Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Tech Debt Prioritizer: Find, Score & Plan the Fixes That Pay

    1

    Scans a repo for tech debt using git churn, complexity, TODOs, outdated deps and test gaps, then scores each item by business impact vs effort and outputs a quarter-ready roadmap you can show to managers.

    Free

    Security scanned
    Tech Debt Prioritizer: Find, Score & Plan the Fixes That Pay

    Tech Debt Prioritizer: Find, Score & Plan the Fixes That Pay

    Example session with this skill installed

    Find our biggest tech debt in this Django monolith and give me something I can show my CTO.

    • Read your context and instructions
    • Compiled the tech debt prioritizer

    Hotspots (last 12 months)

    FileCommitsComplexityBug fixesTests
    billing/services.py14238 (max fn)3122%
    orders/views.py118271940%
    core/utils.py9615410%

    Prioritized items (score = Impact × Freq × Risk / Effort)

    #ItemImpactFreqRiskEffortScore
    1Billing logic is risky to change555341.7
    2core/utils.py grab-bag module242116.0
    3Django 3.2 is out of security support425313.3

    Now: add characterization tests around calculate_invoice(); split core/utils.py by domain; pin and upgrade 6 vulnerable deps.
    Next: extract a BillingService behind an interface (strangler), migrate callers one view at a time; upgrade to Django 4.2 LTS.
    Accept: legacy admin templates (rarely touched, no bugs).

    For your CTO
    Billing code causes 1 in 3 production bugs and is touched weekly. Each change takes ~2× longer than elsewhere. Ask: 20% of one squad for 6 weeks. Expected payoff: fewer billing incidents and faster pricing changes. Django 3.2 also no longer gets security fixes, so that upgrade is a compliance item.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Scans a repo for tech debt using git churn, complexity, TODOs, outdated deps and test gaps, then scores each item by business impact vs effort and outputs a quarter-ready roadmap you can show to managers.

    How it works

    • Collect signals (run, don't guess)
    • Group into debt items
    • Score
    • Roadmap
    • Manager summary

    Use it when

    You say tech debt, what should we refactor, codebase health, legacy code, justify refactoring to management, hotspots, or plan a cleanup sprint.

    Why this one

    • Runs real checks instead of generic advice
    • Concrete output: files, tables and next steps you can act on today
    • Works with Claude Code, Codex CLI, Cursor, Gemini CLI and any SKILL.md agent

    More by Ignasi: Frontend Design Pro, Security Audit, Cut Agent Token Costs.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Code Quality & Review.

    Requires git history and local static analysis tools. Cannot access private bug trackers; relies on commit message patterns for bug linkage.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed today

    • Free with an Agensi account

    Software
    Git

    Permissions

    Terminal / Shell
    Listedtoday

    What's inside

    Frequently Asked Questions

    The skill uses a weighted formula that intersections 'git churn' (how often a file changes) with 'cyclomatic complexity' (how difficult the code is to follow), ensuring you focus on files that actually hinder development speed.

    This skill is compatible with most AI agents that have filesystem access and the ability to run shell commands, such as AutoGPT, Open Interpreter, or custom LangChain agents.

    While it works with any git-initialized repository, the most detailed complexity insights are generated when language-specific tools like ESLint, Radon, or GoCyclo are installed in your environment.

    You receive the logic for hotspot analysis, the prioritization scoring framework, and structured templates for generating both developer roadmaps and executive-level reports.

    The skill relies on local git history and static analysis; it does not send your source code to external servers, though the AI agent will process the metadata locally to generate the report.

    The skill requires a repository with a git history; it cannot provide churn-based insights on flat files or codebases without a commit log.

    New in Code Quality & Review

    Free