Scan a codebase for technical debt—issues that make future maintenance harder—and prioritize fixes using business impact and effort. Generate a ranked backlog, sprint allocations, and trend reports to assess cleanup work over time.
中文简介正在准备中。当前显示英语简介。
Scan codebases for technical debt, score severity, track trends, and generate prioritized remediation plans. Use when users mention tech debt, code quality, refactoring priority, debt scoring, cleanup sprints, or code health assessment. Also use for legacy code modernization planning and maintenance cost estimation.
安装前可以查看交给 AI 代理的指令内容。
Tier: POWERFUL 🔥
Category: Engineering Process Automation
Expertise: Code Quality, Technical Debt Management, Software Engineering
Tech debt is one of the most insidious challenges in software development - it compounds over time, slowing down development velocity, increasing maintenance costs, and reducing code quality. This skill provides a comprehensive framework for identifying, analyzing, prioritizing, and tracking technical debt across codebases.
Tech debt isn't just about messy code - it encompasses architectural shortcuts, missing tests, outdated dependencies, documentation gaps, and infrastructure compromises. Like financial debt, it accrues "interest" through increased development time, higher bug rates, and reduced team velocity.
This skill offers three interconnected tools that form a complete tech debt management system:
Together, these tools enable engineering teams to make data-driven decisions about tech debt, balancing new feature development with maintenance work.
All paths relative to this skill folder. The scanner's JSON output feeds the prioritizer directly; dated inventory snapshots feed the dashboard.
python3 scripts/debt_scanner.py /path/to/codebase --format json --output debt_inventory.json
Emits debt_inventory.json with scan_metadata, summary, debt_items[], file_statistics, and recommendations. Report the summary counts to the user. (Dry run: assets/sample_codebase.)
python3 scripts/debt_prioritizer.py debt_inventory.json --framework wsjf --team-size 6 --sprint-capacity 20 --format json --output debt_priorities.json
Frameworks: cost_of_delay (default), wsjf, rice. Output contains prioritized_backlog (work top-down), sprint_allocation (paste into sprint planning), and insights.
Keep dated snapshots (debt_YYYY-MM-DD.json), then:
python3 scripts/debt_dashboard.py --input-dir snapshots/ --period monthly --format both --output debt_dashboard
Or pass files explicitly (samples: assets/historical_debt_2024-01-15.json assets/historical_debt_2024-02-01.json). The dashboard reports trend direction and executive-ready summaries — use it to verify a cleanup sprint actually reduced debt.
After a remediation sprint: re-run step 1, re-run step 3 with the new snapshot, and assert the targeted categories' counts dropped. A cleanup that doesn't move the dashboard is rework, not debt paydown.
→ See references/debt-frameworks.md for details (also: references/debt-classification-taxonomy.md, references/prioritization-framework.md, references/stakeholder-communication-templates.md)
Problem: Spending too much time analyzing debt instead of fixing it. Solution: Set time limits for analysis, use "good enough" scoring for most items.
Problem: Trying to eliminate all debt instead of managing it. Solution: Focus on high-impact debt, accept that some debt is acceptable.
Problem: Prioritizing technical elegance over business value. Solution: Always tie debt work to business outcomes and customer impact.
Problem: Some teams adopt practices while others ignore them. Solution: Make debt tracking part of standard development workflow.
Problem: Building complex debt management systems that nobody uses. Solution: Start simple, iterate based on actual usage patterns.
Technical debt management is not just about writing better code - it's about creating sustainable development practices that balance short-term delivery pressure with long-term system health. Use these tools and frameworks to make informed decisions about when and how to invest in debt reduction.
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Audit web applications for accessibility issues against WCAG 2.2 Level A and AA, the web accessibility standards. Get framework-specific code fixes, contrast checks, verification steps, and reports, with options for automated checks in development pipelines.
中文简介正在准备中。当前显示英语简介。
Plan A/B tests that compare page variations, from headlines to pricing layouts. Define a hypothesis, choose success metrics, calculate sample size and duration, and prepare launch checks and results reports to support decisions.
中文简介正在准备中。当前显示英语简介。
Create paid ad headlines and body copy tailored to each platform's character limits. Use existing performance data to develop variations, explore new messaging angles, and check copy for length, quality, and potential rejection risks.
中文简介正在准备中。当前显示英语简介。
Review code changes from three critical perspectives: production failures, maintainability, and security. Get a consolidated report that ranks findings by severity and provides merge guidance, helping examine assumptions that an ordinary self-review may overlook.
中文简介正在准备中。当前显示英语简介。
Audit and improve content intended for citation in AI answers. Review evidence, author information, and structure, generate revised content and structured metadata, and keep a local record of observed citations across AI services.
中文简介正在准备中。当前显示英语简介。
Create signed records for consequential agent actions such as deployments, deletions, and payments. Decide which actions need evidence, record the agent, action, target, and policy, then verify the resulting certificate offline to detect later changes.
中文简介正在准备中。当前显示英语简介。