Name: senior-fullstack
Rating: 42.559999999999995 (1 reviews)
Author: administrakt0r

Blog Docs Log in Get started

senior-fullstack

Complete toolkit for senior fullstack with modern tools and best practices.

1.00x

Quality

28%

Does it follow best practices?

Impact

78%

1.00x

Average score across 2 eval scenarios

Securityby

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/senior-fullstack/SKILL.md

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

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 well-structured with real, clearly signaled reference and script files, but it is padded with generic best-practice filler and its core scripts are documented only with placeholder flags and no validation workflow. It reads more as a template than executable guidance.

Suggestions

Document the actual CLI flags/options for each script (fullstack_scaffolder.py, project_scaffolder.py, code_quality_analyzer.py) instead of '[options]' placeholders, with at least one complete copy-paste invocation.

Add a validation/feedback loop to the Development Workflow (e.g., run the analyzer, review its output, fix reported issues, re-run until clean) since the scripts perform batch changes.

Cut the generic 'Best Practices Summary' and 'Tech Stack' sections or move them into a reference file, since they restate knowledge Claude already has.

Dimension	Reasoning	Score
Conciseness	The body is noticeably padded with generic best-practice bullets ('Write comprehensive tests', 'Keep it simple', 'Validate all inputs') and vague filler descriptions ('Advanced tooling for specialized tasks') that restate what Claude already knows, matching the score-2 verbose anchor.	2 / 5
Actionability	Core capability invocations show only '[options]', '[arguments]', and '<project-path>' placeholders without the actual flags/arguments, so guidance stays at high-level hints missing the specific steps to execute; the visible commands (npm run dev, docker build) are generic rather than skill-specific.	2 / 5
Workflow Clarity	The three-step Development Workflow is a rough sequence with poorly defined steps ('Apply fixes', 'Implement Best Practices') and no validation checkpoints, and because scaffolding/analysis scripts act as batch/destructive operations the missing feedback loop keeps this at the score-2 level (capped at 3 anyway).	2 / 5
Progressive Disclosure	Bundle files (references/.md, scripts/.py) are real and clearly signaled with paths plus bullet summaries of their contents, and content is split across files with good section structure; it is not a 5 because generic tech-stack and best-practices material is inlined in SKILL.md that could live in references.	4 / 5
	Total	10 / 20 Passed

Description

25%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 generic and buzzword-laden, naming only a broad domain with no concrete actions and no trigger guidance. It would be hard for a user to know when to invoke this skill over many similar ones.

Suggestions

Replace 'toolkit' with 3-5 concrete actions the skill performs (e.g., 'Scaffolds fullstack project structures, analyzes code quality, and documents architecture patterns').

Add an explicit 'Use when...' clause naming natural user phrases (e.g., 'Use when scaffolding a new fullstack project or auditing code quality').

Drop the fluff phrase 'with modern tools and best practices' and replace with specific trigger terms or file extensions users would actually say.

Dimension	Reasoning	Score
Specificity	It names the domain ('senior fullstack') but uses the non-action noun 'toolkit' with no concrete actions described, matching the score-2 anchor of naming a domain with minimal/generic actions.	2 / 5
Completeness	It offers a vague 'what' ('complete toolkit') and entirely omits any 'when'/Use-when guidance, fitting the score-2 anchor of a vague what with no when; it is not a 1 because the domain is at least named.	2 / 5
Trigger Term Quality	'senior fullstack' is domain jargon rather than a phrase users naturally say, and 'modern tools and best practices' is generic fluff with only one or two weak keywords and no natural trigger phrases.	2 / 5
Distinctiveness Conflict Risk	'Senior fullstack' is extremely broad and would overlap with many general development skills, matching the score-2 anchor of very broad with high overlap risk; it is not a 1 because it does narrow to fullstack rather than 'code and documents'.	2 / 5
	Total	8 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/senior-fullstack/SKILL.md
Commit: 57c135b

Reviewed: 24 hours ago

Table of Contents

Discovery Implementation Validation

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.