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
—
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 niche (legal matter lessons learned), provides three concrete operational modes, and includes both a 'Use when' clause and an extensive 'Trigger on' list with natural user phrases. The description is comprehensive without being padded, uses third-person voice throughout, and would be highly distinguishable from other skills in a large skill library.
| 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 goal ('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 with specific scenarios plus a comprehensive 'Trigger on' list). Both dimensions are thoroughly addressed. | 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 highly natural phrases a legal professional would use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche: legal matter lessons learned with specific legal terminology (matter close, phase gate, scope changes, risk events). The combination of legal domain + retrospective/lessons-learned focus makes it very unlikely to conflict with other skills. | 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 excels at actionability and workflow clarity — its structured templates, classification schemas, and mode-specific workflows are highly concrete and immediately usable. However, it is severely undermined by verbosity (repeating the in-flight capture philosophy multiple times, explaining why lessons fail, extensive M365 descriptions) and a monolithic structure that dumps everything into a single file. Cutting this to ~40% of its current length and splitting reference material into linked files would dramatically improve its effectiveness.
Suggestions
Extract the Domain Knowledge section, M365 Connected Mode details, and Cross-Skill Handoffs into separate reference files (e.g., DOMAIN.md, M365.md, HANDOFFS.md) linked from the main skill with one-line descriptions.
Remove the 'Domain Knowledge — Why Lessons Don't Get Reused' section entirely or reduce to 2-3 bullet points — Claude doesn't need a persuasive essay on why the skill exists.
Consolidate repeated statements about in-flight capture being highest value — this point is made at least 4 times across the introduction, Mode 1, Domain Knowledge, and Time-Sensitive Assumptions sections.
Trim the Boundary with Adjacent Skills section to a concise table rather than multiple paragraphs of prose explaining what the skill does and doesn't do.
| 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, copy-paste-ready templates for every mode (lesson entries, mid-matter reviews, close retrospectives, weekly digests, skill update proposals). Signal detection tables, classification schemas, and triage rules are specific and executable. The structured output formats with field-level guidance are immediately usable. | 3 / 3 |
Workflow Clarity | Multi-step processes are clearly sequenced with explicit validation checkpoints. Mode 0 has triage rules, confidence rankings, and a non-negotiable approval gate. Mode 1 includes pattern detection prompts after every third entry. Mode 3 specifies producing the Reuse Package first if time is limited. The trigger classification flowchart clearly routes inputs to the correct mode, with a sensible default (Mode 1) for ambiguous cases. | 3 / 3 |
Progressive Disclosure | The entire skill is a monolithic wall of text with no references to external files. The M365 Connected Mode section, domain knowledge section, cross-skill handoffs, and detailed mode specifications could all be split into separate reference files. Everything is inline, making the skill extremely long and difficult to navigate quickly. | 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
1eb58a1
- 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.