Content Quality Pipeline
PassAudited by ClawScan on May 1, 2026.
Overview
The skill is a transparent humantext.pro integration, with normal cautions about an external MCP package, API key, third-party text processing, and paid word credits.
This skill appears coherent and purpose-aligned. Before installing, verify the @humantext/mcp-server npm package, protect your HUMANTEXT_API_KEY, and be comfortable with sending text to humantext.pro and spending word credits when humanization runs.
Findings (4)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Installing or using the skill may execute the current npm package for the humantext MCP server.
The skill asks users to run an external npm MCP server through npx, which is expected for this service but means the runtime code comes from outside the reviewed artifacts and is not version-pinned here.
"command": "npx", "args": ["-y", "@humantext/mcp-server"]
Verify the npm package and publisher before use, and consider pinning a trusted version in the MCP configuration.
Anyone with access to the configured API key could use the associated humantext.pro account allowance.
The integration requires a provider API key in the MCP server environment, which is normal for this service but gives the tool access to the user's humantext.pro account credits.
"HUMANTEXT_API_KEY": "htpro_your_key_here"
Store the API key securely, avoid committing MCP config files with real keys, and rotate the key if it is exposed.
Text provided to the skill may be sent to humantext.pro for analysis or rewriting.
The skill's core tools process the submitted or generated text through an external MCP/provider boundary, which is disclosed and purpose-aligned.
You use the humantext.pro MCP tools for detection and humanization.
Do not submit confidential, regulated, or proprietary text unless you are comfortable with the provider's terms and data handling.
Using the workflow can spend humantext.pro word credits, especially for longer or repeated content.
The workflow may invoke a credit-consuming tool based on a detector threshold; this is disclosed and central to the skill, with extra balance checks for long text.
If the AI score is above 30% (or user requests it), use `humanize_text`... Humanization uses word credits.
Confirm expected credit usage before processing large batches or any text where spending credits would be undesirable.