agentleFS
ucsandmanucsandman/claude-skills/moleresearch/SKILL.md

moleresearch

Skill5 starsChanged 2 months agoMITView on GitHub

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.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If 'moleresearch' is not on PATH, run every command as: declick run moleresearch <verb> ...

    line 37
  2. Very specific:

    Every verb: --json (default when piped) --fields a,b --limit N.

    line 38

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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 <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 <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.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.