techdebt

Technical debt detection and remediation. Run at session end to find duplicated code, dead imports, security issues, and complexity hotspots. Triggers: 'find tech debt', 'scan for issues', 'check code quality', 'wrap up session', 'ready to commit', 'before merge', 'code review prep'. Always uses parallel subagents for fast analysis.

1.35x

Quality

—

Does it follow best practices?

Impact

87%

1.35x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

77%

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 is overlong for a single file and leans on inline content plus dangling references to non-existent files rather than genuine progressive disclosure.

Suggestions

Create the referenced references/patterns.md and references/severity-guide.md (or remove the links), so the body's References section points to real bundle files instead of dangling paths.

Move the detailed Detection Patterns, Integration Patterns, and Advanced Usage sections into reference files and keep SKILL.md as a lean overview pointing to them, improving progressive disclosure and conciseness.

Trim low-value padding such as the emoji 'Benefits' list and the 'Best Practices' team-advice section to reduce token cost.

Dimension	Reasoning	Score
Conciseness	The ~420-line body is mostly efficient operational guidance, but padded with emoji 'Benefits', a 'Best Practices' section of team platitudes, and full pre-commit/CI YAML examples that could be trimmed, matching the 'mostly efficient but could be tightened' anchor.	2 / 3
Actionability	Concrete commands ('git diff --name-only HEAD', 'claude skill techdebt --deep --ci'), specific tool lists (ast-grep, radon, eslint, jscpd), explicit threshold tables, and copy-paste-ready code examples for security patterns make the guidance fully executable.	3 / 3
Workflow Clarity	A clear 5-step sequence (scope, spawn subagents, consolidate, report, auto-fix) is laid out, and the destructive auto-fix step includes explicit safety rules plus interactive Y/N/A/Q confirmation checkpoints acting as validation gates.	3 / 3
Progressive Disclosure	Sections are well-organized and references are signaled via markdown links, but the file is a monolithic wall of text with detection patterns, integration, and advanced usage inline, and the referenced 'references/patterns.md' and 'references/severity-guide.md' files do not exist as bundle files.	2 / 3
	Total	10 / 12 Passed

Description

100%

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 specific, complete, and trigger-rich, clearly stating what the skill does and when to use it with natural user-facing trigger phrases. It is a strong, well-distinguished description with only minor generic-trigger overlap.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'find duplicated code, dead imports, security issues, and complexity hotspots' plus 'detection and remediation' — matching the anchor for listing several specific concrete actions.	3 / 3
Completeness	It explicitly answers both what (debt detection/remediation across named categories) and when ('Run at session end' plus an explicit Triggers clause), satisfying the equivalent of a 'Use when...' clause.	3 / 3
Trigger Term Quality	An explicit 'Triggers:' clause lists natural phrases users would say ('find tech debt', 'scan for issues', 'wrap up session', 'ready to commit', 'before merge', 'code review prep'), giving good coverage.	3 / 3
Distinctiveness Conflict Risk	The 'Technical debt detection' niche with distinctive triggers like 'find tech debt', 'before merge', and 'code review prep' is unlikely to fire for unrelated skills, though a few generic terms like 'scan for issues' slightly soften it.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 2 missing	Warning
referenced_paths_exist	Referenced path issues: 4 missing	Warning

	Total	14 / 16 Passed

Repository: NeverSight/skills_feed
Commit: 26d37ce

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.