
Tech Debt Tracker
Scans code for debt markers and maintains a prioritized tech debt register
- Repository
- Donchitos/Claude-Code-Game-Studios
- Stars
- 32,965
- Licence
- MIT
- Files
- 1 file
What it does
Once installed, the agent can scan your project's source code for common signs of technical debt such as TODO, FIXME and HACK comments, deprecated markers, very long files and very long functions. It sorts what it finds into categories like architecture, test or documentation debt, and keeps a register file at docs/tech-debt-register.md. It can also add entries by asking you questions, re-rank items by impact versus effort, and produce a summary report.
Great for
- Teams using the Claude Code Game Studios template who want a tracked list of known shortcuts and problems
- Developers who want a structured way to record and rank technical debt instead of leaving it in scattered comments
- Tech leads planning which cleanup work to schedule next
Skip it if
- Projects with no source code yet: the skill stops and reports NOT ASSESSED rather than producing a useful scan
- Anyone expecting automatic fixes: the skill only records and ranks debt, and asks before writing to the register file
- Teams needing a full static analysis or security scan: it uses simple text searches (Grep) and size counts, not a real code analyser
Try asking
- “/tech-debt scan”
- “/tech-debt add”
- “/tech-debt prioritize”
- “/tech-debt report”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 1 original files, the MIT licence and an attribution note.
tech-debt.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip tech-debt.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip tech-debt.zip -d .claude/skills/Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.
- 3
Ask for the task
No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.
Get better results
- Run scan only once implementation code exists, so the result reflects a real codebase rather than an empty search.
- Approve or decline the register write each time; the skill is designed to ask before writing and never to overwrite the register.
- Use prioritize before sprint planning to get a ranked list of which debt to address first.
What's inside
- SKILL.md
Redistributed unmodified from Donchitos/Claude-Code-Game-Studios under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.