tech-debt
The facts
Its description
Identify, categorize, and prioritize technical debt. Trigger with "tech debt", "technical debt audit", "what should we refactor", "code health", or when the user asks about code quality, refactoring priorities, or maintenance backlog.
The description the agent reads to decide when to use it.
When it starts
The agent sees a description that fires on talk of technical debt, code health, refactoring priorities, or a maintenance backlog, so it picks this skill when someone asks what in a codebase is worth cleaning up or fixing next. It is a self-contained analysis-and-prioritization skill, not something another skill loads.
Things a person might say (the model's guesses)
- “Our codebase has gotten messy — what should we refactor first?”
- “Can you run a technical debt audit on this repo?”
- “We keep shipping regressions and everything feels slow to change. Where's our worst code health problem?”
A model's summary of when it is used.
Licence
Apache-2.0, from LICENSE
The terms its author shares it under, which let it be shown here.
The text
Tech Debt Management
Systematically identify, categorize, and prioritize technical debt.
Raw lines 1 to 9Categories
| Type | Examples | Risk |
|---|---|---|
| Code debt | Duplicated logic, poor abstractions, magic numbers | Bugs, slow development |
| Architecture debt | Monolith that should be split, wrong data store | Scaling limits |
| Test debt | Low coverage, flaky tests, missing integration tests | Regressions ship |
| Dependency debt | Outdated libraries, unmaintained dependencies | Security vulns |
| Documentation debt | Missing runbooks, outdated READMEs, tribal knowledge | Onboarding pain |
| Infrastructure debt | Manual deploys, no monitoring, no IaC | Incidents, slow recovery |
Prioritization Framework
Score each item on:
- Impact: How much does it slow the team down? (1-5)
- Risk: What happens if we don't fix it? (1-5)
- Effort: How hard is the fix? (1-5, inverted — lower effort = higher priority)
Priority = (Impact + Risk) x (6 - Effort)
Raw lines 21 to 29Output
Produce a prioritized list with estimated effort, business justification for each item, and a phased remediation plan that can be done alongside feature work.
Raw lines 30 to 32From anthropics/knowledge-work-plugins at 2574e29, 2026-10-27. Skills read by DeepSeek V4.1 Flash on 2026-11-04. Summary and techniques by Claude Opus 5.5 on 2026-11-06.