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

46%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/code-refactoring-tech-debt/SKILL.md

Quality

Content

42%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill provides a well-structured, comprehensive methodology for technical debt analysis with concrete thresholds and examples, but it is heavily verbose—explaining well-known concepts—and inlines all content into a single monolithic file with no progressive disclosure or validation checkpoints.

Suggestions

Trim explanations of concepts Claude already knows (e.g., definitions of cyclomatic complexity, god classes, feature flags, DDD) and keep only the thresholds and procedures.

Move detailed templates (metrics dashboard YAML, trend-analysis code, communication-plan markdown, refactoring code samples) into reference files under references/ and link to them from SKILL.md.

Add explicit validation checkpoints in the workflow (e.g., 'Verify the debt inventory covers all modules before computing impact', 'Re-validate metrics after remediation').

Dimension	Reasoning	Score
Conciseness	The ~280-line body extensively explains concepts Claude already knows (cyclomatic complexity, god classes, feature envy, DDD, facade/feature-flag patterns) and pads with large illustrative template blocks (YAML dashboards, trend dicts, full stakeholder reports), fitting 'noticeably verbose; several unnecessary explanations or padded sections'.	2 / 5
Actionability	Concrete thresholds (>10 complexity, >50 line methods, >500 line god classes) and example cost/ROI calculations are provided, but the analysis steps give no actual tooling or commands to run, and most code blocks are illustrative templates rather than executable instructions, matching 'some concrete guidance but incomplete'.	3 / 5
Workflow Clarity	Eight numbered sections form a clear sequence (Inventory -> Impact -> Metrics -> Remediation -> Implementation -> Prevention -> Communication -> Success), but there are no explicit validation checkpoints or feedback loops (e.g., verifying inventory completeness), fitting 'steps listed but validation gaps; checkpoints missing or implicit'.	3 / 5
Progressive Disclosure	The body has good section structure, but at ~280 lines with no bundle files (references/, scripts/, assets/ absent), substantial template content (metrics dashboards, communication plans, refactoring examples) that belongs in separate files is fully inlined, matching 'some structure but content that should be separate is inline'.	3 / 5
	Total	11 / 20 Passed

Description

50%Weight 40%Scale 1-5

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 clearly states what the skill does with several concrete actions, but it is written in second person and omits any 'Use when...' trigger guidance, capping completeness and reducing specificity. Trigger term coverage is limited to the single phrase 'technical debt' without synonyms.

Suggestions

Rewrite in third person (e.g., 'Identifies, quantifies, and prioritizes technical debt...') to avoid the voice penalty.

Add an explicit trigger clause such as 'Use when analyzing technical debt, planning refactoring, or assessing code quality and legacy code.'

Include synonym/natural variations like 'refactoring', 'legacy code', or 'code cleanup' to broaden trigger term coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('identifying, quantifying, and prioritizing technical debt', 'Analyze the codebase', 'assess its impact', 'create actionable remediation plans'), which would anchor at 4, but the second-person opening 'You are a technical debt expert' incurs the mandated -1 specificity penalty.	3 / 5
Completeness	There is a clear 'what' (identify/quantify/prioritize/analyze debt and remediate), but no 'Use when...' trigger or equivalent 'when' guidance, so completeness is capped at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	The natural phrase 'technical debt' is present and relevant, plus 'codebase', but common variations users would say (refactoring, legacy code, code cleanup) are missing, matching the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	'technical debt' is a recognizable niche, but the generic 'Analyze the codebase' framing and total absence of triggers mean it could overlap with general code-review or refactoring skills, fitting 'somewhat specific but could still overlap'.	3 / 5
	Total	12 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: rmyndharis/antigravity-skills
Path: skills/code-refactoring-tech-debt/SKILL.md
Commit: 3eff4af

Reviewed: 1 day 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.