glasser-research skillA
glasser-research is agent-read markdown (skill) from openclaudia/openclaudia-skills: Use Glasser to retrieve live marketing data through one prepaid account when a task needs SERPs, keyword metrics, ad libraries, community posts, company data, or another external API and no suitable free source or existing integration is available. Prefer the user's own integrations; Glasser fills data gaps and every run has a disclosed cost..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# Glasser Research Use [Glasser](https://glasser.ai) to find and run paid third-party data API endpoints through one account. Glasser provides access and billing; the selected provider supplies the response. Use the provider's name when attributing data. This is a data collection skill. Return its evidence to the marketing skill that needs it, such as `competitor-analysis`, `keyword-research`, `serp-analyzer`, or `google-reviews`. Keep that skill's analysis method and output format. ## Source selection Follow an explicit tool choice from the user. Otherwise use sources in this order: 1. A suitable free tool already available in the agent. 2. A working integration or API key the user already configured. 3. Glasser for the specific remaining data gap. Do not activate Glasser only because an API appears in its catalog. Use it when the task needs live data that the current environment cannot retrieve. A failed search can mean that the topic has no results; distinguish that from missing access before offering a paid fallback. ## Setup Check the CLI and authentication before planning a paid run: ```bash glasser --version glasser balance ``` …
Read the whole file at its exact version.
How to install
mdr add openclaudia/openclaudia-skills/glasser-research@git:20260918.828134cmdr add openclaudia/openclaudia-skills/glasser-research@sha256:be6c16f29c99d759Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_xpm6dzc6fa3ydtp3)
1 badge views in 30 days
Versions
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (7129 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
openclaudia/openclaudia-skills · 700 stars · license MIT · pushed 2026-09-18 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_xpm6dzc6fa3ydtp3 GET https://markdownregistry.com/api/v1/resolve?ref=openclaudia/openclaudia-skills/glasser-research GET https://markdownregistry.com/api/v1/blob/be6c16f29c99d759f29771a407bf6dd4be3508c546c7675ec3d144c7a6cc9dbb
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.