code-refactoring-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

Quality

30%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/code-refactoring-tech-debt/SKILL.md

Quality

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 severely undermines its effectiveness. While it identifies a clear domain (technical debt) and lists some relevant actions, it lacks an explicit 'Use when...' clause and is missing natural trigger terms users might employ. The truncation means it cannot fully communicate the skill's capabilities or selection criteria.

Suggestions

Complete the truncated description and add an explicit 'Use when...' clause with trigger phrases like 'Use when the user asks about technical debt, code quality issues, refactoring priorities, legacy code cleanup, or code smells.'

Add more natural trigger terms users would say, such as 'refactoring', 'legacy code', 'code smell', 'code quality', 'maintenance burden', and 'cleanup'.

Switch from second-person expert framing ('You are a technical debt expert') to third-person action voice ('Identifies, quantifies, and prioritizes technical debt in software projects').

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 as concrete as listing specific outputs or techniques. It also appears truncated, cutting off at 'create acti'.	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 like 'code quality', 'refactoring', 'legacy code', 'code smell', or 'cleanup'. The truncation also limits keyword coverage.	2 / 3
Distinctiveness Conflict Risk	The focus on 'technical debt' is a reasonably specific niche, but terms like 'analyze the codebase' and 'assess its impact' are generic enough to overlap with code review, code quality, or static analysis 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 reads like a comprehensive technical debt consulting playbook rather than a concise, actionable skill for Claude. It over-explains concepts Claude already knows (code smells, testing types, deployment practices) and fills space with hypothetical examples that won't match any real codebase. The content would benefit enormously from being reduced to a lean checklist/framework with detailed templates moved to separate bundle files.

Suggestions

Reduce the main SKILL.md to ~50-80 lines covering the high-level workflow steps and key decision criteria, moving detailed templates (impact calculation, metrics dashboard, communication plan) into separate bundle files like TEMPLATES.md or METRICS.md.

Remove explanations of concepts Claude already knows (what cyclomatic complexity is, what God classes are, types of testing debt) and replace with just the actionable thresholds and checklists.

Add explicit validation checkpoints: e.g., 'After generating the debt inventory, confirm findings with the user before calculating impact' and 'Verify metric claims against actual tool output (e.g., run coverage tools) before reporting numbers.'

Replace hypothetical placeholder examples ($150/hour, React 16→18) with parameterized templates that instruct Claude to fill in project-specific values from actual codebase analysis.

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~300+ lines. Most content is generic technical debt knowledge that Claude already possesses (what cyclomatic complexity is, what God classes are, what code duplication means). The examples use hypothetical data ($150/hour, React 16→18) that aren't actionable for any specific codebase. Nearly every section could be cut by 80%.	1 / 3
Actionability	Contains some concrete code examples (facade pattern, feature flags) and specific metric thresholds, but most guidance is template-like with placeholder values rather than executable against a real codebase. The YAML and Python snippets are illustrative rather than copy-paste ready—they're example report formats, not tools Claude can run.	2 / 3
Workflow Clarity	The 8-step numbered process provides a clear sequence, but there are no validation checkpoints or feedback loops. For a skill involving codebase analysis (which could produce incorrect assessments), there's no step to verify findings, validate metrics against actual tooling output, or confirm assumptions with the user before proceeding to remediation planning.	2 / 3
Progressive Disclosure	Monolithic wall of text with no references to external files and no bundle structure. All content is inline despite being far too long for a single SKILL.md. The detailed examples, metric templates, and implementation strategies should be split into separate reference files.	1 / 3
	Total	6 / 12 Passed

Validation

90%

Warnings & errors only

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: 79d9c42

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.