CtrlK
BlogDocsLog inGet started
Tessl Logo

code-refactoring-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

44

Quality

45%

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 ./.agent/skills/code-refactoring-tech-debt/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

32%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 a lean overview that correctly delegates detail to sub-modules, but the actual instructions are empty and every referenced sub-skill file is missing, leaving no executable guidance. It reads as an incomplete skeleton rather than a working skill.

Suggestions

Populate the empty "## Instructions" section with concrete, executable steps for conducting technical debt analysis (e.g., specific commands, metrics to collect, analysis commands), or inline a quick-start example.

Provide the eight referenced ./sub-skills/*.md files so the progressive-disclosure links resolve; until they exist, inline the most critical guidance directly in SKILL.md.

Add validation checkpoints to the workflow (e.g., confirm debt items are measurable, verify remediation ROI before prioritizing) so the multi-step process has explicit feedback loops.

DimensionReasoningScore

Conciseness

Mostly efficient with no concept over-explanation, but it repeats the frontmatter description verbatim and carries generic "Use this skill when / Do not use this skill when" boilerplate that could be tightened, matching the mostly-efficient-with-some-unnecessary-content anchor.

3 / 5

Actionability

The "## Instructions" section is empty and the only guidance is a list of eight module links, all of which point to non-existent files; there is high-level structure but no specific executable steps, matching the minimal-guidance anchor.

2 / 5

Workflow Clarity

The eight modules imply a rough sequence (inventory → impact → metrics → plan → implementation → prevention → communication → success metrics), but steps are poorly defined, validation checkpoints are absent, and the linked files do not exist, matching the rough-sequence-many-gaps anchor.

2 / 5

Progressive Disclosure

References are one level deep and cleanly signaled as a numbered list, but all eight referenced ./sub-skills/*.md files are absent from the bundle, so the disclosure structure is broken and navigation dead-ends, falling below the well-organized anchors.

2 / 5

Total

9

/

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 a clear, specific set of capabilities for technical debt analysis but omits any explicit "Use when..." trigger guidance, capping completeness at 3, and uses second-person voice which lowers specificity. It is a distinct niche with minor overlap risk.

Suggestions

Add an explicit 'Use when...' clause with concrete user trigger phrases (e.g., 'Use when the user mentions technical debt, tech debt, code quality, refactoring backlog, or maintenance burden').

Convert to third-person voice ('Identifies, quantifies, and prioritizes technical debt...') to recover the specificity penalty and match skill-description conventions.

Add natural synonyms and file/term variants (tech debt, refactoring, code smell) to improve trigger-term coverage.

DimensionReasoningScore

Specificity

Names multiple concrete actions ("identifying, quantifying, and prioritizing technical debt", "Analyze the codebase to uncover debt, assess its impact, and create acti[onable remediation plans]"), which would be a 5, but second-person voice ("You are a technical debt expert") triggers the −1 specificity penalty.

4 / 5

Completeness

The "what" is clearly stated (identify, quantify, prioritize, assess, remediate), but there is no "Use when..." clause or equivalent trigger guidance, so per the guideline completeness is capped at 3.

3 / 5

Trigger Term Quality

Relevant keywords ("technical debt", "codebase", "debt", "remediation") are present but common variants users say ("tech debt", "refactoring", "code quality", "maintenance") are missing, matching the anchor with some keywords but missing synonyms.

3 / 5

Distinctiveness Conflict Risk

"Technical debt" is a distinct niche with clear triggers; only minor overlap risk with closely related refactoring or code-review skills, matching the mostly-distinct anchor.

4 / 5

Total

14

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

relative_links

Relative link issues: 8 missing

Warning

Total

14

/

16

Passed

Repository
Dokhacgiakhoa/Agent-Skills-4-Vibe-Coding-CLI
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.