continuous-improvement-engine-scott-margetts
Capture, structure, and recycle lessons from active and closed legal matters. Three modes: in-flight capture (triggered by scope changes, risk events, status updates — highest value), mid-matter review (phase gates or quarterly), and matter close retrospective (full structured findings). Lessons are formatted for immediate reuse, not filed and forgotten. Use when a risk materialises, a scope change lands, a phase completes, or a matter closes and you want to convert what happened into something useful for the next matter. Trigger on: 'capture a lesson', 'what did we learn', 'matter close', 're
npx skills add lawve-ai/awesome-legal-skills --skill continuous-improvement-engine-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
You are a Legal Project Management skill that captures, structures, and recycles operational lessons from legal matters — in-flight, at phase gates, and at matter close. You convert what happened into something reusable on the next matter.
How it works
The skill operates in three modes:
- Mode 0 — Automated insight capture and skill update proposals: runs weekly across all active matters, scanning signals (emails, RAID updates, time entries, billing data, LC correspondence, status reports) to produce up to five triaged skill-update proposals ranked by confidence and actionability for human approval.
- Mode 1 — In-flight lesson capture: triggered by events (scope change, risk materialised, issue resolution, delivery problem, positive signal). Produces a Lesson Entry with required fields (Matter, Date captured, Trigger, Reference, WHAT HAPPENED, ROOT CAUSE, LESSON, REUSE TARGET, REUSE ACTION) and an identifier block before the entry. Includes specific guidance on how to categorize and feed back into other skills (e.g., risk-and-issues-manager, scope-change-controller).
- Mode 2 — Mid-matter review: triggered at phase completion or regular review points. Produces a structured, lighter review with a two-sentence summary, a list of lessons captured this phase, patterns identified, adjustments for next phase, and open items. Displays an identifier block before the review and uses available information to generate the output.
- Mode 3 — Matter close retrospective: (text truncated in the excerpt) intended to produce a full retrospective with structured findings for reuse on the next matter.
The skill explicitly instructs how to format outputs so they are immediately reusable and how to route lessons into other skills via a REUSE TARGET list. It emphasizes capturing lessons at the moment of vivid detail and applying a flag to route outputs appropriately if inputs come from different event types.
When to use it
- A risk has materialised, a scope change has landed, or a significant issue has been resolved — capture the lesson now, not at close.
- A phase has completed or a quarter has passed — mid-matter review.
- A matter is closing — full retrospective with structured findings.
- You want to turn a pattern from this matter into a reusable input for the next one.
What it can touch
The skill can receive outputs from other skills (risk-and-issues-manager, scope-change-controller, status-report-drafter, etc.) and extract a usable lesson entry or broader insights. It uses a structured REUSE TARGET to indicate where the lesson should feed back (e.g., matter-intake-scoping, risk-and-issues-manager, scope-change-controller, local-counsel-manager, matter-plan-builder, or Other).
# Continuous Improvement Engine You are a Legal Project Management skill that captures, structures, and recycles operational lessons from legal matters — in-flight, at phase gates, and at matter close. You convert what happened into something reusable on the next matter. The failure mode this skill exists to prevent: lessons learned that sit in a document no one reads. The standard retrospective produces a report, the report gets filed, the next matter makes the same mistakes. This skill is designed differently — lessons are captured at the moment they are most vivid, structured for immediate reuse, and fed back into the active skills (scoping assumptions, risk registers, instruction templates) rather than into a separate lessons-learned library. The highest-value mode is in-flight capture. A lesson extracted the week a scope change lands is ten times more useful than the same observation made six months later at matter close, when the detail has blurred and the team has moved on. ## When to use this skill - A risk has materialised, a scope change has landed, or a significant issue has been resolved — capture the lesson now, not at close - A phase has completed or a quarter has pas
- When to use this skill
- Boundary with Adjacent Skills
- Before Starting Any Mode
- Operating Modes
- Mode 0 — Automated insight capture and skill update proposals
- Mode 1 — In-flight lesson capture
- Mode 2 — Mid-matter review
- Mode 3 — Matter close retrospective
- Domain Knowledge — Why Lessons Don't Get Reused
- Output Format
- LPM vs Attorney Boundary
- Cross-Skill Handoffs
- M365 Connected Mode (Optional)
- Time-Sensitive Assumptions
What does the continuous-improvement-engine-scott-margetts skill do?
Capture, structure, and recycle lessons from active and closed legal matters. Three modes: in-flight capture (triggered by scope changes, risk events, status updates — highest value), mid-matter review (phase gates or quarterly), and matter close retrospective (full structured findings). Lessons are formatted for immediate reuse, not filed and forgotten. Use when a risk materialises, a scope change lands, a phase completes, or a matter closes and you want to convert what happened into something useful for the next matter. Trigger on: 'capture a lesson', 'what did we learn', 'matter close', 're
How do I install it?
Run `npx skills add lawve-ai/awesome-legal-skills --skill continuous-improvement-engine-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.