ai-workflowlisted

Set up LLM workflow discipline for projects that use AI / LLM calls in production or eval suites. Authors an eval-cost-watcher agent that projects token cost BEFORE regression evals run, plus an AI-workflow-discipline rule covering mock-mode placement, fixture freshness, and multi-stage cost accumulation. Optionally a small eval-regression skill stub. Invoke /dotclaude:ai-workflow only when the project actually has AI workflows.
vindm/dotclaude · ★ 1 · AI & Automation · score 68

Install: claude install-skill vindm/dotclaude

# `/dotclaude:ai-workflow` — LLM workflow + cost discipline kit You are setting up the AI-workflow safety layer — the discipline that prevents night-long eval runs from producing four-figure surprise bills, and that catches the mock-mode-bypass class of bug at the source rather than in the invoice. The eval-cost-watcher agent is the showpiece. It reads the diff, counts fixtures, projects cost ranges, and suggests cheaper alternatives — all BEFORE the eval runs. ## Phase 1 — Read the project's AI shape Before any question: 1. **Detect AI SDK presence** — does the project actually have LLM calls? ```bash grep -rln "@anthropic-ai/sdk\|openai\|@ai-sdk\|@google/generative-ai\|gemini\|claude" \ package.json Cargo.toml pyproject.toml requirements.txt 2>/dev/null | head grep -rn "from anthropic\|from openai\|import.*@anthropic" \ --include="*.py" --include="*.ts" --include="*.js" . 2>/dev/null | head -10 ``` If NO AI dependencies, STOP. Report applicability check failed. Tell the user this skill doesn't apply. 2. **AI workflow directories** — find where prompts / configs / fixtures live: ```bash find . -type d \( -name "ai" -o -name "llm" -o -name "prompts" -o -name "evals" \ -o -name "workflows" -o -name "agents" -o -name "fixtures" \) \ -not -path "*/node_modules/*" 2>/dev/null | head find . -path ./node_modules -prune -o \ \( -name "*.prompt.*" -o -name "*system-prompt*" -o -name "*instruction*" \) \ -print 2>/dev/null |