Use this skill whenever the user asks about payroll & employer taxes across jurisdictions. Trigger phrases include "payroll", "withholding", "PAYE", "FICA", "social security", "employer". The skill is a thin router — it directs you to call the OpenAccountants MCP server (already configured at https://www.openaccountants.com/api/mcp) which holds 14 verified skill(s) for this scope.
How this skill is triggered — by the user, by Claude, or both
Slash command
/openaccountants-payroll:openaccountants-payrollThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
This Claude plugin gives you direct access to **14 verified
This Claude plugin gives you direct access to 14 verified tax/accounting skill(s) from OpenAccountants for payroll & employer taxes across jurisdictions.
When the user asks anything in scope, follow this workflow:
start({ intent, jurisdiction }) on the
openaccountants MCP server. It returns a ready plan with the
exact skills to load.skills_to_load, call
get_skill({ slug }) — that returns the authoritative markdown
(rates, brackets, deductions, audit flash points, citations).request_accountant_review({ jurisdiction, scenario, working_paper })
to route them to the named lead verifier for that jurisdiction
with a Calendly link.australia-payrollbelgium-payrollcanada-payrollfrance-payrollgermany-payrollindia-payrollitaly-payrolljapan-payrollmalta-payrollnetherlands-payrollportugal-payrollspain-payrollsweden-payrolluk-payrollOutputs are working papers, not filed returns. No client–accountant relationship until both sides sign an engagement letter. See openaccountants.com for the verifier network.
npx claudepluginhub openaccountants/marketplace --plugin openaccountants-payrollGuides completion of development work by verifying tests, detecting environment, and presenting structured options for merge, PR, or cleanup.
Guides creation and editing of skills using test-driven development with pressure scenarios and subagents to verify agent compliance.
Dispatches multiple subagents concurrently for independent tasks without shared state. Use when facing 2+ unrelated failures or subsystems that can be investigated in parallel.