Update to Spend Management Analysis

{
  "description": "Analyze legal e-billing, outside-counsel spend, law-firm timekeeping, or matter-economics files to diagnose staffing mix, budget variance, allocation, and supported AI-leverage opportunities. Use for legal-spend reviews, QBR prep, spend spikes, matter pacing, realization, or practice-group economics. Do not use for general procurement spend or legal advice.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 292
    },
    {
      "relative_path": "references/analysis-method.md",
      "size_in_bytes": 5096
    },
    {
      "relative_path": "references/ledes-1998b.md",
      "size_in_bytes": 1545
    },
    {
      "relative_path": "references/report-and-export.md",
      "size_in_bytes": 3447
    },
    {
      "relative_path": "scripts/build_workbook.py",
      "size_in_bytes": 12353
    },
    {
      "relative_path": "scripts/parse_ledes.py",
      "size_in_bytes": 12458
    }
  ],
  "name": "spend-management-analysis",
  "skill_md_contents": "---\nname: spend-management-analysis\ndescription: Analyze legal e-billing, outside-counsel spend, law-firm timekeeping, or matter-economics files to diagnose staffing mix, budget variance, allocation, and supported AI-leverage opportunities. Use for legal-spend reviews, QBR prep, spend spikes, matter pacing, realization, or practice-group economics. Do not use for general procurement spend or legal advice.\n---\n\n# Spend Management Analysis\n\nTurn uploaded legal billing or staffing data into an evidence-backed explanation of what happened, why it likely happened, and what the user can do next. Do not merely restate totals or recreate an e-billing dashboard.\n\nResolve bundled paths relative to this `SKILL.md` file.\n\n## Start here\n\n1. Inspect only the files the user provided. Classify the data as:\n   - in-house/legal-ops data about outside-counsel spend; or\n   - law-firm internal data about practice economics, realization, or staffing.\n2. Check for LEDES before assuming CSV or Excel. If the first line starts with `LEDES1998B[]`, read [references/ledes-1998b.md](references/ledes-1998b.md) and use `scripts/parse_ledes.py` before analysis.\n3. Determine the audience. Infer it only when the request clearly identifies the setting, such as QBR preparation or an internal legal-operations review. Otherwise ask one concise question before producing the full report: is this for an internal review, a conversation with outside counsel, or an executive/board audience?\n4. Read [references/analysis-method.md](references/analysis-method.md), then normalize and analyze the data.\n5. Before delivering results, read [references/report-and-export.md](references/report-and-export.md) and create the required report, workbook, and findings CSV.\n\n## Core standards\n\n- Normalize platform-specific columns into a consistent working table, but preserve enough source detail to trace findings back to the input.\n- Base every material claim on the supplied data. State missing fields, thin samples, and analytical limits plainly; never fill gaps with invented values.\n- Compare like with like when possible: similar matter types, phases, firms, practice groups, or periods actually represented in the input.\n- Separate a likely staffing, rate, scope, or intake-process driver from the observed variance. Label inference as inference.\n- Recommend actions; do not make binding staffing, vendor, or firm decisions.\n- Treat attorney names, rates, client matters, and invoice details as sensitive. Repeat only the identifying detail needed to support a finding.\n\n## Required outcome\n\nDeliver:\n\n1. An audience-tailored written report with an executive summary, ranked actions, staffing-mix findings, budget-variance findings, allocation findings, and supported AI-leverage opportunities.\n2. A polished `.xlsx` workbook generated with `scripts/build_workbook.py`.\n3. A flat findings `.csv` generated by the same script.\n\nIf a report section has no supported finding, say so briefly. Include AI-leverage opportunities only when task codes, activity codes, or line descriptions identify actual work categories. A matter name, practice area, role mix, or rate alone is not enough evidence for an AI-leverage finding. In the workbook payload, record whether AI leverage was `assessed` or `not_assessed` and include a short assessment note; do not treat an empty opportunity list as proof that an assessment occurred.\n\n## Boundaries\n\n- Do not access outside billing or timekeeping systems unless the user separately authorizes and provides an available integration.\n- Do not assess fee reasonableness under ethics rules or give legal advice.\n- Do not claim a trend without the relevant comparison period.\n- Do not invent dollar or hour savings from AI. Keep AI opportunity estimates qualitative and require attorney review plus applicable confidentiality, privilege, and AI-use controls.\n\n## Runtime fallback\n\nThe workbook helper requires Python 3 and `openpyxl`. If code execution or that dependency is unavailable and cannot be enabled within the current environment, still deliver the written analysis and a findings table, clearly disclose that the workbook could not be generated, and give the user the bundled command they can run locally.\n"
}