Tw Ecom Invoice Ezpay
asgard-ai-platform/skills
Issue and manage Taiwan e-invoices via ezPay (加值服務中心) through mcp-ezpay-einvoice.
Read and manage the user's QuickBooks business through Intuit's official MCP server, including reports, invoices, customers, products, payment links, sales settings, and industry benchmarks.
$ npx skills add asgeirtj/system_prompts_leaks --skill quickbooks -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install asgeirtj/system_prompts_leaks quickbooks --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/Meta/muse-agent/skills/quickbooks .claude/skills/quickbooks && 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 "quickbooks" agent skill from https://github.com/asgeirtj/system_prompts_leaks/tree/main/Meta/muse-agent/skills/quickbooks into .claude/skills/quickbooks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "quickbooks", 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/Meta/muse-agent/skills/quickbooksType 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 quickbooks -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install asgeirtj/system_prompts_leaks quickbooks --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/Meta/muse-agent/skills/quickbooks .agents/skills/quickbooks && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "quickbooks" agent skill from https://github.com/asgeirtj/system_prompts_leaks/tree/main/Meta/muse-agent/skills/quickbooks into .agents/skills/quickbooks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "quickbooks", 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 quickbooks -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install asgeirtj/system_prompts_leaks quickbooks --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/Meta/muse-agent/skills/quickbooks .cursor/skills/quickbooks && 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 "quickbooks" agent skill from https://github.com/asgeirtj/system_prompts_leaks/tree/main/Meta/muse-agent/skills/quickbooks into .cursor/skills/quickbooks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "quickbooks", 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 Meta/muse-agent/skills/quickbooks--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 quickbooks -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install asgeirtj/system_prompts_leaks quickbooks --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/Meta/muse-agent/skills/quickbooks .gemini/skills/quickbooks && 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 "quickbooks" agent skill from https://github.com/asgeirtj/system_prompts_leaks/tree/main/Meta/muse-agent/skills/quickbooks into .gemini/skills/quickbooks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "quickbooks", 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 quickbooksInstalls 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 quickbooks -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/Meta/muse-agent/skills/quickbooks .github/skills/quickbooks && 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 "quickbooks" agent skill from https://github.com/asgeirtj/system_prompts_leaks/tree/main/Meta/muse-agent/skills/quickbooks into .github/skills/quickbooks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "quickbooks", 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 quickbooks -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 quickbooks --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/Meta/muse-agent/skills/quickbooks .opencode/skills/quickbooks && 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 "quickbooks" agent skill from https://github.com/asgeirtj/system_prompts_leaks/tree/main/Meta/muse-agent/skills/quickbooks into .opencode/skills/quickbooks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "quickbooks", 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.
quickbooksRead and manage the user's QuickBooks business through Intuit's official MCP server, including reports, invoices, customers, products, payment links, sales settings, and industry benchmarks.
Quickbooks is an agent skill from asgeirtj/system_prompts_leaks. Read and manage the user's QuickBooks business through Intuit's official MCP server, including reports, invoices, customers, products, payment links, sales settings, and industry benchmarks.
Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `connector_auth_config.yaml` and `manifest.yaml`).
It sits in Documents & Office, covering Forms and invoices. It works with QuickBooks and Model Context Protocol. 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.
8 steps, taken from the first numbered list 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.
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.
Quickbooks loads about 1.9k tokens when it runs. Until then it costs about 50 tokens; SKILL.md has 1,104 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). 1,104 words, ~1,929 tokens.
.claude/skills/quickbooks/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.Use QuickBooks data to answer business questions and complete supported actions.
Run quickbooks status first. If disconnected, run quickbooks authorize-url
and share only the returned connect_url. After the user connects, run status
again. Run quickbooks disconnect only when the user explicitly asks.
Every QuickBooks tool in this catalogue requires a connected company; use
quickbooks call-tool for all of them. Each tool also needs the 3LO scopes of
its permission tier. Hatch approval still applies to every write.
