CtrlK
BlogDocsLog inGet started
Tessl Logo

tech-debt-radar

Proactive architectural review skill using Frontier Model semantic RAG to sweep historical issues and Memory Core sessions for technical debt. Triggers: Use this skill when conducting architectural analysis, proactively searching for technical debt, auditing the repository for abandoned logical loops, when explicitly requested to scan for ambient architectural debt, or during PR review for fundamental architectural shifts.

71

Quality

86%

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

SKILL.md
Quality
Evals
Security

Quality

Content

90%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 an extremely concise, well-disclosed pointer to a single verified reference file, providing executable guidance for a simple delegating skill. Its only gap is the absence of explicit validation feedback loops, which matters less for a read-and-adhere workflow.

Suggestions

Add a brief one-line note on how to confirm the guide was followed (e.g., a checkpoint that the reference's checklist was completed) to strengthen workflow clarity.

Consider a short section header so the delegation stands out structurally rather than as a single unstructured sentence.

DimensionReasoningScore

Conciseness

A single lean sentence delegates to the reference guide with no over-explanation of concepts Claude already knows; every token earns its place.

5 / 5

Actionability

Gives a concrete, executable instruction — invoke the `view_file` tool on a specific path — covering the common case directly.

5 / 5

Workflow Clarity

The single action ('read the guide before proceeding') is unambiguous and sequenced, but as a delegating skill it lacks explicit validation checkpoints; this sits just below a 5.

4 / 5

Progressive Disclosure

Points to one real one-level-deep reference (tech-debt-radar-guide.md, verified present in ./references/) with a clear signal, though the body itself has no section structure.

4 / 5

Total

18

/

20

Passed

Description

83%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 is strong: it pairs a clear capability statement with an explicit, multi-phrase trigger clause covering both proactive and PR-review scenarios. It is concise and avoids fluff while remaining distinctive.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions ('sweep historical issues', 'mine the Memory Core', 'auditing the repository for abandoned logical loops'), with only minor jargon-heavy phrasing preventing full comprehensiveness.

4 / 5

Completeness

Clearly states both what the skill does ('architectural review skill ... to sweep ... for technical debt') and when to use it via concrete trigger phrases, fully satisfying the what-and-when requirement.

5 / 5

Trigger Term Quality

The explicit 'Triggers:' clause includes several natural user phrases ('architectural analysis', 'searching for technical debt', 'PR review'), though a few common synonyms are missing.

4 / 5

Distinctiveness Conflict Risk

The niche architectural-debt scope with distinct triggers is largely distinguishable from sibling skills, with only minor overlap risk against general code-review skills.

4 / 5

Total

17

/

20

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
neomjs/neo
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.