CtrlK
BlogDocsLog inGet started
Tessl Logo

tech-debt-tracker

Scan codebases for technical debt, score severity, track trends, and generate prioritized remediation plans. Use when users mention tech debt, code quality, refactoring priority, debt scoring, cleanup sprints, or code health assessment. Also use for legacy code modernization planning and maintenance cost estimation.

72

Quality

88%

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

The canonical home for this skill is tech-debt-tracker in alirezarezvani/claude-skills

SKILL.md
Quality
Evals
Security

Quality

Content

81%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 body is highly actionable with a clear, validated workflow, but it spends tokens explaining tech-debt fundamentals Claude already knows and advertises bundle files that are absent from the package.

Suggestions

Trim or remove the 'Overview' paragraphs and the 'Common Pitfalls and How to Avoid Them' section — they explain tech-debt concepts Claude already knows and dilute the token budget.

Ship the referenced bundle files (scripts/debt_scanner.py, debt_prioritizer.py, debt_dashboard.py, references/*.md, assets/sample_codebase and historical snapshots) so the signaled one-level-deep navigation actually resolves.

Move the classification-framework detail (currently pointed at references/) into the reference files so the SKILL.md body stays a lean overview, confirming each 'See references/...' path exists.

DimensionReasoningScore

Conciseness

The opening 'Tech debt is one of the most insidious challenges in software development...' and the five Problem/Solution pitfalls restate concepts Claude already knows; the actionable command block is efficient, but the prose padding keeps it from a 4.

3 / 5

Actionability

All three tools are shown as fully-formed, copy-paste-ready commands with flags and arguments (e.g. 'python3 scripts/debt_scanner.py /path/to/codebase --format json --output debt_inventory.json') plus described output schemas, covering the common cases.

5 / 5

Workflow Clarity

A clearly numbered scan → prioritize → dashboard sequence is capped by an explicit 'Verification loop' that re-runs the scan and asserts category counts dropped — a real feedback loop for the batch operation.

5 / 5

Progressive Disclosure

Good structure with a concise quick-start inline and clearly signaled one-level-deep references (references/debt-frameworks.md et al.), but the referenced bundle directories (scripts/, assets/, references/) do not actually exist, leaving the navigation dangling.

4 / 5

Total

17

/

20

Passed

Description

96%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.

A strong, well-structured description that crisply states capabilities and provides rich, natural trigger phrases. Only minor overlap risk with adjacent code-quality/refactoring skills keeps distinctiveness from a perfect score.

DimensionReasoningScore

Specificity

Names four concrete actions — 'Scan codebases for technical debt, score severity, track trends, and generate prioritized remediation plans' — giving comprehensive coverage rather than a single generic verb.

5 / 5

Completeness

Explicitly answers both halves: a clear 'what' (scan, score, track, generate plans) and an explicit 'Use when...' trigger clause with concrete phrases.

5 / 5

Trigger Term Quality

Dense set of natural phrases users would actually say — 'tech debt, code quality, refactoring priority, debt scoring, cleanup sprints, or code health assessment' plus 'legacy code modernization' — covering synonyms and variations.

5 / 5

Distinctiveness Conflict Risk

Tech-debt tracking is a clear niche with distinct triggers, but 'code quality' and 'refactoring priority' carry minor overlap risk with general code-review or refactoring skills.

4 / 5

Total

19

/

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

referenced_paths_exist

Referenced path issues: 10 missing

Warning

Total

15

/

16

Passed

Repository
alirezarezvani/claude-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.