geo_mcp_server: Skill for Claude Code

.claude/skills/publish-research/SKILL.md

publish-research is a skill for Claude Code from rickycambrian/geo_mcp_server. It costs 37 tokens per session (1,737 once invoked), scanned A, original, MIT.

A workflow for publishing a research paper and its findings to the Geo knowledge graph, a structured system for linking research information and claims.

In plain words
What is it for?
Use it to provide paper metadata, extract exactly five main claims, configure a wallet, create a personal space, and publish the paper with the required ontology.
Why use it?
It ensures papers use the required research structure so their claims can be found in Geo’s knowledge tools.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is rickycambrian/geo_mcp_server's own configuration. It tells Claude Code how to work on geo_mcp_server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything geo_mcp_server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to rickycambrian/geo_mcp_server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/rickycambrian/geo_mcp_server/main/.claude/skills/publish-research/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/rickycambrian/geo_mcp_server

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for publish-research

README.md
[![agentmods](https://agentmods.dev/badge/skills/rickycambrian/geo_mcp_server/publish-research/github.svg)](https://agentmods.dev/skills/rickycambrian/geo_mcp_server/publish-research)
Your own site
<a href="https://agentmods.dev/skills/rickycambrian/geo_mcp_server/publish-research"><img src="https://agentmods.dev/badge/skills/rickycambrian/geo_mcp_server/publish-research/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for publish-research

Your own site · 80×15
<a href="https://agentmods.dev/skills/rickycambrian/geo_mcp_server/publish-research"><img src="https://agentmods.dev/badge/skills/rickycambrian/geo_mcp_server/publish-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,737 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00037 $0.01737
Opus 5 $0.00018 $0.00869
Sonnet 5 $0.00007 $0.00347
Haiku 4.5 $0.00004 $0.00174

Measured 10d ago against content hash 9010f63469f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

publish-research scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/publish-research/SKILL.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Publish Research Paper

Publish a research paper and its extracted claims to the Geo knowledge graph using the canonical Research ontology types.

Steps

  1. Configure wallet if not already done:

    • Use configure_wallet with the user's private key, or rely on GEO_PRIVATE_KEY env var
  2. Set up space:

    • Call setup_space to ensure the personal space exists
  3. Use the correct tool:

    • MUST use create_research_ontology_paper_and_claims
    • NEVER use create_knowledge_graph, build_schema, or create_knowledge_graph_from_file -- those create local types that do NOT match the canonical schema and claims will be invisible in Knowledgebook/GeoBrowser
  4. Provide paper metadata:

    • title (required)
    • abstract, publishDate, authors, topics, publishedIn, webUrl (optional)
  5. Extract and provide exactly 5 main claims (following the gold-standard 5-claim structure):

    • Position 1: Core problem/gap
    • Position 2: Key technical contribution
    • Position 3: Main empirical result
    • Position 4: Generalizability/robustness
    • Position 5: Broader implication
    • Each claim needs text (required)
    • Optional: sourceQuote, topics, supportingArguments, opposingArguments
  6. Propose to DAO (default, always use):

    • Call propose_dao_edit with daoSpaceAddress, daoSpaceId, and name
    • Do NOT call publish_edit before propose_dao_edit — it clears the session
    • DAO space ID: 6b05a4fc85e69e56c15e2c6891e1df32
    • DAO space address: 0xd3a0cce0d01214a1fc5cdedf8ca78bc1618f7c2f

Canonical Research Ontology Type IDs

These are the production type IDs used by GeoBrowser and Knowledgebook. The create_research_ontology_paper_and_claims tool handles these automatically.

Type ID Source
Paper 5e24fb52856c4189a9716af4387b1b89 Research ontology space
Claim 96f859efa1ca4b229372c86ad58b694b Research ontology space
Person 7ed45f2bc48b419e8e4664d5ff680b0d SystemIds.PERSON_TYPE
Topic 5ef5a5860f274d8e8f6c59ae5b3e89e2 Research ontology space
Project 484a18c5030a499cb0f2ef588ff16d50 SystemIds.PROJECT_TYPE

Read the full file on GitHub · 116 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 116 lines · 37 tokens per session scan A 9010f63469f0

Subscribe to this mod's changes

publish-research is a skill published in the GitHub repository rickycambrian/geo_mcp_server (0 stars, last pushed 5mo ago), licensed MIT. It adds 37 tokens to every session and 1,737 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.