continuous-improvement-engine
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', 'retrospective', 'lessons learned', 'what went wrong', 'what worked', 'phase gate review', 'debrief', 'extract the learning', 'close the matter', 'what should we do differently', 'pattern from this matter', 'improve the next one'.
82
77%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/continuous-improvement-engine/SKILL.mdQuality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that clearly defines a specific legal domain capability with three distinct operational modes. It provides comprehensive trigger terms that cover natural user language, explicitly states both what the skill does and when to use it, and occupies a clear niche that minimizes conflict with other skills. The description is detailed without being padded, and uses appropriate third-person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and modes: in-flight capture (with specific triggers like scope changes, risk events), mid-matter review (phase gates or quarterly), and matter close retrospective (full structured findings). Also specifies output format intent ('formatted for immediate reuse'). | 3 / 3 |
Completeness | Clearly answers both 'what' (capture, structure, and recycle lessons from legal matters across three modes) and 'when' (explicit 'Use when' clause covering risk materialisation, scope changes, phase completion, matter close, plus a comprehensive 'Trigger on' list). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say, including 'capture a lesson', 'what did we learn', 'matter close', 'retrospective', 'lessons learned', 'what went wrong', 'what worked', 'phase gate review', 'debrief', 'what should we do differently', and more. These are natural phrases a legal professional would use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche: legal matter lessons learned with specific legal domain terminology (matter close, phase gates, scope changes, risk events). Unlikely to conflict with general retrospective or project management skills due to the explicit legal matter framing and specialized trigger terms. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
55%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill demonstrates excellent actionability with concrete, structured templates and clear workflow sequences across all four operating modes. However, it is severely undermined by extreme verbosity — repeating key concepts multiple times, explaining rationale Claude doesn't need, and inlining content that should be in separate reference files. The monolithic structure with no progressive disclosure means the entire ~400-line document must be loaded into context even when only one mode is needed.
Suggestions
Cut the 'Domain Knowledge — Why Lessons Don't Get Reused' section entirely — this is background rationale that Claude doesn't need to execute the skill, and the key insight (capture early) is already stated multiple times elsewhere.
Move the M365 Connected Mode section to a separate CONNECTED-MODE.md reference file and link to it with a one-line summary in the main skill.
Move the detailed signal detection table and Mode 0 classification schema to a separate SIGNAL-DETECTION.md reference file, keeping only a brief summary in the main skill.
Eliminate repeated statements about in-flight capture being highest value — state it once in the introduction and remove the 3-4 other instances throughout the document.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~400+ lines. It extensively explains why lessons don't get reused (domain knowledge Claude doesn't need), repeats the same concepts multiple times (in-flight capture superiority is stated at least 4 times), and includes lengthy rationale sections that explain the philosophy rather than instruct. The M365 Connected Mode section alone is massive and largely describes capabilities rather than providing actionable steps. | 1 / 3 |
Actionability | The skill provides highly concrete, structured templates for every mode (Mode 0-3) with specific field schemas, classification tables, triage rules, and exact output formats. The signal detection table, lesson entry structure, and skill update proposal schema are all copy-paste ready and immediately usable. | 3 / 3 |
Workflow Clarity | Each mode has a clear sequence with explicit validation checkpoints — the identifier hard gate, the approval gate for Mode 0 proposals ('non-negotiable'), pattern detection prompts after every third lesson entry, and the triage rules before producing digests. The cross-skill handoff section clearly maps inputs and outputs between skills with explicit routing instructions. | 3 / 3 |
Progressive Disclosure | This is a monolithic wall of text with no references to external files. The M365 Connected Mode section, the Domain Knowledge section, the signal detection tables, and the cross-skill handoffs could all be split into separate reference files. Everything is inline in a single massive document, making it difficult to navigate and consuming excessive context window. | 1 / 3 |
Total | 8 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- legalopsconsulting/lpm-skills
- Commit
8f9093f
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.