CtrlK
BlogDocsLog inGet started
Tessl Logo

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

54

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

63%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 content is a thorough, well-sequenced analytical workflow with concrete thresholds and executable example patterns, but it is monolithic and padded with extensive illustrative blocks that hurt token efficiency and would benefit from being split into referenced files. Validation checkpoints between phases are absent.

Suggestions

Move the detailed example templates (metrics dashboards, refactoring code, communication reports, quality-gate configs) into separate reference files and link to them from SKILL.md to improve progressive disclosure and conciseness.

Trim or generalize time-sensitive examples (React 16→18, 2024_Q1 trend dates) or relocate them to a clearly labeled 'deprecated/legacy patterns' section.

Add explicit validation checkpoints between phases (e.g. 'Confirm the debt inventory is complete and metrics captured before prioritizing remediation') to raise workflow clarity.

DimensionReasoningScore

Conciseness

The body is mostly efficient structured checklists without re-explaining basics, but it is padded with many fully filled-in example blocks (cost calculations, dashboards, communication reports) and embeds time-sensitive items (React 16→18, 2024_Q1 dates) outside any deprecated section.

3 / 5

Actionability

Provides concrete, usable thresholds (>10 cyclomatic complexity, >50-line methods, >500-line god classes) and executable patterns such as the feature-flag PaymentFacade refactoring and YAML quality-gate configs, with only minor gaps since the code is illustrative rather than directly runnable against a user's codebase.

4 / 5

Workflow Clarity

The eight phases (Inventory → Impact → Metrics → Remediation → Implementation → Prevention → Communication → Success Metrics) form a clear, well-ordered sequence, but there are no explicit validation checkpoints or feedback loops between phases.

4 / 5

Progressive Disclosure

The skill is a ~390-line monolithic SKILL.md with no bundle files and no external references; section structure is good, but template content (dashboards, refactoring patterns, communication templates) that could be split into separate reference files is fully inlined, and the under-50-line exception does not apply.

3 / 5

Total

14

/

20

Passed

Description

58%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 states a clear capability set around technical debt analysis but omits any explicit 'when to use' trigger guidance and uses second-person voice, which caps completeness and lowers specificity. Trigger-term coverage is adequate but lacks synonyms that broaden natural activation.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers, e.g. 'Use when the user asks to assess technical debt, prioritize refactoring, or plan code-quality improvements.'

Rewrite in third person ('Analyzes technical debt...') to avoid the second-person voice penalty.

Include synonyms users naturally say — refactoring, code smells, legacy code, code quality — to improve trigger-term quality and distinctiveness.

DimensionReasoningScore

Specificity

Lists several concrete actions ('identifying, quantifying, and prioritizing technical debt', 'Analyze the codebase to uncover debt, assess its impact, and create actionable remediation plans'), nearing comprehensive coverage; reduced from 5 to 4 by the second-person voice penalty ('You are a technical debt expert').

4 / 5

Completeness

Has a clear 'what' (identify/quantify/prioritize/remediate debt) but no 'Use when...' clause or equivalent explicit trigger guidance, so completeness is capped at 3 per the rubric guideline.

3 / 5

Trigger Term Quality

Contains the natural core term 'technical debt' and 'codebase', but misses common synonyms and variations users would say such as refactoring, code smells, legacy code, or code quality.

3 / 5

Distinctiveness Conflict Risk

The 'technical debt' niche is mostly distinct, but it carries minor overlap risk with closely related refactoring and code-quality skills rather than being a uniquely triggered niche.

4 / 5

Total

14

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
sickn33/antigravity-awesome-skills
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.