Tech Debt
Run a structured technical-debt audit and get a scored, phased refactor backlog you can mix with feature work.
Overview
Tech Debt is an agent skill most often used in Operate (also Ship and Build) that identifies, categorizes, and prioritizes technical debt with a scored backlog and phased remediation plan.
Install
npx skills add https://github.com/anthropics/knowledge-work-plugins --skill tech-debtWhat is this skill?
- Six debt categories with risk framing: code, architecture, test, dependency, documentation, infrastructure
- Priority formula: (Impact + Risk) × (6 − Effort) for comparable ranking
- Produces prioritized list with effort estimates, business justification, and phased remediation plan
- Triggered by tech debt audit, refactor priorities, or code health questions
- 6 technical-debt categories
- 3-axis scoring: Impact, Risk, Effort
Adoption & trust: 3.5k installs on skills.sh; 19.6k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You know the codebase is slowing you down but cannot agree on what to refactor first or how to justify the time.
Who is it for?
Solo builders or tiny teams maintaining a live product who need one session to turn vague “code smell” into an ordered refactor queue.
Skip if: Greenfield projects with no production history, or when you only want a single-file lint fix without a portfolio-wide audit.
When should I use this skill?
User says tech debt, technical debt audit, what should we refactor, code health, refactoring priorities, or maintenance backlog.
What do I get? / Deliverables
You get a ranked debt backlog with effort, risk justification, and a phased fix plan you can schedule next to features.
- Prioritized debt list with scores
- Per-item business justification
- Phased remediation plan
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Canonical shelf is Operate because debt remediation and backlog grooming are ongoing production concerns after you are shipping. Iterate fits prioritizing what to fix next without blocking the whole roadmap—aligned with phased remediation alongside features.
Where it fits
Quarterly pass to rank dependency and test debt before the next two-week sprint.
Pre-release audit to see if flaky tests or missing integration coverage should block ship.
Turn ‘we need to refactor auth’ into scored items with effort for the implementation plan.
How it compares
Use for portfolio-level debt triage with scoring—not the same as a one-off linter pass or a full architecture rewrite spec.
Common Questions / FAQ
Who is tech-debt for?
Indie and solo developers shipping SaaS, APIs, or CLIs who own maintenance and need structured refactor priorities without a dedicated platform team.
When should I use tech-debt?
During Operate when grooming the maintenance backlog; in Ship before a release freeze to see what risks regressions; in Build when scoping a refactor epic alongside new features.
Is tech-debt safe to install?
It is guidance and analysis output—review the Security Audits panel on this Prism page for the upstream package before installing in your agent.
SKILL.md
READMESKILL.md - Tech Debt
# 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.