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

Quality

48%

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 ./docs/v19.7/configuration/agent/skills_external/antigravity-awesome-skills-main/skills/codebase-cleanup-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-sequenced, domain-complete analysis framework, but it is significantly over-long, re-explains concepts Claude already knows, and offers illustrative rather than executable guidance. It is a monolithic single file whose templates and code examples belong in separate reference files.

Suggestions

Cut definitions and patterns Claude already knows (complexity thresholds, code-smell taxonomy, facade/feature-flag migration) and keep only project-specific guidance, checklists, and output expectations.

Move the metrics-dashboard YAML, stakeholder-report templates, quality-gate configs, and refactoring code samples into references/ files (e.g., references/templates.md) linked one level deep from SKILL.md.

Add validation checkpoints to the workflow, e.g., 'verify computed metrics against tool output (SonarQube/coverage reports) before presenting the dashboard' and 'confirm cost assumptions (hourly rate, bug counts) with the user before finalizing ROI projections'.

Dimension	Reasoning	Score
Conciseness	The ~380-line body extensively restates domain knowledge Claude already has (cyclomatic complexity thresholds, god classes, feature envy, shotgun surgery, facade-plus-feature-flag migration patterns) and includes circular boilerplate ('Use this skill when: Working on technical debt analysis and remediation tasks'), matching the 'noticeably verbose; several unnecessary explanations or padded sections' anchor.	2 / 5
Actionability	There are concrete thresholds and cost formulas, but the code examples are illustrative rather than executable (PaymentService.process_payment is 'pass', feature_flag is undefined) and no runnable commands or tool invocations are given, matching the 'pseudocode instead of executable code; missing key details' anchor.	3 / 5
Workflow Clarity	The eight numbered phases form a clear sequence with an Output Format section, but validation checkpoints are absent throughout (e.g., no step to verify computed metrics against actual tool output or confirm cost estimates with the user), matching the 'sequence present but checkpoints missing' anchor.	3 / 5
Progressive Disclosure	Section structure is good (numbered ### headings, Output Format), but no bundle files exist and large template blocks (metrics dashboard YAML, stakeholder reports, quality-gate configs, refactoring code samples) are fully inlined in one ~380-line file where the rubric expects them split into clearly signaled reference files; this sits between the 'inlined content, minimal structure' (2) and 'good structure, references mostly clear' (4) anchors.	3 / 5
	Total	11 / 20 Passed

Description

53%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 communicates a clear domain and a concrete set of actions, but it is truncated mid-word, uses second-person voice, and entirely lacks a 'Use when...' trigger clause, capping completeness at 3. Trigger-term coverage is adequate but misses natural synonyms users would actually say.

Suggestions

Rewrite in third person and complete the truncated final clause, e.g.: 'Identifies, quantifies, and prioritizes technical debt in software projects; analyzes the codebase to uncover debt, assess its impact, and create actionable remediation plans.'

Append an explicit trigger clause: 'Use when the user mentions technical debt, tech debt, legacy code, code quality, or asks for a refactoring roadmap or debt cleanup plan.'

Include natural synonyms ('tech debt', 'refactoring', 'code smells') so the description matches how users actually phrase these requests.

Dimension	Reasoning	Score
Specificity	Names the domain and several actions ('identifying, quantifying, and prioritizing technical debt', 'Analyze the codebase to uncover debt, assess its impact'), but the rubric's third-person guideline penalizes the second-person 'You are a technical debt expert' framing by 1, and the text is truncated mid-phrase ('create acti'), cutting off the final action.	3 / 5
Completeness	The 'what' is clearly stated (identify, quantify, prioritize, analyze, assess impact), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which the rubric caps at 3. It is not a 4 because the 'when' is entirely absent rather than merely under-specified.	3 / 5
Trigger Term Quality	'Technical debt' and 'remediation' are natural terms users would say, but common synonyms and variations like 'tech debt', 'refactoring', 'legacy code', or 'code smells' are missing, matching the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	'Technical debt analysis and remediation' carves a mostly distinct niche with low overlap risk versus general code-review or refactoring skills; it is not a 5 because the lack of explicit trigger phrases leaves minor overlap with adjacent software-quality skills.	4 / 5
	Total	13 / 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: duclm1x1/Dive-Ai
Path: docs/v19.7/configuration/agent/skills_external/antigravity-awesome-skills-main/skills/codebase-cleanup-tech-debt/SKILL.md
Commit: 20ba150

Reviewed: 6 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.