CtrlK
BlogDocsLog inGet started
Tessl Logo

leg-implement-target-nextjs

Implement or incrementally complete a legacy-modernization module in a target Next.js application from a canonical curated feature requirement package and its linked target implementation specification. Use when a reviewed mockup supplies the approved visual UI while curated requirements supply every backend, Oracle, validation, operation, persistence, transaction, error, and security behavior; supports POC generation with explicit known gaps without silently inventing missing behavior.

48

Quality

51%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.codex/skills/leg-implement-target-nextjs/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

48%Scale 1-5

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

This skill is a comprehensive but overly verbose specification for implementing Next.js modules from curated requirements. Its strengths are a well-structured 10-step workflow with clear modes and validation checkpoints, and extremely thorough coverage of edge cases around data mapping, error handling, and mutation scope. Its weaknesses are significant verbosity (many rules are restated in multiple sections), lack of concrete code examples for the implementation patterns it describes, and insufficient progressive disclosure for a document of this length.

Suggestions

Extract detailed behavioral rules (error translation requirements, mutation scope rules, adapter contract details) into separate reference files and link to them from the main workflow steps, reducing the SKILL.md to an overview with clear navigation.

Add concrete, executable code examples for key patterns: a sample API route handler, an error translator implementation skeleton, a repository query pattern, and a test case structure—these would dramatically improve actionability.

Consolidate repeated principles (e.g., 'never use mock values', 'don't guess between packages', domain validation requirements) into a single constraints section or the existing authority-and-conformance.md reference rather than restating them across multiple steps.

Convert dense prose paragraphs (especially in steps 5, 7, and 8) into structured tables or decision matrices that Claude can parse more efficiently.

DimensionReasoningScore

Conciseness

The skill is extremely verbose at ~400+ lines with extensive elaboration on concepts Claude already understands (e.g., explaining what sparse mutations are, how error translators work, what null vs blank vs omitted means). Many sections read like a specification document rather than actionable instructions, with repeated emphasis on the same principles (e.g., 'never use mock values' appears in multiple forms throughout). Significant portions could be condensed to tables or bullet lists without losing meaning.

2 / 5

Actionability

The skill provides detailed behavioral rules and constraints but is light on executable code examples. The few code blocks shown are path templates and a single PowerShell validation command rather than implementation patterns. Most guidance is procedural prose describing what to do conceptually rather than showing concrete code snippets for API routes, database queries, error translators, or test structures that could be directly used.

3 / 5

Workflow Clarity

The 10-step workflow is clearly numbered and sequenced with logical progression from scope resolution through implementation to verification and recording. Step 9 includes explicit validation checkpoints (lint, typecheck, tests, build, browser verification). However, some steps are extremely dense and mix multiple concerns, and the feedback loops for error recovery within steps could be more explicit. The validation script in step 2 is a good checkpoint example.

4 / 5

Progressive Disclosure

The skill references one external file (references/authority-and-conformance.md) which is good progressive disclosure, but the bulk of the content is monolithic. Many sections (error translation rules, mutation scope rules, test verification lists) are deeply detailed inline when they could be split into reference files. No bundle files were provided, so the single reference cannot be verified, and the skill would benefit from splitting detailed behavioral rules into separate reference documents.

3 / 5

Total

12

/

20

Passed

Description

55%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 targets a very specific workflow but suffers from dense, jargon-heavy language that would be difficult for Claude to match against natural user requests. It attempts to be comprehensive by listing many behavior categories but reads more like an internal specification than a discoverable skill description. The 'when' clause exists but functions more as a precondition list than actionable trigger guidance.

Suggestions

Replace jargon like 'canonical curated feature requirement package' with simpler, more natural terms users would actually say, such as 'legacy app migration,' 'modernize to Next.js,' or 'convert legacy system.'

Add explicit trigger terms users would naturally use, e.g., 'Use when the user asks to modernize a legacy application, migrate to Next.js, or implement features from a requirements spec.'

Break the dense single sentence into clearer 'what it does' and 'when to use it' sections, listing 2-3 concrete actions (e.g., 'generates Next.js components from mockups, implements backend logic from requirement specs, creates POC with documented gaps').

DimensionReasoningScore

Specificity

The description names the domain (legacy-modernization in Next.js) and mentions some concrete concepts like 'POC generation' and working from 'curated feature requirement packages,' but the actual actions are vague ('implement or incrementally complete a module'). It lists many behavior categories (Oracle, validation, persistence, etc.) but these read more as a laundry list of concerns than concrete actions the skill performs.

3 / 5

Completeness

The 'what' is present (implement/complete a legacy-modernization module from requirement packages) and the 'when' is partially addressed ('Use when a reviewed mockup supplies the approved visual UI while curated requirements supply every backend...behavior'). However, the 'when' clause is more of a precondition description than explicit trigger guidance, making it less actionable for skill selection.

4 / 5

Trigger Term Quality

The description uses highly specialized jargon ('canonical curated feature requirement package,' 'linked target implementation specification,' 'legacy-modernization module') that users are unlikely to naturally say. Terms like 'Next.js,' 'Oracle,' and 'POC' are somewhat natural but buried in dense technical language. Common user phrases like 'migrate,' 'modernize legacy app,' or 'convert old code' are missing.

2 / 5

Distinctiveness Conflict Risk

The description is quite specific to a particular workflow (legacy modernization from curated requirement packages with mockups), which makes it fairly distinct. However, it could overlap with general Next.js development skills or other code generation skills. The mention of 'canonical curated feature requirement package' is distinctive but overly specialized.

4 / 5

Total

13

/

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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
sibendu/ai_tessl
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.