Skip to main content
affpapa.org
RU EN
skill CX Codex official · Anthropic

tech-debt · anthropics — Claude Code skill: audit and rank technical debt

Sorts technical debt into categories and scores each item so you know what to fix first. Useful when the backlog feels endless.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add anthropics/knowledge-work-plugins --skill tech-debt -a claude-code
Open on GitHub

What tech-debt does

The skill walks your codebase and groups what it finds into six buckets: code, architecture, tests, dependencies, documentation, infrastructure. Each bucket carries its own failure mode, from slow feature work to security holes and rough incident recovery. Every item then gets three scores between 1 and 5 — how much it slows the team, what happens if it stays, and how hard the fix is. Effort is inverted, so a small cleanup outranks a big rewrite.

Priority comes out as (Impact + Risk) x (6 - Effort). You get a ranked list with effort estimates and a business case per line, plus a phased plan you can run next to feature work. The arithmetic is deliberately plain, which makes the argument about numbers instead of taste.

Nothing here runs linters or pulls coverage reports. The model assigns the scores from your code and whatever you tell it about the project. A repo with no tests and no docs will leave some categories thin, and that is expected — the audit only reflects what the code shows.

What it helps with

  • spot modules that keep slowing delivery
  • separate urgent refactors from cosmetic ones
  • make the case for debt work to stakeholders
  • break a large refactor into phases beside feature work
  • flag outdated and abandoned dependencies

Example prompts for the agent

  • Run a technical debt audit on this repo and rank the findings
  • What should we refactor first?
  • Assess code health and give me a phased remediation plan

How to install tech-debt

1Skills CLI (Vercel)

npx skills add anthropics/knowledge-work-plugins --skill tech-debt -a claude-code

2Manually: put the files in place

~/.claude/skills/tech-debt/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/tech-debt/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about tech-debt

How do I install tech-debt in Claude Code?

Run npx skills add anthropics/knowledge-work-plugins --skill tech-debt -a claude-code. The skill lands in ~/.claude/skills/tech-debt/SKILL.md.

What does tech-debt do?

It identifies technical debt, sorts it into categories, and scores each item on impact, risk and effort. The result is a ranked list with a remediation plan.

Which platforms support the skill?

Claude, Codex, Cursor, GitHub Copilot, Gemini CLI and OpenCode. Each platform has its own install command.

Source text

SKILL.md · Apache-2.0 
---
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.

© anthropics · Apache-2.0 · anthropics/knowledge-work-plugins

Similar skills

Everything for Code review and refactoring →
improve-codebase-architecture Matt Pocock This skill scans a codebase for architectural friction, then builds a visual HTML report with refactoring candidates. Use it before a deeper architecture review. 1,163,035installs tdd Matt Pocock Guides the red-green TDD loop: ensures tests are written first, keep them at public interfaces, and avoid coupling to implementation details. 1,141,062installs triage Matt Pocock This skill moves issues and external PRs through triage states, verification, and agent briefs. It fits maintainers managing an issue queue. 990,453installs codebase-design Matt Pocock This skill helps design modules with small interfaces and hidden complexity. Use it when refactoring code, choosing a seam, or making tests easier to write. 850,344installs code-review Matt Pocock Reviews changes from a chosen reference point against repository standards and the originating spec. Use it for a branch, PR, or work in progress. 789,521installs implement Matt Pocock Implements work from a specification or tickets, following a test-driven flow and ending with review and a commit. Use it when a coding task needs a defined delivery routine. 774,700installs

From the same set159

The whole set →
system-design Walks you through designing services and systems: requirements, components, trade-offs. Useful when you need to decide how to split a service into parts. CX Codex +1 7,500installs memory-management This skill organizes workplace shorthand, names, and project details into files an agent can consult. It fits projects where requests rely on an internal vocabulary and shared context. CX Codex +1 7,400installs task-management Tracks commitments, active work, and follow-ups in a local TASKS.md file. Useful when managing project to-dos directly from the AI coding chat. CX Codex +1 7,200installs architecture Writes an Architecture Decision Record or reviews a system design: options, trade-offs, consequences. Useful when you have to pick between technologies. CX Codex +1 6,700installs knowledge-synthesis Merges search results across chats, emails, and documents into deduplicated answers with source attribution. Flags conflicting facts and scores source reliability. CX Codex +1 6,400installs testing-strategy This skill designs testing strategies and test plans for a project. Use it when you need test types, coverage goals, or gaps in existing checks. CX Codex +1 6,400installs view-pdf Opens PDFs in an interactive viewer for shared markup, form filling, highlights, stamps, and visual signatures. Use it when text reading alone is not enough. CX Codex +1 6,300installs explore-data Profiles tables and datasets to inspect column distributions, missing values, and anomalies before running analyses. CX Codex +1 5,900installs

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor