CtrlK
BlogDocsLog inGet started
Tessl Logo

codebase-cleanup-tech-debt

You are a technical debt expert specializing in identifying, quantifying, and prioritizing technical debt in software projects. Analyze the codebase to uncover debt, assess its impact, and create acti

52

Quality

57%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/codebase-cleanup-tech-debt/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%

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

The skill is rich with concrete, actionable templates and a clear high-level sequence, but it is verbose, explains concepts Claude already knows, and bundles everything into one large file with no progressive disclosure. Validation checkpoints are implicit rather than built into the workflow.

Suggestions

Move detailed templates (metrics dashboard, ROI tables, quality-gate configs, refactoring examples) into separate reference files and link to them from SKILL.md to reduce token load and improve progressive disclosure.

Trim definitions of well-known concepts (e.g., what duplicated code or god classes are) and keep only the skill-specific thresholds and quantification guidance.

Add explicit validation/checklist steps within the workflow (e.g., 'confirm metrics are measurable before prioritizing', 'verify ROI inputs with the user') rather than relying on a single Limitations checkpoint.

DimensionReasoningScore

Conciseness

The body is mostly actionable but runs ~395 lines and explains concepts Claude already knows (e.g., defining copy-paste duplication, cyclomatic complexity thresholds, god classes); it could be tightened considerably.

2 / 3

Actionability

It supplies concrete, copy-paste-ready templates — cost calculations (hours x $150/hour), a metrics dashboard YAML, ROI figures, a prioritized roadmap, and quality-gate configs — giving Claude specific, usable scaffolding for an analytical task.

3 / 3

Workflow Clarity

There is a clear eight-step sequence (Inventory -> Impact -> Dashboard -> Plan -> Implementation -> Prevention -> Communication -> Metrics), but validation checkpoints within steps are implicit rather than explicit, and the only checkpoint ('Stop and ask for clarification') lives in the Limitations section.

2 / 3

Progressive Disclosure

The body is well-organized into sections, but it is a monolithic 395-line file with no bundle references; detailed templates and examples that would suit separate reference files are all inline, so it is not a 3.

2 / 3

Total

9

/

12

Passed

Description

50%

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 conveys a clear domain and several concrete actions but is weakened by second-person voice, no 'Use when' trigger clause, and missing common term variations. It answers 'what' but not 'when'.

Suggestions

Rewrite in third person (e.g., 'Identifies, quantifies, and prioritizes technical debt...') to avoid the voice penalty.

Add an explicit 'Use when...' clause with natural triggers such as 'tech debt', 'refactoring backlog', 'legacy code', or 'code quality'.

Include common variations of the term ('tech debt') alongside 'technical debt' to improve trigger coverage.

DimensionReasoningScore

Specificity

The description lists several concrete actions ('identifying, quantifying, and prioritizing technical debt', 'Analyze the codebase to uncover debt, assess its impact, and create actionable...'), which would warrant a 3, but the second-person voice ('You are a technical debt expert') triggers the rubric's one-point specificity penalty.

2 / 3

Completeness

It clearly answers 'what' the skill does, but there is no 'Use when...' clause or equivalent trigger guidance, which the rubric caps at 2 for a missing 'when'.

2 / 3

Trigger Term Quality

'technical debt' and 'codebase' are natural terms a user might say, but common variations like 'tech debt', 'refactoring', 'legacy code', or 'code quality' are missing, so coverage is partial.

2 / 3

Distinctiveness Conflict Risk

'technical debt' is a recognizable niche, but without explicit triggers and with broad phrasing it could overlap with general refactoring or code-review skills.

2 / 3

Total

8

/

12

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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
sickn33/antigravity-awesome-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.