Tech Debt

anthropics/knowledge-work-pluginsOfficial

This breaks down technical debt into six categories (code, architecture, test, dependency, documentation, and infrastructure) and scores each item using a formula that weighs impact, risk, and effort. The output is a prioritized backlog with business justifications and a phased remediation plan you can work through alongside feature development. It's most useful when you know something's wrong but can't articulate why refactoring X matters more than refactoring Y, or when you need to make the case to leadership that yes, we really do need to upgrade that ancient library. The scoring framework is simple enough to be practical without turning debt management into its own full-time job.

skills.sh installs: 6.7K
GitHub stars: 35.3K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add anthropics/knowledge-work-plugins --skill tech-debt --agent claude-code

Installs into .claude/skills of the current project.

Files

Tech Debt Management

Systematically identify, categorize, and prioritize technical debt.

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.

SKILL.md on GitHub

Details

Repository: github.com/anthropics/knowledge-work-plugins
Category: Code Review & Quality
First seen: Apr 16, 2026

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Dependency debt	Outdated libraries, unmaintained dependencies	Security vulns
Documentation debt	Missing runbooks, outdated READMEs, tribal knowledge	Onboarding pain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