CtrlK
BlogDocsLog inGet started
Tessl Logo

nestjs-expert

You are an expert in Nest.js with deep knowledge of enterprise-grade Node.js application architecture, dependency injection patterns, decorators, middleware, guards, interceptors, pipes, testing strategies, database integration, and authentication systems.

49

Quality

54%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/nestjs-expert/SKILL.md

The canonical home for this skill is nestjs-expert in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

52%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 content is rich and largely actionable with concrete commands and real issue references, but it suffers from significant verbosity and a monolithic structure that rehashes Nest.js basics instead of using progressive disclosure. Splitting reference material into separate files and trimming redundant explanation would substantially improve it.

Suggestions

Move the Problem-Specific Approaches, Common Patterns, Decision Trees, and Quick Reference sections into separate reference files (e.g. PROBLEMS.md, PATTERNS.md) and link them one level deep from a concise overview, lifting progressive_disclosure above 2.

Delete or condense the Domain Coverage and Decision Trees sections that restate Nest.js fundamentals Claude already knows, to reduce token bloat and raise conciseness above 2.

Complete the stubbed code examples (e.g. the Exception Filter 'Custom error handling' placeholder) with executable bodies, and add explicit validate→fix→retry feedback loops around the detection and validation steps to push workflow_clarity toward 5.

DimensionReasoningScore

Conciseness

The ~550-line body is noticeably verbose: the Domain Coverage, Decision Trees, Common Patterns, Performance Optimization, and Quick Reference sections restate Nest.js fundamentals Claude already knows and overlap with each other, though the problem-specific approaches with real issue references add genuine value.

2 / 5

Actionability

It provides concrete, mostly-executable guidance including grep/test/find detection commands, npm validation commands, and TypeScript code patterns for modules, decorators, testing, and filters, with only minor gaps such as the exception filter 'Custom error handling' placeholder.

4 / 5

Workflow Clarity

The 'When invoked' section gives a clear numbered sequence (detect → identify → apply → validate) with an explicit validation order (typecheck → unit → integration → e2e) and a routing step, though error-recovery feedback loops are only lightly emphasized.

4 / 5

Progressive Disclosure

No bundle files exist and all content lives in a single monolithic SKILL.md; large reference blocks (problem-specific approaches, common patterns, decision trees, external resources) that clearly belong in separate files are inlined rather than split with one-level-deep references.

2 / 5

Total

12

/

20

Passed

Description

56%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 establishes a clear Nest.js niche with strong keyword coverage, but is written in second person and omits any 'Use when...' trigger clause, capping completeness and reducing specificity. Adding explicit invocation triggers and rephrasing in third person would materially raise the score.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers, e.g. 'Use when debugging Nest.js dependency injection, module boundaries, guards, or TypeORM/Mongoose integration issues.'

Rephrase to third person ('Provides expertise in Nest.js...') instead of second person ('You are an expert...') to satisfy the voice guideline and recover the specificity penalty.

Convert 'deep knowledge of' framings into concrete actions (e.g. 'Diagnoses circular dependencies, configures Passport JWT strategies, sets up TypeORM repositories') to lift specificity above 2.

DimensionReasoningScore

Specificity

The description names the Nest.js domain and enumerates many specific subsystems (DI, decorators, middleware, guards, interceptors, pipes, testing, DB, auth), but frames them as 'deep knowledge of' rather than concrete actions, and the second-person 'You are an expert' voice triggers a -1 specificity penalty per the rubric guidelines.

2 / 5

Completeness

It clearly answers the 'what' (an expert in Nest.js covering listed subsystems) but provides no 'Use when...' clause or equivalent explicit trigger guidance, so completeness is capped at 3 per the rubric guideline.

3 / 5

Trigger Term Quality

Good natural keyword coverage including 'Nest.js', 'decorators', 'guards', 'interceptors', 'pipes', 'testing', and 'authentication' that users debugging the framework would say, though a few synonyms and variant spellings are missing.

4 / 5

Distinctiveness Conflict Risk

Nest.js is a specific framework niche with distinct triggers, but the breadth over Node.js architecture, testing, and database integration creates minor overlap risk with nodejs-expert and database-expert (which the skill itself routes to).

4 / 5

Total

13

/

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.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (557 lines); consider splitting into references/ and linking

Warning

frontmatter_unknown_keys

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

Warning

Total

14

/

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.