continuous-improvement
Skill0 starsChanged 3 months agoMITView on GitHub
ULTRA-ADVANCED Continuous Improvement - Continuous improvement workflow - metrics, experiments, kaizen culture, feedback loops
5 other projects use a version of this.
Adopted by
Most recently taken up by
- l-gevity/l-gevity-skillstheir own version, first seen Nov 14, 2026
- BurakD/ai-engineering-harnesstheir own version, first seen Nov 1, 2026
- naimkatiman/continuous-improvementtheir own version, first seen Oct 13, 2026
- kaka-ruto/skillstheir own version, first seen Apr 23, 2026
- muyen/vibe-to-prodtheir own version, first seen Jan 3, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- l-gevity/l-gevity-skills★ 88same name
- muyen/vibe-to-prod★ 34same name
- naimkatiman/continuous-improvement★ 9same name
- kaka-ruto/skills★ 4same name
- BurakD/ai-engineering-harness★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository220 other files it gives its agents.
- AGENTS.mdAGENTS.md
- desktop-control-mcpSkill
- force-deleteSkill
- analytics-guardSkill
- api-contract-guardSkill
- api-security-guardSkill
- async-guardSkill
- build-guardSkill
- changelog-guardSkill
- ci-guardSkill
- circuit-breaker-guardSkill
- clean-arch-guardSkill
- clean-code-guardSkill
- comment-guardSkill
- commit-guardSkill
- concurrency-guardSkill
- config-guardSkill
- cors-guardSkill
- cqrs-guardSkill
- csrf-guardSkill
- css-guardSkill
- cyclomatic-guardSkill
- ddd-guardSkill
- dead-code-guardSkill
- dependency-injection-guardSkill
- deploy-guardSkill
- docker-compose-guardSkill
- docker-guardSkill
- docs-guardSkill
- duplicate-code-guardSkill
- encryption-guardSkill
- env-check-guardSkill
- error-handling-guardSkill
- event-driven-guardSkill
- event-sourcing-guardSkill
- file-guardSkill
- graceful-shutdown-guardSkill
- health-check-guardSkill
- helm-guardSkill
- hexagonal-guardSkill
- html-guardSkill
- iam-guardSkill
- idor-guardSkill
- injection-guardSkill
- json-guardSkill
- jwt-guardSkill
- kubernetes-guardSkill
- large-class-guardSkill
- logging-pattern-guardSkill
- long-method-guardSkill
- lsp-guardSkill
- markdown-guardSkill
- message-queue-guardSkill
- migration-pattern-guardSkill
- naming-guardSkill
- nested-depth-guardSkill
- observer-pattern-guardSkill
- pr-guardSkill
- python-guardSkill
- react-guardSkill
- The first 60 shown.
The file
Files
Continuous Improvement - ULTRA-ADVANCED v1.0
Overview
Continuous improvement workflow - metrics, experiments, kaizen culture, feedback loops. This skill scans codebases for violations, scores compliance, and generates actionable recommendations.
Detection Patterns
| Pattern | Description | Severity |
| No baseline metrics | Improvement without measurement | high |
| No experiment design | Change without hypothesis | medium |
| No feedback loop | Results of change not reviewed | medium |
| Not trended | Point measurement without trend data | medium |
| No team involvement | Top-down improvement only | high |
Scoring
- A (90-100): Excellent
- B (75-89): Good
- C (60-74): Fair
- D (40-59): Poor
- F (0-39): Failing
Implementation
import re, os
from typing import Dict, List, Set, Any
from datetime import datetime
class ContinuousImprovement:
def __init__(self):
self.file_results = {}
def scan_file(self, file_path: str) -> Dict:
try:
with open(file_path, 'r', encoding='utf-8', errors='ignore') as f:
content = f.read()
return self._analyze(content, file_path)
except Exception as e:
return {'error': str(e), 'file': file_path}
def _analyze(self, content: str, file_path: str) -> Dict:
issues = []
for pid, info in self._patterns().items():
matches = re.findall(info['regex'], content, re.IGNORECASE | re.MULTILINE)
if matches:
issues.append({'id': pid, 'severity': info['severity'],
'count': len(matches), 'message': info['message']})
score = max(0.0, 100.0 - sum(self._weight(i['severity']) * i['count'] for i in issues))
return {'file': file_path, 'issues': issues, 'score': round(score, 1),
'grade': self._grade(score), 'analyzed_at': datetime.now().isoformat()}
def _patterns(self) -> Dict:
return {}
def _weight(self, s: str) -> float:
return {'critical': 10.0, 'high': 7.0, 'medium': 5.0, 'low': 2.0}.get(s, 5.0)
def _grade(self, s: float) -> str:
return 'A' if s >= 90 else 'B' if s >= 75 else 'C' if s >= 60 else 'D' if s >= 40 else 'F'
def scan_directory(self, d: str, exts: Set[str] = None) -> Dict:
results = {}
skip = {'.git', 'node_modules', 'venv', '__pycache__', 'target', 'build', 'dist'}
for root, dirs, files in os.walk(d):
dirs[:] = [dd for dd in dirs if not dd.startswith('.') and dd not in skip]
for f in files:
if exts and not any(f.endswith(e) for e in exts): continue
results[os.path.join(root, f)] = self.scan_file(os.path.join(root, f))
return results
def generate_report(self, results: Dict) -> Dict:
if not results: return {'error': 'No results'}
total_issues = sum(len(r.get('issues', [])) for r in results.values() if 'issues' in r)
scores = [r.get('score', 0) for r in results.values() if 'score' in r]
avg = sum(scores) / len(scores) if scores else 0
return {'files_scanned': len(results), 'total_issues': total_issues,
'avg_score': round(avg, 1), 'grade': self._grade(avg),
'critical': sum(1 for r in results.values() for i in r.get('issues', []) if i.get('severity') == 'critical'),
'recommendations': []}Version: 1.0.0 Status: PRODUCTION READY Total Patterns: 5
See Also
- terabox-improvement
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