Connecting grants read access only. Before a write or deletion, or after one
fails for missing access, run quickbooks status --for-command <tool-name>,
for example quickbooks status --for-command qbo_sales_create_invoice. Every
account write and deletion shares one write-access tier, so the first request
covers all of them, including sending and deleting, and not only the requested
action; say so. When it returns scope_status: not_granted, copy
scope_add_url exactly and post it on its own line as
[Additional QuickBooks access](<scope_add_url>), then wait for the user to
finish before retrying. Unlike a record link, this link gets its own line.
granted means the recorded scopes cover the command; Intuit can still reject
the token or the company's access. unavailable means the grant is unknown.
For a read that fails for missing access, use the same status command to
request the read tier. Never construct OAuth URLs or ask for tokens in chat.
Use quickbooks list-tools only to discover which tools exist. Immediately
before every provider call, run quickbooks list-tools --name <exact-tool-name>
and read that tool's current input_schema; never guess a field name, nesting
shape, type, or enum value from another tool. Exact lookup uses the connected
user's token, like the call. The CLI rechecks that schema immediately
before dispatch and rejects mismatches rather than letting Intuit silently
ignore them. Call only a reviewed tool and pass an object to--arguments-json:
quickbooks call-tool --name company_info --arguments-json '{}'
quickbooks call-tool --name profit_loss_quickbooks_account_text --arguments-json '<JSON object>'
quickbooks call-tool --name qbo_sales_get_invoices --arguments-json '<JSON object>'For a broad business-health question, ask for the period, accounting method,
and desired scope in one message. Call company_info, then only the relevant
text report tools. Prefer each report's built-in comparison instead of making
duplicate calls for another period. Combine the results into one answer.
For reports, verify the period in every result; if it differs from the user's
request, do not present the figures as the requested report.
For industry research or figures supplied by the user, use the industry
benchmark tool. For the connected company's own performance, use
benchmarking_quickbooks_account_text. State when peer data or company data is
missing.
For receivables or payables, start with the corresponding A/R or A/P aging
summary. Fetch detail only when the user asks for a customer, vendor, aging
bucket, or reminder. Prefer _text report variants for broad synthesis; use
the reviewed widget/non-text variant when the user directly requests that
report or its richer presentation. Link an invoice using its
reference_number as the label and its returned link as the target. Use its
full id only in tool calls.
Before creating an invoice or estimate, resolve the customer and products.
Ask before creating any missing customer or product. Treat each line's
amount as its unit price, not its extended total. Create the document once,
compare the returned total with the proposal, and show the created document
before any send.
QuickBooks invoices have no draft state. Once a create succeeds, the invoice is live in the user's company, even before it is sent. Never call it a draft, say it is in draft, or offer to finalize it, even where a tool description mentions draft invoices. If it has not been sent, say it is created but not yet sent.
Hatch keeps editing, sending, recurring billing, and deletion under separate permissions. Approval cards show the specific operation and request details.
Apply the same preview, confirmation, and read-back pattern to invoice or estimate updates and deletions, recurring invoices, payment links, sales settings, transaction imports, and company-profile changes. For duplicate operations, show the source record and intended copy before acting. Never blindly retry these operations after an uncertain result.
quickbooks list-tools --name <exact-tool-name>, fix the arguments, and
retry the same operation at most once. Never switch tools on retry: do not
use a get, update, create, invoice, or other operation to repair a failed
send. Never create a second record to repair the first. Local schema
validation and privsep failures happen before the provider call; do not say
QuickBooks or Intuit rejected the request unless the error explicitly came
from MCP HTTP, RPC, or provider output.[label](url). Copy the URL verbatim into the target:
never shorten it, strip query parameters, rebuild one from an id, or offer
a link the tool did not return. Label it with what it opens, using the
record's own customer-facing name from the tool output, such as
[Invoice 1042](url); never use the URL, a bare domain, or a path as the
label. Keep the link inside the line that describes its record — the
list row or sentence naming that invoice — so it reads inline with the
detail it belongs to. A link alone on its own line is presented as a
separate card instead, which separates it from that detail, so do not
give a record link a line of its own.Use only tools returned by quickbooks list-tools and allowed by the local
reviewed catalogue. Do not request arbitrary URLs, scopes, or unlisted tools.
