CtrlK
BlogDocsLog inGet started
Tessl Logo

giuseppe-trisciuoglio/developer-kit

Comprehensive developer toolkit providing reusable skills for Java/Spring Boot, TypeScript/NestJS/React/Next.js, Python, PHP, AWS CloudFormation, AI/RAG, DevOps, and more.

89

Quality

89%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

SecuritybySnyk

Risky

Do not use without reviewing

Overview
Quality
Evals
Security
Files

Quality

Discovery

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is a strong skill description that clearly identifies the tool, lists concrete capabilities, provides explicit 'Use when' guidance, and enumerates specific trigger terms. It is well-scoped to a distinct product (Google NotebookLM), minimizing conflict risk. The description is comprehensive without being overly verbose.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions: querying project documentation, managing research notebooks and sources, retrieving AI-synthesized information, generating audio podcasts or reports, and performing contextual queries against curated knowledge bases.

3 / 3

Completeness

Clearly answers both 'what' (interaction with Google NotebookLM for RAG capabilities, querying docs, managing notebooks, generating podcasts/reports) and 'when' (explicit 'Use when...' clause with multiple trigger scenarios plus a 'Triggers on' list).

3 / 3

Trigger Term Quality

Includes explicit trigger terms ('notebooklm', 'nlm', 'notebook query', 'research notebook', 'query documentation in notebooklm') as well as natural phrases like 'RAG', 'knowledge bases', and 'research notebooks' that users would plausibly say.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive due to the specific product name 'Google NotebookLM', the tool name 'notebooklm-mcp-cli', and niche triggers like 'nlm' and 'notebook query'. Unlikely to conflict with generic documentation or RAG skills.

3 / 3

Total

12

/

12

Passed

Implementation

77%

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

This is a strong, highly actionable skill with excellent executable examples and clear workflow sequencing including validation checkpoints and security guardrails. Its main weakness is length — the document tries to be both a quick-start guide and a comprehensive reference in one file, leading to moderate verbosity. Some metadata-level content (trigger phrases, 'When to Use' lists) adds bulk without instructional value.

Suggestions

Move the detailed command references (source management, studio content, research, downloads) into a separate REFERENCE.md file, keeping only the most common operations (query, create notebook, add source) in the main skill.

Remove the 'When to Use' and 'Trigger phrases' sections — these are metadata concerns that belong in frontmatter, not in the instructional body.

DimensionReasoningScore

Conciseness

The skill is fairly comprehensive but includes some unnecessary sections like 'When to Use' with trigger phrases (metadata-level info that doesn't belong in the body), and the 'Overview' paragraph restates what the heading already conveys. The 'Best Practices' and 'Constraints and Warnings' sections have some overlap with inline warnings. However, the command examples themselves are lean and well-structured.

2 / 3

Actionability

The skill provides fully executable, copy-paste-ready CLI commands for every operation. Each command includes concrete flags, arguments, and expected output examples. The examples section shows realistic end-to-end workflows with actual command sequences and sample outputs.

3 / 3

Workflow Clarity

The skill has a clear 4-step workflow (verify → identify notebook → perform operation → present results) with explicit validation checkpoints: checking authentication before operations, using --wait for source processing, polling for completion of long-running tasks, and requiring user confirmation before acting on results. The feedback loop for expired authentication is clearly specified.

3 / 3

Progressive Disclosure

The content is well-organized with clear section headers and logical grouping, but it's quite long (~250+ lines) and could benefit from splitting detailed command references (source management, studio content, research) into separate reference files. Everything is inline in a single document, making it a somewhat monolithic reference despite good internal structure.

2 / 3

Total

10

/

12

Passed

Validation

90%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

10

/

11

Passed

Reviewed

Table of Contents