clawdirect-dev

Build agent-facing web experiences with ATXP-based authentication, following the ClawDirect pattern. Use this skill when building websites that AI agents interact with via MCP tools, implementing cookie-based agent auth, or creating agent skills for web apps. Provides templates using @longrun/turtle, Express, SQLite, and ATXP.

Quality

85%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Risky

Do not use without reviewing

Quality

Content

85%

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, actionable skill with complete, executable code examples and clear workflow progression. The main weakness is some verbosity in explanatory sections (ATXP explanation, deployment platform list) that Claude doesn't need. The architecture diagram, while helpful for humans, adds tokens without adding actionable information for Claude.

Suggestions

Remove or significantly condense the 'What is ATXP?' section - link to the ATXP skill instead of explaining it

Remove the deployment platform list - Claude knows common Node.js hosting options; just mention 'any Node.js hosting with persistent storage'

Dimension	Reasoning	Score
Conciseness	The skill is fairly efficient but includes some unnecessary explanations (e.g., 'What is ATXP?' section explaining concepts, deployment platform listings). The architecture diagram and some explanatory text could be trimmed since Claude can infer these patterns.	2 / 3
Actionability	Excellent executable code throughout - complete TypeScript files for db.ts, tools.ts, api.ts, and index.ts are copy-paste ready. Commands are specific with exact npm packages, and the skill template is fully formed.	3 / 3
Workflow Clarity	Clear 6-step build process with explicit sequencing. Each step builds on the previous with concrete file creation. The cookie bootstrap flow includes validation (checking cookie existence, verifying against database) and clear error handling paths.	3 / 3
Progressive Disclosure	Well-organized with clear sections progressing from overview to implementation to deployment. External references are one level deep and clearly signaled (GitHub repo, ATXP skill link). Content is appropriately split between quick understanding and detailed implementation.	3 / 3
	Total	11 / 12 Passed

Description

85%

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 well-structured description that clearly defines both capabilities and usage triggers. The main weakness is reliance on specialized terminology (ATXP, ClawDirect, @longrun/turtle) that may not match natural user queries, though this specificity also makes it highly distinctive within its niche.

Suggestions

Add more natural trigger terms users might say, such as 'agent authentication', 'AI web interface', 'automated browser auth', or 'headless agent access'

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: 'Build agent-facing web experiences', 'ATXP-based authentication', 'following the ClawDirect pattern', and specifies the tech stack (Express, SQLite, ATXP, @longrun/turtle).	3 / 3
Completeness	Clearly answers both what ('Build agent-facing web experiences with ATXP-based authentication') and when ('Use this skill when building websites that AI agents interact with via MCP tools, implementing cookie-based agent auth, or creating agent skills for web apps').	3 / 3
Trigger Term Quality	Includes some relevant terms like 'agent auth', 'MCP tools', 'web apps', 'agent skills', but uses specialized jargon (ATXP, ClawDirect, @longrun/turtle) that users may not naturally say. Missing common variations like 'agent authentication', 'AI web interface'.	2 / 3
Distinctiveness Conflict Risk	Highly distinctive with specific niche: ATXP authentication, ClawDirect pattern, agent-facing web experiences. The combination of MCP tools, cookie-based agent auth, and specific tech stack makes it unlikely to conflict with generic web development skills.	3 / 3
	Total	11 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (501 lines); consider splitting into references/ and linking	Warning

	Total	10 / 11 Passed

Repository: napoleond/clawdirect
Commit: b645ffd

Reviewed: 4 months 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.