AutoGineer
Generated banner for Tech Debt
Generated logo for Tech Debt

Tech Debt

AnthropicOfficialPublished by Anthropic

  • Skill
  • Review and audit
  • Software development
  • Apache-2.0
  • No issues found
Download ZIP

From the author

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 by Anthropic

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

The tech-debt skill provides a structured approach to managing technical debt by categorizing issues across code, architecture, testing, dependencies, documentation, and infrastructure. It utilizes a specific scoring formula based on impact, risk, and effort to help teams objectively prioritize their maintenance backlog. The skill outputs a prioritized list with business justifications and a phased remediation plan designed to integrate seamlessly with ongoing feature development.

What it does

  • Categorizes technical debt into six distinct areas including code, architecture, and infrastructure.
  • Applies a mathematical scoring framework to rank debt items by priority.
  • Generates business justifications for addressing specific maintenance tasks.
  • Creates a phased remediation plan that balances refactoring with feature work.

When to use it

  • When evaluating the current state of code quality or maintenance backlogs.
  • When deciding which parts of a codebase require immediate refactoring.
  • When planning development cycles that need to include debt reduction.
  • When justifying the need for infrastructure or documentation improvements to stakeholders.

Advantages

  • Provides an objective, data-driven method for prioritizing technical work.
  • Helps teams balance long-term code health with short-term feature delivery.
  • Covers a broad spectrum of debt types beyond just code, including documentation and infrastructure.
  • Facilitates clearer communication with stakeholders regarding the business impact of technical debt.

Usage examples

“tech debt”
The agent will initiate an audit process, asking for context on the current codebase to categorize and score existing technical debt items.
“what should we refactor”
The agent will analyze the provided codebase or project context to suggest high-priority refactoring candidates based on the impact-risk-effort framework.

Install

  1. Download the skill as a ZIP:

    https://autogineer.com/agent-skills/anthropics/tech-debt/download

  2. Unzip it into the cross-client skills folder of your project:

    mkdir -p .agents/skills && unzip tech-debt.zip -d .agents/skills

Documentation by Anthropic

Tech Debt Management

Systematically identify, categorize, and prioritize technical debt.

Categories

TypeExamplesRisk
Code debtDuplicated logic, poor abstractions, magic numbersBugs, slow development
Architecture debtMonolith that should be split, wrong data storeScaling limits
Test debtLow coverage, flaky tests, missing integration testsRegressions ship
Dependency debtOutdated libraries, unmaintained dependenciesSecurity vulns
Documentation debtMissing runbooks, outdated READMEs, tribal knowledgeOnboarding pain
Infrastructure debtManual deploys, no monitoring, no IaCIncidents, 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.

Files

SKILL.md

Tech Debt Management

Systematically identify, categorize, and prioritize technical debt.

Categories

TypeExamplesRisk
Code debtDuplicated logic, poor abstractions, magic numbersBugs, slow development
Architecture debtMonolith that should be split, wrong data storeScaling limits
Test debtLow coverage, flaky tests, missing integration testsRegressions ship
Dependency debtOutdated libraries, unmaintained dependenciesSecurity vulns
Documentation debtMissing runbooks, outdated READMEs, tribal knowledgeOnboarding pain
Infrastructure debtManual deploys, no monitoring, no IaCIncidents, 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.

Requirements and compatibility

Written for: Claude Code, Claude apps

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Security

No issues found by our static scan· No issues found

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Attribution and licence

Published by
Anthropic
Publisher
Anthropic (Official)
Source
anthropics/knowledge-work-plugins · engineering/skills/tech-debt · commit e050c2e
Licence
Apache License 2.0 (redistribution allowed)
  • LICENSE (added by AutoGineer from LICENSE)
  • ATTRIBUTION.md (written by AutoGineer)
Synced

AutoGineer is not affiliated with or endorsed by Anthropic or Anthropic.

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download tech-debt.zip