tech-debt

Track, categorize, and prioritize technical debt across the codebase. Scans for debt indicators, maintains a debt register, and recommends repayment scheduling.

Quality

58%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/tech-debt/SKILL.md

Quality

Content

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill body is well-structured into clear phases with explicit verdicts and confirmation gates, giving Claude an actionable workflow. It is held back by a duplicated category taxonomy, detection steps described without executable commands, and a missing validation loop on the destructive prioritize-mode rewrite.

Suggestions

Define the six debt categories once and reference that definition from both Scan and Add modes to remove the verbatim duplication.

Provide concrete search commands for the Scan step (e.g. grep/ripgrep patterns for TODO/FIXME/HACK/@deprecated and a line-count threshold) instead of describing indicators in the abstract.

Add a validation step after the prioritize-mode rewrite — re-read docs/tech-debt-register.md and confirm every original entry is present and the table still parses — before reporting COMPLETE.

Dimension	Reasoning	Score
Conciseness	The body is lean and avoids explaining concepts Claude already knows, but the six-category taxonomy is duplicated verbatim between the Scan categorization list and the Add-mode AskUserQuestion options, which could be tightened into a single shared definition.	2 / 3
Actionability	Concrete elements are present (explicit thresholds like 'over 500 lines', a priority formula, a copy-paste register table, and AskUserQuestion option sets), but detection steps like 'duplicated code blocks' and 'god objects' are described rather than given as executable grep/search commands, leaving guidance incomplete.	2 / 3
Workflow Clarity	Phases are clearly sequenced with explicit Verdict checkpoints and user-confirmation gates before writes, but the prioritize mode performs a batch overwrite of the register with no validation that the file was written correctly or that the format was preserved, capping workflow clarity at 2 for a destructive/batch operation.	2 / 3
Progressive Disclosure	The single-file skill has clear phase-based headers and no nested references, but all content is inline and the 'Debt Register Format' and 'Rules' sections are awkwardly nested under 'Phase 3: Next Steps', so organization could be improved.	2 / 3
	Total	8 / 12 Passed

Description

67%

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 and distinctive, naming several concrete actions and staking out a clear niche. Its main weakness is the missing explicit 'when to use' trigger guidance and limited coverage of natural trigger-term variations.

Suggestions

Add a 'Use when...' clause naming explicit triggers, e.g. 'Use when the user mentions technical debt, tech debt, code smells, or wants to triage a refactoring backlog.'

Expand trigger terms to include common phrasings like 'tech debt', 'code smells', and 'refactoring backlog' alongside 'technical debt'.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Track, categorize, and prioritize', 'Scans for debt indicators', 'maintains a debt register', 'recommends repayment scheduling' — matching the multi-action anchor.	3 / 3
Completeness	Clearly answers what the skill does, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 2 per the guidelines.	2 / 3
Trigger Term Quality	Contains the dominant natural term 'technical debt' but misses common variations a user might say such as 'tech debt', 'code smells', 'refactoring backlog', or 'TODO/FIXME cleanup'.	2 / 3
Distinctiveness Conflict Risk	'Technical debt across the codebase' is a clear niche with distinct triggers and is unlikely to fire for unrelated skills.	3 / 3
	Total	10 / 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: Donchitos/Claude-Code-Game-Studios
Path: .claude/skills/tech-debt/SKILL.md
Commit: 984023d

Reviewed: 3 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.