codebase-cleanup-tech-debt
You are a technical debt expert specializing in identifying, quantifying, and prioritizing technical debt in software projects. Analyze the codebase to uncover debt, assess its impact, and create acti
43
30%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/codebase-cleanup-tech-debt/SKILL.mdQuality
Discovery
32%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description is truncated, which immediately undermines its effectiveness. While it identifies a clear domain (technical debt analysis) and lists some relevant actions, it lacks an explicit 'Use when...' clause and misses common trigger terms users might naturally use. The use of second person ('You are') violates the third-person voice requirement.
Suggestions
Complete the truncated description and add an explicit 'Use when...' clause with trigger terms like 'technical debt', 'code quality', 'refactoring priorities', 'legacy code', 'code smells'.
Rewrite in third person voice (e.g., 'Identifies, quantifies, and prioritizes technical debt...') instead of the current second person 'You are...' framing.
Add more specific concrete actions such as 'generates debt inventory reports', 'estimates remediation effort', 'maps dependency risks' to distinguish from generic code analysis skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (technical debt) and some actions (identifying, quantifying, prioritizing, analyzing, assessing impact), but these are somewhat generic and not fully concrete. It also appears truncated, cutting off at 'create acti' which likely means 'create actionable plans' or similar. | 2 / 3 |
Completeness | The description addresses 'what' (analyze codebase for technical debt) but has no explicit 'Use when...' clause or equivalent trigger guidance. Additionally, the description is truncated, making it incomplete. Per the rubric, a missing 'Use when' clause caps completeness at 2, and the truncation further reduces it. | 1 / 3 |
Trigger Term Quality | Includes relevant terms like 'technical debt', 'codebase', 'prioritizing', but misses common user variations such as 'code quality', 'refactoring', 'legacy code', 'code smell', or 'maintainability'. The terms present are reasonable but not comprehensive. | 2 / 3 |
Distinctiveness Conflict Risk | The focus on 'technical debt' is somewhat distinctive, but terms like 'analyze the codebase' and 'assess its impact' are generic enough to overlap with code review, code quality analysis, or refactoring skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is essentially a lengthy consulting report template rather than a focused, actionable skill for Claude. It over-explains concepts Claude already understands (code smells, testing types, DDD), fills space with hypothetical example data, and provides no progressive disclosure despite its massive length. The core value—how to systematically analyze a real codebase for technical debt—is buried under template boilerplate.
Suggestions
Reduce content by 60-70%: Remove explanations of well-known concepts (cyclomatic complexity, God classes, DDD) and fictional example calculations. Focus on the specific analytical workflow and decision criteria Claude should follow.
Split detailed templates into referenced files: Move the metrics dashboard template, communication plan template, and implementation code examples into separate files (e.g., METRICS_TEMPLATE.md, COMMUNICATION_TEMPLATE.md) and reference them from the main skill.
Add validation checkpoints: Include explicit verification steps like 'Before proceeding to remediation planning, confirm the debt inventory with the user' and 'Validate cost estimates against actual team velocity data before presenting ROI projections.'
Make the skill operate on actual code: Add concrete instructions for how Claude should use tools (file search, grep, code reading) to discover real debt in the user's codebase, rather than providing pre-filled template examples.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~300+ lines with extensive template/example data that Claude already knows how to generate. The skill explains general software engineering concepts (what cyclomatic complexity is, what God classes are, what DDD is) and provides hypothetical example calculations that pad the content enormously without adding actionable, project-specific value. | 1 / 3 |
Actionability | Contains some concrete code examples (facade pattern, feature flags) and specific metric thresholds, but most content is template/placeholder data (fictional cost calculations, made-up metrics like 'score: 890') rather than executable guidance. The skill reads more like a consulting report template than instructions Claude can directly act on against a real codebase. | 2 / 3 |
Workflow Clarity | The 8-step numbered sequence provides a clear high-level workflow, but there are no validation checkpoints or feedback loops between steps. For a skill involving potentially destructive refactoring operations, there's no explicit 'verify before proceeding' guidance, and the steps are more of a report outline than an operational workflow. | 2 / 3 |
Progressive Disclosure | The entire skill is a monolithic wall of text with no references to external files. All detailed templates, examples, metrics dashboards, and implementation strategies are inlined, making the skill extremely long. Content like the communication plan templates, team allocation YAML, and detailed code examples could easily be split into referenced files. | 1 / 3 |
Total | 6 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- sickn33/antigravity-awesome-skills
- Commit
93c57b2
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.