tech-debt
anthropics/knowledge-work-plugins
Identify, categorize, and prioritize technical debt with a structured scoring framework.
What is tech-debt?
Systematically identify and rank technical debt across code, architecture, testing, dependencies, documentation, and infrastructure. Use this when assessing code quality, planning refactoring work, or evaluating maintenance backlog priorities.
- Categorizes debt into six types: code, architecture, test, dependency, documentation, and infrastructure
- Scores each item on impact, risk, and effort using a quantitative framework
- Calculates priority using the formula (Impact + Risk) × (6 - Effort)
- Produces prioritized lists with estimated effort and business justification
- Generates phased remediation plans that fit alongside feature work
How to install tech-debt
npx skills add https://github.com/anthropics/knowledge-work-plugins --skill tech-debtHow to use tech-debt
- 1.Describe your codebase, recent changes, or specific pain points
- 2.Let the skill identify debt across the six categories
- 3.Review the prioritization scores and business justifications
- 4.Adopt the phased remediation plan to integrate fixes into regular work
Use cases
- Audit a codebase to identify the highest-impact refactoring opportunities
- Plan a quarterly maintenance roadmap by scoring existing technical debt
- Justify engineering time allocation to stakeholders with risk and impact metrics
- Prioritize dependency upgrades when facing security or compatibility issues
- Create a phased remediation strategy that doesn't block feature delivery
- Engineering leads planning sprint capacity
- Teams conducting code health reviews
- Architects evaluating system-wide refactoring needs
- Tech leads justifying maintenance work to product managers
tech-debt FAQ
Score each debt item 1-5 for Impact (team slowdown), Risk (consequence if unfixed), and Effort (1-5, where lower effort scores higher). Then calculate: (Impact + Risk) × (6 - Effort). Higher scores indicate higher priority.
Yes. The skill produces phased remediation plans designed to be done alongside feature work, so you can integrate small fixes into regular sprints rather than requiring dedicated refactoring cycles.
The framework is a guide, not law. Adjust Impact and Risk scores based on your team's context—security debt may warrant higher risk scores, while documentation debt depends on team size and turnover.
Conduct a full audit quarterly or when planning major releases. Track ongoing debt continuously as part of code review and sprint planning.
Full instructions (SKILL.md)
Source of truth, from anthropics/knowledge-work-plugins.
name: tech-debt 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.
Tech Debt Management
Systematically identify, categorize, and prioritize technical debt.
Categories
| 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)
Output
Produce a prioritized list with estimated effort, business justification for each item, and a phased remediation plan that can be done alongside feature work.
Related skills
More from anthropics/knowledge-work-plugins and the wider catalog.
data-visualization
Pick the right chart and generate publication-quality Python visualizations with built-in design and accessibility best practices.
code-review
Review code changes for security, performance, and correctness issues before merging.
documentation
Write and maintain technical documentation for APIs, READMEs, runbooks, and architecture guides.
build-dashboard
Build self-contained interactive HTML dashboards with charts, filters, and tables that open directly in a browser.
task-management
Track tasks in a shared TASKS.md file with optional visual dashboard.
memory-management
Two-tier memory system that decodes workplace shorthand so Claude understands requests like a colleague would.