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.
66
52%
Does it follow best practices?
Impact
87%
1.35xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./data/skills-md/0xdarkmatter/claude-mods/techdebt/SKILL.mdQuality
Discovery
92%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong description that clearly communicates specific capabilities (duplicated code, dead imports, security issues, complexity hotspots) and provides extensive explicit trigger terms covering multiple user scenarios. The main weakness is potential overlap with other code quality or security-focused skills due to the breadth of its scope, but the combination of triggers and the session-end timing context help mitigate this.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'find duplicated code, dead imports, security issues, and complexity hotspots.' Also mentions parallel subagents for fast analysis, adding implementation detail. | 3 / 3 |
Completeness | Clearly answers both 'what' (technical debt detection and remediation—duplicated code, dead imports, security issues, complexity hotspots) and 'when' (session end, before merge, code review prep, with explicit trigger phrases listed). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would actually say: 'find tech debt', 'scan for issues', 'check code quality', 'wrap up session', 'ready to commit', 'before merge', 'code review prep'. These cover multiple natural phrasings and contexts. | 3 / 3 |
Distinctiveness Conflict Risk | While the specific triggers like 'find tech debt' and 'complexity hotspots' are fairly distinctive, terms like 'check code quality', 'code review prep', and 'scan for issues' could overlap with linting skills, security scanning skills, or general code review skills. The scope is broad enough to potentially conflict with more focused tools. | 2 / 3 |
Total | 11 / 12 Passed |
Implementation
12%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads as an aspirational design document rather than actionable instructions for Claude. It's extremely verbose (~350+ lines) with fictional CLI commands, placeholder templates, and extensive content Claude already knows (what SQL injection is, how CI/CD works). The core problem is that it describes a system rather than teaching Claude how to execute one—there's no actual implementation of the parallel subagent spawning, analysis logic, or report generation.
Suggestions
Replace fictional '/techdebt' slash commands with actual executable instructions showing how Claude should spawn subagents, what tools to call, and how to consolidate results—the skill needs real implementation, not a product spec.
Cut content by 60-70%: remove the architecture benefits list, language support tiers, CI/CD integration examples, baseline tracking, custom patterns, troubleshooting, and best practices—these are either Claude's existing knowledge or aspirational features.
Move detection patterns, security checks, and complexity thresholds into separate referenced bundle files (e.g., references/patterns.md) and keep SKILL.md as a concise orchestration guide.
Add concrete validation steps: what should Claude check after subagents return results? How should it handle subagent failures or empty results? Include explicit error recovery flows.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~350+ lines. Contains extensive explanatory content Claude doesn't need (architecture diagrams with emoji, benefits lists, detailed explanations of what each scanner does). The detection patterns section, language support tiers, integration patterns (CI/CD YAML, pre-commit hooks), baseline tracking, custom patterns, troubleshooting, and best practices sections massively inflate token count. Much of this is general knowledge Claude already possesses or aspirational features (slash commands, --flags) that don't correspond to real executable functionality. | 1 / 3 |
Actionability | Despite appearing detailed, the skill lacks truly executable guidance. The '/techdebt' commands are fictional slash commands with no implementation. The subagent instructions are templates with placeholders rather than concrete, copy-paste-ready code. There's no actual code showing how to spawn subagents, perform AST analysis, or consolidate results—it's a design document describing what should happen rather than instructing Claude how to do it. | 1 / 3 |
Workflow Clarity | The 5-step workflow is clearly sequenced and logically ordered (determine scope → spawn subagents → consolidate → report → optional fix). The auto-fix section includes safety rules which serve as validation constraints. However, there are no real validation checkpoints for the scanning process itself—no feedback loops for when subagents fail, return inconsistent results, or when tools are unavailable beyond a brief troubleshooting section. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of text with everything inline. References to 'references/patterns.md' and 'references/severity-guide.md' are listed at the bottom but no bundle files exist. The detection patterns, language support, integration patterns, advanced usage, and troubleshooting sections should all be in separate referenced files. The skill tries to be both an overview and a comprehensive reference simultaneously. | 1 / 3 |
Total | 5 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- NeverSight/skills_feed
- Commit
3ae408c
- 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.