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

62

1.66x
Quality

48%

Does it follow best practices?

Impact

80%

1.66x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/codebase-cleanup-tech-debt/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

38%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 into clear phases with concrete templates, but it is verbose and padded with mock data, lacks validation checkpoints in its workflow, and is entirely monolithic with no progressive disclosure via reference files.

Suggestions

Move the metrics dashboard, stakeholder report, and prevention-gate templates into separate reference files (e.g. references/templates.md) and link to them from SKILL.md.

Replace mock example data (debt_trends, debt_budget) with real, runnable commands for measuring debt (e.g. complexity/duplication tool invocations) to lift actionability.

Add explicit validation checkpoints between phases (e.g. 'confirm the inventory is complete before scoring impact') to raise workflow clarity above 3.

DimensionReasoningScore

Conciseness

The ~380-line body is noticeably padded with mock/example blocks (fake debt_trends dicts, debt_budget objects, sample stakeholder reports) and explains metrics thresholds Claude already knows; several sections could be trimmed without losing instruction.

2 / 5

Actionability

Provides concrete templates (refactoring facade Python, quality-gates YAML, metrics YAML), but key measurement details are mock/placeholder data and it names tools (sonarqube, dependabot, codecov) without giving commands to actually run them.

3 / 5

Workflow Clarity

Eight numbered phases (Inventory, Impact, Metrics, Plan, Implementation, Prevention, Communication, Success Metrics) form a clear sequence, but there are no explicit validation/verification checkpoints or feedback loops in the workflow.

3 / 5

Progressive Disclosure

The skill is monolithic: all content lives in SKILL.md with no references/scripts/assets bundle files, and substantial material (metrics templates, stakeholder report formats, prevention config) that belongs in separate reference files is inlined.

2 / 5

Total

10

/

20

Passed

Description

58%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.

The description states concrete capabilities and occupies a clear niche, but it is written in second person and omits any explicit 'Use when...' trigger guidance, capping completeness and triggering a specificity penalty.

Suggestions

Rewrite in third person and add a 'Use when...' clause, e.g. 'Use when the user asks about technical debt, legacy code, refactoring priorities, or code-quality debt.'

Add natural synonyms users say ('refactoring', 'legacy code', 'code smells') to improve trigger coverage.

Complete the truncated trailing word in the description string so it does not end mid-sentence on 'acti'.

DimensionReasoningScore

Specificity

Lists several concrete actions ("identifying, quantifying, and prioritizing technical debt", "Analyze the codebase to uncover debt, assess its impact, and create actionable remediation plans") approaching comprehensive coverage, but the second-person voice ("You are a technical debt expert") triggers the mandated -1 specificity penalty from a base of 5.

4 / 5

Completeness

Has a clear 'what' (identify, quantify, prioritize, analyze, assess impact, create remediation plans) but no 'when' / "Use when..." trigger clause, which per the guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

Includes the natural term "technical debt" plus "codebase" and "remediation", but lacks common variations/synonyms (e.g. "refactoring", "legacy code", "code smells") that users would naturally say.

3 / 5

Distinctiveness Conflict Risk

"Technical debt analysis and remediation" is a recognizable niche with distinct triggers; minor overlap risk with general refactoring or code-review skills keeps it just below a 5.

4 / 5

Total

14

/

20

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
administrakt0r/AI-Agents-Safe-Coding-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.