performance-scorecard
Performance scorecard design, post-matter feedback collection, QBR preparation, and firm comparison for in-house legal ops teams evaluating outside counsel. Design a scorecard framework calibrated to your team's maturity level. Produce post-matter feedback forms for supervising attorneys to complete at matter close. Prepare a QBR pack with agenda, data summary, and talking points for structured business reviews. Produce a side-by-side firm comparison for panel decision-making. Trigger on: 'design a performance scorecard', 'how do we evaluate our firms', 'build us a scorecard', 'post-matter fee
npx skills add lawve-ai/awesome-legal-skills --skill performance-scorecard-scott-margetts --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Describes a system to design a performance scorecard for outside counsel, collect post-matter feedback, prepare QBR materials, and produce firm comparisons to inform panel decisions. It defines a structured framework with quantitative and qualitative criteria, scoring methodology, and tiered consequences. It also provides an implementation note and templates for the scorecard framework and related outputs.
How it works
- Triggers mode based on user intent (e.g., design a performance scorecard, how do we evaluate our firms, build us a scorecard).
- Mode 1: Scorecard Design delivers two documents: the Performance Scorecard Framework and the GC Implementation Note. The framework includes Part 1 (Quantitative Criteria with data sources and scoring), Part 2 (Qualitative Criteria), Part 3 (Scoring Methodology), Part 4 (Performance Tier Definitions), and Part 5 (Consequence Framework). The GC Implementation Note covers purpose, data sources, implementation sequence, required resources, and a decision request.
- Provides calibration rules by maturity level (Early, Intermediate, Advanced) and details on which criteria to include at each level.
- Outputs are formatted with specific headers and structured tables, including data sources like e-billing, invoice-review, and matter records. Includes placeholder fields for company name, panel size, and other inputs.
- Part 4 defines performance tiers with score ranges and corresponding labels and descriptions. Part 5 lists consequences by tier.
- Includes a reference maturity section and an implementation sequence with dates placeholders.
When to use it
- Trigger phrases listed in the skill description (e.g., design a performance scorecard, build us a scorecard, what criteria should I use, QBR, compare the firms) indicate Mode 1 should run.
- Applicable when building or redesigning a scorecard framework, collecting post-matter feedback, and preparing for firm comparisons to inform panel decisions.
What it can touch
- Documents produced as .docx files (headers include [Company], dates, and panel details).
- Data sources referenced: e-billing platform, matter management, spreadsheet inputs, and invoice review records.
- Tools cited: not directly invoked in the output; references to data sources imply interaction with respective systems to populate inputs.
Caveats
- Explicitly notes not to perform invoice-review-compliance, panel design, panel reviews, or matter instruction design—these are excluded and should be sourced from other skills.
- Uses placeholders for missing data and company name substitution rules; ensure input data is provided to populate headers and fields.
- The output prescribes a governance flow (GC approval, firm communication, data collection) and assigns consequences, which must be actionable within the organization’s governance.
# performance-scorecard ## Description Performance scorecard design, post-matter feedback, QBR preparation, and firm comparison for in-house legal ops teams managing outside counsel relationships. Build a scorecard framework with quantitative and qualitative criteria calibrated to your team's maturity level. Produce post-matter feedback forms for supervising attorneys to complete at matter close. Prepare a QBR pack — agenda, period data summary, and firm-facing talking points — for structured business reviews. Produce a comparative firm scorecard for panel decision-making. Trigger on: 'design a performance scorecard', 'how do we evaluate our firms', 'build us a scorecard', 'post-matter feedback form', 'QBR', 'quarterly business review', 'prep for the firm review', 'compare the firms', 'rank our panel', 'evaluate outside counsel', 'annual firm review'. --- ## What This Skill Does Produces the operational tools for evaluating outside counsel performance — the scorecard framework, the feedback forms, the QBR preparation materials, and the comparative data structures that inform panel decisions. Encodes the methodology for collecting, aggregating, and acting on firm performance data ac
- Description
- What This Skill Does
- Pre-flight — Confirm and Fill
- Mode 1: Scorecard Design
- Input
- How to run this mode
- Performance Scorecard Framework template
- GC Implementation Note template
- Reference framework — maturity calibration
- Mode 2: Post-Matter Feedback
- Matter Feedback Form template
- Feedback Collection Note template
- Reference framework — feedback timing and design
- Mode 3: QBR Preparation
What does the performance-scorecard skill do?
Performance scorecard design, post-matter feedback collection, QBR preparation, and firm comparison for in-house legal ops teams evaluating outside counsel. Design a scorecard framework calibrated to your team's maturity level. Produce post-matter feedback forms for supervising attorneys to complete at matter close. Prepare a QBR pack with agenda, data summary, and talking points for structured business reviews. Produce a side-by-side firm comparison for panel decision-making. Trigger on: 'design a performance scorecard', 'how do we evaluate our firms', 'build us a scorecard', 'post-matter fee
How do I install it?
Run `npx skills add lawve-ai/awesome-legal-skills --skill performance-scorecard-scott-margetts --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From lawve-ai/awesome-legal-skills, a repository with 618 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.
