Mmcp.market

doncheli-tech-debt skill

by doncheli·doncheli/don-cheli-sdd·57 stars·Apache-2.0

Identify, quantify, and prioritize technical debt in the codebase. Activate when user mentions "tech debt", "code quality", "technical debt", "code smells", "refactor candidates", "what to clean up".

A100/100content scan

Is the doncheli-tech-debt skill safe?

Clean: nothing in its files matched our rules. We read 1 file in the folder on 2026-09-28.

No findings.

Install the doncheli-tech-debt skill

A skill is a folder. Copy it into your agent's skills folder and the agent loads it when the task matches its description.

git clone --depth 1 https://github.com/doncheli/don-cheli-sdd.git /tmp/don-cheli-sdd
mkdir -p ~/.claude/skills
cp -r /tmp/don-cheli-sdd/.opencode/skills/doncheli-tech-debt ~/.claude/skills/doncheli-tech-debt
available in every project

In the Claude apps, zip the folder and upload it from the Skills settings. The folder on GitHub

The instructions your agent would load

SKILL.md as published, without the frontmatter. Read it on GitHub

Don Cheli: Tech Debt Scanner

Instructions

  1. Scan the codebase for tech debt signals:
  • TODO/FIXME/HACK/XXX comments with file and line
  • Functions exceeding cyclomatic complexity of 10
  • Files exceeding 300 lines (configurable)
  • Duplicated code blocks (> 10 lines repeated 3+ times)
  • Deprecated dependencies or APIs in use
  • Missing error handling (uncaught exceptions, empty catch blocks)
  • Test files that exist but have 0 assertions
  1. Score each item by impact (high/medium/low) and effort (hours estimate)
  2. Compute a Tech Debt Ratio: debt items / total files
  3. Prioritize using the impact/effort matrix: Quick Wins first, then High Impact
  4. Recommend a remediation plan with a suggested order
  5. Never auto-refactor — produce the plan and wait for approval
  6. Save the report to .dc/tech-debt-.md

Output Format

## Tech Debt Report — 2026-03-28

### Summary
- Total debt items: 18
- Tech Debt Ratio: 18/94 files = 19% (target: <10%)
- Estimated remediation effort: ~14h

### Quick Wins (high impact, low effort)
1. src/utils/format.ts — 3 duplicate date-format blocks — 1h — extract to shared util
2. src/auth/token.ts:88 — empty catch block silently swallows JWT errors — 30m fix

### High Impact (high impact, higher effort)
1. src/payments/processor.ts — cyclomatic complexity 18 — 4h refactor

### Low Priority
1. 7 TODO comments in src/legacy/ — document or schedule removal

### Remediation Plan
Sprint 1 (8h): Quick wins + empty catch blocks
Sprint 2 (6h): payments/processor.ts refactor
Backlog: legacy TODOs

More skills from doncheli/don-cheli-sdd

  • Adoncheli-api-contractDesign complete API contracts covering endpoints, auth, rate limiting, error handling, retries, circuit breaker and idempotency. Activate when user mentions "api contract", "api design", "endpoint", "webhook", "REST", "GraphQL", "OpenAPI", "design the API".
  • Adoncheli-api-contractDesign complete API contracts covering endpoints, auth, rate limiting, error handling, retries, circuit breaker and idempotency. Activate when user mentions "api contract", "api design", "endpoint", "webhook", "REST", "GraphQL", "OpenAPI", "design the API".
  • Adoncheli-audit-trailRecord and query the decision log for a project. Activate when user mentions "audit", "trail", "log decisions", "decision history", "why was this decided", "ADR", "architecture decision".
  • Adoncheli-audit-trailRecord and query the decision log for a project. Activate when user mentions "audit", "trail", "log decisions", "decision history", "why was this decided", "ADR", "architecture decision".
  • Adoncheli-changelogAuto-generate CHANGELOG.md entries from git commit history. Activate when user mentions "changelog", "release notes", "what changed", "generate changelog", "CHANGELOG", "release history".
  • Adoncheli-changelogAuto-generate CHANGELOG.md entries from git commit history. Activate when user mentions "changelog", "release notes", "what changed", "generate changelog", "CHANGELOG", "release history".
  • Adoncheli-context-healthReport the current state of the context window and recommend compression or cleanup actions. Activate when user mentions "context health", "context window", "how much context", "context full", "running out of context", "compress context".
  • Adoncheli-context-healthReport the current state of the context window and recommend compression or cleanup actions. Activate when user mentions "context health", "context window", "how much context", "context full", "running out of context", "compress context".
  • Adoncheli-data-policyAudit and document what personal or sensitive data the project collects, processes, and stores. Activate when user mentions "privacy", "data policy", "what data", "GDPR", "personal data", "data retention", "PII".
  • Adoncheli-data-policyAudit and document what personal or sensitive data the project collects, processes, and stores. Activate when user mentions "privacy", "data policy", "what data", "GDPR", "personal data", "data retention", "PII".
  • Adoncheli-debateRun an adversarial multi-role debate to surface trade-offs and reach a reasoned decision. Activate when user mentions "debate", "discuss", "trade-off", "decision", "compare options", "pros and cons", "choose between".
  • Adoncheli-debateRun an adversarial multi-role debate to surface trade-offs and reach a reasoned decision. Activate when user mentions "debate", "discuss", "trade-off", "decision", "compare options", "pros and cons", "choose between".

All agent skills → · MCP servers