← Back to Skills Marketplace
133
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install sages-stash
Description
Returns a non-R18 image as a "surprise" when users search for NSFW content using specified trigger keywords.
Usage Guidance
This skill is internally inconsistent: it says it will return non-R18 images but its API parameter (r18=1) and ambiguous parsing instructions likely cause it to return explicit images or behave unpredictably. Before installing or enabling it, verify the lolicon API documentation to confirm the correct r18 parameter (use r18=0 for non-R18), fix the JSON field naming (urls.original vs url), and test the exact returned URL in a safe environment. Consider limiting this skill to explicit user invocation only, and be cautious about hotlinking via i.pixiv.re (possible terms-of-service or copyright issues). If you rely on the skill for content-safety, do not trust it until the parameter/logic errors are corrected and outputs are manually inspected.
Capability Assessment
Purpose & Capability
The skill's stated purpose is to return a non-R18 'surprise' image for NSFW queries, but the SKILL.md uses the lolicon API with the query parameter r18=1 (which typically means R18/explicit). That parameter contradicts the declared goal and is disproportionate to the stated purpose. Also the SKILL.md instructs adding an i.pixiv.re prefix for direct access — plausible for pixiv-based images but not justified or documented in the skill metadata.
Instruction Scope
The instructions only call an external API via curl and parse JSON, which is consistent in scope, but they contain clear inconsistencies: an initial line says 'Do NOT parse the output tags. Only return the content inside data[number].url.' while later steps reference data[number].urls.original. More importantly, the r18=1 parameter is described as 'required for filtering' yet the skill intends to return non-R18 images — this mismatch could cause the skill to return exactly the NSFW content it claims to avoid. The skill also instructs rewriting returned URLs to add a CDN prefix, which could change link provenance and has legal/terms-of-service implications.
Install Mechanism
Instruction-only skill with no install spec and no code files; nothing is written to disk. This is low-risk from an install perspective.
Credentials
The skill requests no environment variables, credentials, or config paths. That is proportionate to its simple API-calling function.
Persistence & Privilege
The skill is not always-enabled and is user-invocable only. It does not request elevated persistence or modify other skills or configs.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install sages-stash - After installation, invoke the skill by name or use
/sages-stash - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
sages-stash 1.0.0
- Initial release of sages-stash.
- Responds to NSFW image requests with a random non-R18 image as a "surprise."
- Supports trigger keywords in both Chinese and English related to NSFW content.
- Fetches images from the lolicon.app API, returning direct Pixiv CDN links.
- Ensures all links provided are safe and non-R18.
Metadata
Frequently Asked Questions
What is sages-stash?
Returns a non-R18 image as a "surprise" when users search for NSFW content using specified trigger keywords. It is an AI Agent Skill for Claude Code / OpenClaw, with 133 downloads so far.
How do I install sages-stash?
Run "/install sages-stash" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is sages-stash free?
Yes, sages-stash is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does sages-stash support?
sages-stash is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created sages-stash?
It is built and maintained by ato-z (@ato-z); the current version is v1.0.0.
More Skills