How do I install the Moleresearch skill?

Run npx skillmds@latest add ucsandman/moleresearch in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Moleresearch safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Moleresearch?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Moleresearch free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Moleresearch?

ucsandman (@ucsandman) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Moleresearch by ucsandman — Agent Skill

Name: Moleresearch
Author: ucsandman

File contents

moleresearch

Generated by declick from mcp:C:/Users/sandm/.local/bin/mole-mcp.exe. Deterministic, no screenshots, JSON by default when piped.

moleresearch (mcp)  source: mcp:C:/Users/sandm/.local/bin/mole-mcp.exe  server: C:/Users/sandm/.local/bin/mole-mcp.exe
  mole-aggregate <session-id>         Ask a question of the user's local data. [mutating]
  mole-citations <session-id>         Numbered sources for the claims in this session, so prose can cite [1], [2] and [mutating]
  mole-claim-add <session-id>         Record a claim with the quote that supports it. [mutating]
  mole-claims-list <session-id>       List the claims recorded in this session, with their sources and quotes. [mutating]
  mole-connect-list                   List the local files the user registered with 'mole connect', with their tables [mutating]
  mole-dataset <session-id>           The finished table: rows recorded across every document in the session, merged b [mutating]
  mole-edge-add <session-id>          Record how two claims relate: contradicts, duplicate_of, or neither. [mutating]
  mole-fetch <session-id>             Fetch a URL and return its extracted text, through mole's SSRF guard, robots han [mutating]
  mole-pairs-candidates <session-id>  Claim pairs worth comparing, retrieved by lexical similarity — no model call, an [mutating]
  mole-rows-add <session-id>          Record dataset rows read from one document. [mutating]
  mole-search <session-id>            Search the web through the configured provider, with mole's rate limiting. [mutating]
  mole-session-close <session-id>     Close a session and report what it collected: documents fetched, claims recorded [mutating]
  mole-session-open <question>        Open a research session. [mutating]
  ... 7 more verbs (20 total): declick describe moleresearch --grep <text> | --offset N --limit N | --verb v
common: --json --fields --limit --rows --where --dry-run --full   exit: 0 ok 1 err 2 missing 3 blocked 4 auth

Examples (replace UPPERCASE tokens with real values; 'declick describe moleresearch --verb ' prints one verb's flags and what it returns):

moleresearch mole-aggregate SESSION_ID --session-id SESSION_ID --connector CONNECTOR --table TABLE --template TEMPLATE --columns COLUMNS --dry-run
moleresearch mole-citations SESSION_ID --session-id SESSION_ID --dry-run
moleresearch mole-claim-add SESSION_ID --session-id SESSION_ID --doc-id DOC_ID --text TEXT --quote QUOTE --dry-run

If 'moleresearch' is not on PATH, run every command as: declick run moleresearch ... (same output, same exit codes). Every verb: --json (default when piped) --fields a,b --limit N; mutating verbs accept --dry-run. Success: {"ok":true,"data":...,"meta":{"count":N,"truncated":false}}. Failure: {"ok":false,"error":"...","exit":N}. Exit 2 means the verb is not in the server tools list, 3 blocked by governance. Every verb starts mcp:C:/Users/sandm/.local/bin/mole-mcp.exe, calls one tool and exits, so the server does not have to be running first.

---name: moleresearchdescription: Use when you need to ask a question of the user's local data or other moleresearch operations from the shell. Run 'moleresearch describe' first.---# moleresearchGenerated by declick from mcp:C:/Users/sandm/.local/bin/mole-mcp.exe. Deterministic, no screenshots, JSON by default when piped.```moleresearch (mcp) source: mcp:C:/Users/sandm/.local/bin/mole-mcp.exe server: C:/Users/sandm/.local/bin/mole-mcp.exe mole-aggregate <session-id> Ask a question of the user's local data. [mutating] mole-citations <session-id> Numbered sources for the claims in this session, so prose can cite [1], [2] and [mutating] mole-claim-add <session-id> Record a claim with the quote that supports it. [mutating] mole-claims-list <session-id> List the claims recorded in this session, with their sources and quotes. [mutating] mole-connect-list List the local files the user registered with 'mole connect', with their tables [mutating] mole-dataset <session-id> The finished table: rows recorded across every document in the session, merged b [mutating] mole-edge-add <session-id> Record how two claims relate: contradicts, duplicate_of, or neither. [mutating] mole-fetch <session-id> Fetch a URL and return its extracted text, through mole's SSRF guard, robots han [mutating] mole-pairs-candidates <session-id> Claim pairs worth comparing, retrieved by lexical similarity — no model call, an [mutating] mole-rows-add <session-id> Record dataset rows read from one document. [mutating] mole-search <session-id> Search the web through the configured provider, with mole's rate limiting. [mutating] mole-session-close <session-id> Close a session and report what it collected: documents fetched, claims recorded [mutating] mole-session-open <question> Open a research session. [mutating] ... 7 more verbs (20 total): declick describe moleresearch --grep <text> | --offset N --limit N | --verb vcommon: --json --fields --limit --rows --where --dry-run --full exit: 0 ok 1 err 2 missing 3 blocked 4 auth```Examples (replace UPPERCASE tokens with real values; 'declick describe moleresearch --verb <verb>' prints one verb's flags and what it returns):```moleresearch mole-aggregate SESSION_ID --session-id SESSION_ID --connector CONNECTOR --table TABLE --template TEMPLATE --columns COLUMNS --dry-runmoleresearch mole-citations SESSION_ID --session-id SESSION_ID --dry-runmoleresearch mole-claim-add SESSION_ID --session-id SESSION_ID --doc-id DOC_ID --text TEXT --quote QUOTE --dry-run```If 'moleresearch' is not on PATH, run every command as: declick run moleresearch <verb> ... (same output, same exit codes).Every verb: --json (default when piped) --fields a,b --limit N; mutating verbs accept --dry-run. Success: {"ok":true,"data":...,"meta":{"count":N,"truncated":false}}. Failure: {"ok":false,"error":"...","exit":N}.Exit 2 means the verb is not in the server tools list, 3 blocked by governance. Every verb starts mcp:C:/Users/sandm/.local/bin/mole-mcp.exe, calls one tool and exits, so the server does not have to be running first.

Frequently asked questions

Moleresearch