Geepers Corpus

Query the COCA (Corpus of Contemporary American English) linguistics API for word frequency, collocations, concordances, and historical usage trends. Use for...

Security Scan

The skill claims to query the COCA corpus but its SKILL.md points to an unverified third‑party API, uses inconsistent naming, and asks for an API key that the registry metadata does not declare — these mismatches merit caution.

Purpose & Capability

The skill description says it queries COCA, but the runtime instructions name the service 'Dreamer Corpus' and point to https://api.dr.eamer.dev (not an official COCA/english‑corpora host). The package metadata (name 'Geepers Corpus') doesn't match the SKILL.md branding. The lack of source/homepage makes it impossible to verify that this endpoint legitimately provides COCA data.

Instruction Scope

SKILL.md instructs the agent to call external endpoints and to set DREAMER_API_KEY. It does not request local file access, which is appropriate, but the instructions direct all queries to an unverified external host and ask the agent to use an API key (not declared in registry). There is nothing in the document indicating why a third‑party host is necessary or whether user queries or results are logged/shared beyond the API.

Install Mechanism

Instruction‑only skill with no install spec and no code files — nothing will be written to disk by an installer. This is a low install risk.

Credentials

The registry metadata lists no required environment variables, but SKILL.md instructs users to export DREAMER_API_KEY for authentication. That mismatch is a red flag: the skill will expect a secret not declared in its manifest, and the origin/scope of that credential is unclear.

Persistence & Privilege

always is false and there are no indications the skill requests persistent system privileges or modifies other skills/config. Autonomous invocation is allowed by platform default; that combined with the other concerns increases risk but is not by itself unusual.

What to consider before installing

Do not install or use this skill until the developer clears up the inconsistencies. Ask for: (1) the canonical API provider and official docs proving access to COCA (an authoritative domain or project page), (2) why the registry lists no required env vars while SKILL.md requires DREAMER_API_KEY, and (3) a source/homepage or repo so you can inspect who runs api.dr.eamer.dev. Treat any queries you send to the service as potentially logged by an unknown third party; avoid sending sensitive text. If you cannot verify the API's legitimacy, prefer a skill backed by a known provider or one that documents its data provenance and credentials in the manifest.

Dreamer Corpus

Access the COCA corpus API at https://api.dr.eamer.dev.

COCA contains 1+ billion words of contemporary American English from spoken, fiction, magazine, newspaper, and academic sources.

Authentication

export DREAMER_API_KEY=your_key_here

Endpoints

Word Search / Concordance

GET https://api.dr.eamer.dev/v1/corpus/search?word=serendipity&limit=20

Returns KWIC (keyword-in-context) examples showing the word in actual usage.

Collocations

GET https://api.dr.eamer.dev/v1/corpus/collocations?word=run&pos=verb&limit=20

Returns words that statistically co-occur with the target word (MI score, frequency).

Frequency

GET https://api.dr.eamer.dev/v1/corpus/frequency?word=algorithm&genre=academic

Returns frequency per million words, with optional genre filter: spoken, fiction, magazine, newspaper, academic.

When to Use

• Checking how formal or common a word is in real American English
• Finding natural collocations for writing assistance
• Linguistic research on word usage patterns
• Historical frequency trends across decades

Don't Use When

• You need non-English corpora
• You need corpora other than contemporary American English (COCA is 1990-present)