Dev Loop Tech Debt Tracker
Use when the user asks to track technical debt, build a tech debt register, prioritize debt by interest and cost, measure code health, or set a debt budget per sprint. Produces a debt inventory with scoring and a paydown plan. Not for doing the refactor (use dev-loop-refactor-guide) or quality gates (use qc).
Install
npx skills add j4flmao/agent-skills --skill dev-loop-tech-debt-trackergit clone --depth 1 https://github.com/j4flmao/agent-skills.git /tmp/agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/agent-skills/skills/dev-loop/tech-debt-tracker ~/.claude/skills/dev-loop-tech-debt-trackerPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Technical Debt Tracker
## Purpose
Systematically identify, track, prioritize, and reduce technical debt — establishing a quantifiable, transparent process that balances feature velocity with codebase health.
## Agent Protocol
### Trigger
Exact user phrases: "technical debt", "tech debt", "code debt", "debt tracking", "code quality debt", "debt backlog", "reduce tech debt", "tech debt sprint", "debt prioritization", "code health".
### Input Context
- Codebase size and age (lines of code, years in production)
- Current pain points (slow development, frequent bugs, long onboarding)
- Existing debt indicators (test coverage %, cyclomatic complexity, duplication)
- Team size and velocity (story points per sprint, team capacity)
- Business constraints (release deadlines, regulatory requirements, SLAs)
- Tooling available (SonarQube, CodeClimate, Codacy, custom)
### Output Artifact
Tech debt inventory with prioritized items, remediation estimates, and tracking system.
### Response Format
```
Item: {ID} {title} ({type})
Impact {1-5} × Frequency {1-5} / Effort {1-5} = Priority {score}
Interest: {cost per sprint if left}
Plan: {sprint allocation, owner}
Status: {OPEN|IN PROGRESS|DONE}
```
### Completion Criteria
- [ ] Debt discovery methods established (automated scans + developer input)
- [ ] Debt items cataloged with type, location, impact, and effort
- [ ] Prioritization rubric defined (impact × frequency × effort)Details
- Skill name
dev-loop-tech-debt-tracker- Repository
- j4flmao/agent-skills
- Path
skills/dev-loop/tech-debt-tracker/SKILL.md- License
- MIT
- Repo updated
- 17 November 2026
FAQ
What does the Dev Loop Tech Debt Tracker skill do?
Use when the user asks to track technical debt, build a tech debt register, prioritize debt by interest and cost, measure code health, or set a debt budget per sprint. Produces a debt inventory with scoring and a paydown plan. Not for doing the refactor (use dev-loop-refactor-guide) or quality gates (use qc).
How do I install the Dev Loop Tech Debt Tracker skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add j4flmao/agent-skills --skill dev-loop-tech-debt-tracker. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Dev Loop Tech Debt Tracker popular?
It lives in j4flmao/agent-skills, which has 45 GitHub stars and 6 forks.
Related skills
Agent Observability
45j4flmao/agent-skills
Use when the user asks about agent observability, tracing agent reasoning, debugging an agent loop, OpenTelemetry GenAI spans for LLM calls, LLM cost tracking per agent, agent audit logs or hallucination/eval monitoring in production. Produces instrumentation config, trace schema, dashboards, alerts and cost attribution. Not for generic service tracing without LLMs (use devops-opentelemetry).
AI Agent Architectures
45j4flmao/agent-skills
Use when the user asks to build an AI agent, design an agent that calls tools and keeps memory, write an agent system prompt or pick an agent framework (Claude Agent SDK, OpenAI Agents SDK, LangGraph). Produces an architecture brief covering loop, tools, memory, guardrails and evals, routing depth to child skills. Not for workflow patterns (use ai-agentic-workflows).
AI Agent Core Loop
45j4flmao/agent-skills
Use when the user asks about the agent loop, ReAct vs plan-and-solve, re-planning, Reflexion, an agent stuck in a loop, max iterations or termination conditions. Produces a loop spec or patch with state, success predicate, caps and no-progress detection. Not for overall agent design (use ai-agent-architectures) or tool schemas (use tool-calling-principles).
Devops Internal Developer Platform
45j4flmao/agent-skills
Use when the user asks to build an internal developer portal with Backstage, Backstage plugins, software templates and Scaffolder custom actions, the software catalog entity model, TechDocs, the permission framework, or golden path templates. Produces Backstage implementation designs. Not for platform team strategy and maturity (use devops-platform-engineering).
Dev Loop Refactor Guide
45j4flmao/agent-skills
Use when the user asks to refactor a long function or class safely, remove code smells, extract methods, untangle legacy code, or improve structure without changing behavior. Produces a step-by-step refactoring plan with characterization tests. Not for tracking debt backlogs (use dev-loop-tech-debt-tracker) or system migrations (use enterprise-legacy-migration).
Devops Policy As Code
45j4flmao/agent-skills
Use when the user asks to enforce admission policies with OPA Gatekeeper, Rego, Kyverno, ValidatingAdmissionPolicy (CEL), conftest or opa test, mutation policies, or compliance as code in CI. Produces tested policies and CI enforcement. Not for compliance programs (use enterprise-compliance-audit) or RBAC/ABAC design (use abac-access-control).
Browse the most popular Claude skills, all software development skills, or write your own with the skills generator.