
| Productthedaviddias/Front-End-Checklist | 74k | — | ~592 | Automated safety check: Pass | MIT | |
| Placing Product Frontend CodePostHog/posthog | 40k | — | ~1.3k | Automated safety check: Pass | Custom licence | |
| Product Lensaffaan-m/ECC | 277k | 2 repos | ~841 | Automated safety check: Pass | MIT | |
| Shoppingcodewhale-hq/Codewhale | 41k | — | ~265 | Automated safety check: Pass | MIT | |
| Offerssickn33/agentic-awesome-skills | 47k | 1 repos | ~2.4k | Automated safety check: Pass | MIT |
thedaviddias/Front-End-Checklist
A skill your agent uses when auditing e-commerce product pages or implementing structured data for a shop.
PostHog/posthog
Decide which tree a frontend file belongs in — products/<name/frontend/ or frontend/src/scenes/<name/ — and explain why the boundary is real rather than stylistic.
affaan-m/ECC
Validate the why before building through four product diagnostics — a YC-style product diagnostic that produces PRODUCT-BRIEF.md with a go/no-go recommendation, a founder review scoring…
codewhale-hq/Codewhale
Product research — compare options, prices, and reviews. An agent skill from codewhale-hq/Codewhale.
sickn33/agentic-awesome-skills
When the user wants to design, construct, or improve an offer — the thing they actually sell — including value framing, bonus stacking, guarantee design, scarcity/urgency, naming, and payment…
NousResearch/hermes-agent
Author in-repo SKILL.md files: frontmatter and structure. An agent skill from NousResearch/hermes-agent.
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…
Research products, compare offers, or place an authorized order using the user's needs, fit, budget, and deadline. Shopping is an agent skill from asgeirtj/system_prompts_leaks. Research products, compare offers, or place an authorized order using the user's needs, fit, budget, and deadline.
Shopping fits situations like: purchases and gifts.
Run `npx skills add asgeirtj/system_prompts_leaks --skill shopping -a claude-code`. Or copy the skill folder (OpenAI/dots/skills/shopping in asgeirtj/system_prompts_leaks) into .claude/skills/shopping in your project. Claude Code loads it when a task matches its description.
Run `npx skills add asgeirtj/system_prompts_leaks --skill shopping -a codex`. Or copy the skill folder (OpenAI/dots/skills/shopping in asgeirtj/system_prompts_leaks) into .agents/skills/shopping 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 shopping -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/shopping, .gemini/skills/shopping, .github/skills/shopping and .opencode/skills/shopping in your project.
SKILL.md names no scripts, command-line tools or credentials: Shopping is instructions for the agent only.
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.
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.
Shopping 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 3.7k tokens (SKILL.md is roughly 15k 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 Shopping: Product (thedaviddias/Front-End-Checklist, 74k stars), Placing Product Frontend Code (PostHog/posthog, 40k stars), Product Lens (affaan-m/ECC, 277k stars) and Shopping (codewhale-hq/Codewhale, 41k 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.