Do not give legal, tax, compliance, collections, or regulated financial advice.
© 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
SKILL.md and 2 other files in Meta/muse-agent/skills/quickbooks of asgeirtj/system_prompts_leaks.
Open the folder on GitHubat commit 60d44cc
Quickbooks 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 |
|---|---|---|---|---|---|---|
| Quickbooks this skillasgeirtj/system_prompts_leaks | 69k | — | ~1.9k | Automated safety check: Pass | CC0-1.0 | |
| Tw Ecom Invoice Ezpayasgard-ai-platform/skills | 242 | — | ~3.5k | Automated safety check: Pass | MIT | |
| Statement Extract And ProveOneWave-AI/claude-skills | 336 | — | ~2.2k | Automated safety check: Pass | MIT | |
| Purchase Order ProcessingGAIK-project/gaik-toolkit | 100 | — | ~3.9k | Automated safety check: Pass | MIT | |
| Sealeap Bifang Amazon Small Niche Market Screeningxjli360/sealeap-amazon-skills | 251 | — | ~806 | Automated safety check: Pass | MIT | |
| Invoice Verifyinfometa/workbuddyskills | 348 | — | ~3.8k | Automated safety check: Notes | None |
asgard-ai-platform/skills
Issue and manage Taiwan e-invoices via ezPay (加值服務中心) through mcp-ezpay-einvoice.
OneWave-AI/claude-skills
Converts bank, credit card and brokerage statement PDFs, invoices and vendor price lists into clean CSV or Excel, then proves the extraction is complete and correct - opening balance plus…
GAIK-project/gaik-toolkit
Process Purchase Orders and Bills of Material to generate priced Sales Orders
xjli360/sealeap-amazon-skills
Screen Amazon sub-markets for a capital-constrained seller by capping demand, checking top-listing concentration against the market average, filtering out seasonal curves, reading new-product share…
infometa/workbuddyskills
智能发票专家团的发票识别、税局验真、商业信用核查和智能票夹归档能力。当用户上传发票文件(图片/PDF/OFD/XML)、 批量上传表格、指定本地文件夹或提供发票四要素信息时, 自动识别发票内容、查验真伪、核查开票方商业信用,并输出归档报告。
infometa/workbuddyskills
支持 PDF / PNG / JPG 上传识别发票要素,核验发票真伪与票面信息,并输出销方企业画像(登记地/行业/纳税人身份/开票特征);内置票种映射、金额口径换算、查验配额与超时重试策略
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
Categories
Read and manage the user's QuickBooks business through Intuit's official MCP server, including reports, invoices, customers, products, payment links, sales settings, and industry benchmarks. Quickbooks is an agent skill from asgeirtj/system_prompts_leaks. Read and manage the user's QuickBooks business through Intuit's official MCP server, including reports, invoices, customers, products, payment links, sales settings, and industry benchmarks.
Quickbooks fits situations like: tasks that involve Forms and invoices.
Run `npx skills add asgeirtj/system_prompts_leaks --skill quickbooks -a claude-code`. Or copy the skill folder (Meta/muse-agent/skills/quickbooks in asgeirtj/system_prompts_leaks) into .claude/skills/quickbooks in your project. Claude Code loads it when a task matches its description.
Run `npx skills add asgeirtj/system_prompts_leaks --skill quickbooks -a codex`. Or copy the skill folder (Meta/muse-agent/skills/quickbooks in asgeirtj/system_prompts_leaks) into .agents/skills/quickbooks 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 quickbooks -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/quickbooks, .gemini/skills/quickbooks, .github/skills/quickbooks and .opencode/skills/quickbooks in your project.
SKILL.md names no scripts, command-line tools or credentials: Quickbooks 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.
Quickbooks 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 Quickbooks: Tw Ecom Invoice Ezpay (asgard-ai-platform/skills, 242 stars), Statement Extract And Prove (OneWave-AI/claude-skills, 336 stars), Purchase Order Processing (GAIK-project/gaik-toolkit, 100 stars) and Sealeap Bifang Amazon Small Niche Market Screening (xjli360/sealeap-amazon-skills, 251 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.