auditing-a-pigment-application
Execution skill. Use when auditing, reviewing, or health-checking a Pigment application. Covers the structured audit checklist, severity classification, and output format. Also triggers on requests to clean up, find unused blocks, assess model quality, or find what is wrong with an application.
Install
With your agent
Install OMGSkills skill "gopigment/ai-plugins:skills/auditing-a-pigment-application" into this agent's normal skills directory: call the OMGSkills MCP get_install_plan tool for your agent and run the script it returns (it installs only the pinned commit and verifies SKILL.md), and stop if MCP or the pin is unavailable. Do not overwrite or change existing skills without asking me.
Manual command
git clone https://github.com/gopigment/ai-plugins /tmp/ai-plugins && ln -s /tmp/ai-plugins/skills/auditing-a-pigment-application ~/.claude/skills/auditing-a-pigment-applicationFrom README
Auditing a Pigment Application Run a structured, read-only audit. Do not modify anything unless the user explicitly asks for fixes after reviewing the report. CRITICAL -- Collect Formula Health Evidence First Start every audit with tool:listissues to surface active formula computation errors. These are highest-severity because they produce wrong or missing outputs. For each errored block, retrieve its formula with tool:searchmetricsandlists (showdetails: true) and identify the root cause (type mismatch, missing reference, scenario-specific failure). Use tool:getmetricdependencies on errored blocks to trace downstream impact and distinguish root causes from cascading symptoms. CRITICAL -- Trace Dependency Fragility Use tool:getmetricdependencies on critical output metrics (cashflow totals, P&L summaries, KPIs). Flag: Long chains where a single upstream error cascades to many outputs Missing intermediate metrics (too much logic in one formula) Fragile roll-forward patterns (e.g.