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

73%

Does it follow best practices?

Impact

87%

1.35x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./data/skills-md/0xdarkmatter/claude-mods/techdebt/SKILL.md

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 body is well-structured and largely actionable with good sequencing and safety rules, but it is over-long for a SKILL.md, inlines detail that belongs in reference files, and points to two reference files that are missing. Tightening and adding the referenced files would raise quality notably.

Suggestions

Move Detection Patterns, Language Support, and Advanced Usage detail into the referenced files (references/patterns.md, references/severity-guide.md) and actually create those files so the links resolve.

Trim the promotional Architecture ASCII diagram and emoji 'Benefits' list to a one-line note, keeping the body focused on guidance Claude cannot infer.

Replace the placeholder subagent template ({scope}, {category}) with one fully worked example invocation so the core step is copy-paste executable.

Dimension	Reasoning	Score
Conciseness	Mostly actionable content, but at ~420 lines it includes padded sections (the ASCII architecture diagram and the emoji 'Benefits' list) that could be trimmed without losing guidance.	3 / 5
Actionability	Provides copy-paste-ready pre-commit hooks, CI YAML, and JSON rule/baseline examples, but the core subagent instruction block uses template placeholders ({scope}, {category}) rather than fully executable code.	4 / 5
Workflow Clarity	Steps 1-5 are clearly sequenced and the auto-fix mode has explicit safety rules plus interactive confirmation, though verification of subagent scan output is only implicit.	4 / 5
Progressive Disclosure	Section structure is solid, but large detail blocks (Detection Patterns, Language Support, Integration Patterns, Advanced Usage) are inlined, and the two referenced files (references/patterns.md, references/severity-guide.md) do not exist in the bundle.	3 / 5
	Total	14 / 20 Passed

Description

83%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 description that clearly states capabilities, gives explicit session-end timing, and lists concrete natural-language triggers. It is slightly held back by the generic 'remediation' wording and a few broad trigger terms that could overlap with adjacent skills.

Dimension	Reasoning	Score
Specificity	Lists several concrete detection actions ('duplicated code, dead imports, security issues, and complexity hotspots') plus 'remediation', but 'remediation' itself is generic, leaving a minor coverage gap.	4 / 5
Completeness	Explicitly answers both 'what' ('Technical debt detection and remediation' with four categories) and 'when' ('Run at session end' plus an explicit 'Triggers:' clause with concrete phrases).	5 / 5
Trigger Term Quality	Seven natural trigger phrases ('find tech debt', 'scan for issues', 'wrap up session', 'before merge', etc.) give good keyword coverage, though common synonyms like 'code smells', 'lint', or 'refactor' are missing.	4 / 5
Distinctiveness Conflict Risk	Clear tech-debt niche with distinct triggers, but broad phrases like 'scan for issues' and 'check code quality' create minor overlap risk with linting or security skills.	4 / 5
	Total	17 / 20 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
Path: data/skills-md/0xdarkmatter/claude-mods/techdebt/SKILL.md
Commit: 2f57aec

Reviewed: about 22 hours 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.