New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Setting Up Papergraph

by lotchuazzz-crypto in lotchuazzz-crypto/papergraph-mcp

A skill your agent uses when a user has cloned PaperGraph MCP and asks to install, initialize, configure, set up, or start using it with an agent or MCP client.

MITAuto-check passedAgent Workflows

Install Setting Up Papergraph

skills CLI
$ npx skills add lotchuazzz-crypto/papergraph-mcp --skill setting-up-papergraph -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install lotchuazzz-crypto/papergraph-mcp setting-up-papergraph --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/lotchuazzz-crypto/papergraph-mcp.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/setting-up-papergraph .claude/skills/setting-up-papergraph && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
setting-up-papergraph
GitHub stars
282
Token cost
~3.3k tokens
SKILL.md length
1,712 words
Files
4 (incl. references)
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when a user has cloned PaperGraph MCP and asks to install, initialize, configure, set up, or start using it with an agent or MCP client.

  • Works in 9 steps: If a repository directory already… → Verify the pinned uvx --from ...… → For raw user wording, Markdown links,… → …
  • A user has cloned PaperGraph MCP and asks to install
  • SKILL.md covers Response contract and Failure branches
  • Calls uvx, python and git

What it does

Setting Up Papergraph is an agent skill from lotchuazzz-crypto/papergraph-mcp. Use when a user has cloned PaperGraph MCP and asks to install, initialize, configure, set up, or start using it with an agent or MCP client.

Its SKILL.md is about 3.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `agents/openai.yaml`, `references/client-configuration.md` and `references/usage-prompt.md`).

It sits in Agent Workflows, covering MCP servers and Academic paper search. It works with Model Context Protocol, arXiv, Python and LaTeX. The repository describes itself as: PaperGraph MCP turns math papers into evidence-grounded reading maps for AI agents: extract results, trace proof evidence, plan reading order, and review external dependencies… The licence is MIT.

When your agent uses it

  • A user has cloned PaperGraph MCP and asks to install
  • Start using it with an agent

Example prompts

  • “/setting-up-papergraph”

Requirements

  • Python 3

Workflow steps

9 steps, taken from the first numbered list in SKILL.md.

  1. If a repository directory already exists, inspect its branch, HEAD, working changes, and remote URL. Run git fetch --tags origin before…
  2. Verify the pinned uvx --from ... papergraph-mcp --version command and run pinned uvx --from ... papergraph-mcp doctor or call…
  3. For raw user wording, Markdown links, URLs, or prose, call validate_arxiv_request or load_arxiv_request.
  4. If a user provides both an arXiv ID and an arXiv URL, load_arxiv_request must stop before loading unless they identify the same paper.
  5. Use load_arxiv_paper only after the user has provided one already-disambiguated arXiv ID.
  6. If validation returns action: ask_user_to_choose, stop and ask which one to analyze. detecting a conflict and then continuing is a failure.
  7. For a user's first real reading project, propose plan-starter-project before bootstrap-reading-project so they can review the workspace…
  8. After bootstrap or Reading Report export, report Evidence Triage before interpreting dependency output. Name the triage status, supported…
  9. If Evidence Triage reports external blockers, use workspace_search_external_reference to gather scholarly metadata candidates. Report…

What it can do on your machine

Read from SKILL.md and the folder at commit ff1604a. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • uvx
    • python
    • git
    • uv

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use uvx, git and uv, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Setting Up Papergraph loads about 3.3k tokens when it runs, and up to ~5.7k if it reads all its reference files. Until then it costs about 41 tokens; SKILL.md has 1,712 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~41
When it runs · the whole SKILL.md, loaded when a task matches
~3.3k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~5.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from lotchuazzz-crypto/papergraph-mcp at commit ff1604a, republished under its MIT licence (© lotchuazzz-crypto). 1,712 words, ~3,338 tokens.

Download SKILL.mdSave it as .claude/skills/setting-up-papergraph/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
setting-up-papergraph
description
Use when a user has cloned PaperGraph MCP and asks to install, initialize, configure, set up, or start using it with an agent or MCP client.

Set up PaperGraph

Guide one conservative setup conversation. This skill does not change PaperGraph runtime behavior.

Before responding, read references/usage-prompt.md completely. Present that reusable prompt before requesting install approval, even if the user may defer setup.

Response contract

Keep these four phases short and in this order. Do not show later phases as completed before their work occurs.

What the user gets

Briefly explain that PaperGraph lets an MCP client analyze LaTeX papers, build a multi-paper workspace, search theorem-like content, and inspect explicit citation evidence. Give the reusable prompt in a copyable block. Translate it only under the preservation rule in its reference.

Before loading arXiv papers:

  1. If a repository directory already exists, inspect its branch, HEAD, working changes, and remote URL. Run git fetch --tags origin before trusting remote-tracking refs, and verify the remote default branch (do not assume main). Run python scripts/check_onboarding.py --repository <checkout> to compare local refs. Its freshness_verified: false means it did not fetch: matching a cached ref is not proof of freshness. Updating an old feature branch's upstream is not updating default-branch instructions. Unless the user explicitly requests a historical version, use instructions from the freshly fetched remote default revision. Preserve dirty or historical checkouts: use a separate clean checkout for current instructions, never reset, stash, overwrite, or switch the user's working files automatically. If fetch fails, disclose that freshness is unknown; do not say “already latest.”
  2. Verify the pinned uvx --from ... papergraph-mcp --version command and run pinned uvx --from ... papergraph-mcp doctor or call get_environment_diagnostics.
  3. For raw user wording, Markdown links, URLs, or prose, call validate_arxiv_request or load_arxiv_request.
  4. If a user provides both an arXiv ID and an arXiv URL, load_arxiv_request must stop before loading unless they identify the same paper.
  5. Use load_arxiv_paper only after the user has provided one already-disambiguated arXiv ID.
  6. If validation returns action: ask_user_to_choose, stop and ask which one to analyze. detecting a conflict and then continuing is a failure.
  7. For a user's first real reading project, propose plan-starter-project before bootstrap-reading-project so they can review the workspace path, artifact directory, explicit paper inputs, and generated manifest path before writes.
  8. After bootstrap or Reading Report export, report Evidence Triage before interpreting dependency output. Name the triage status, supported local chains, candidate starting point, external blockers, and next actions. Do not treat empty dependencies as evidence that no mathematical dependencies exist.
  9. If Evidence Triage reports external blockers, use workspace_search_external_reference to gather scholarly metadata candidates. Report confidence, provider evidence, ambiguity, and boundaries before applying anything. Use workspace_resolve_external_reference_candidate only for a selected candidate, or workspace_resolve_external_reference only with a confirmed arXiv ID, local PDF, DOI, URL, or published metadata. Then call workspace_list_external_reference_resolutions, workspace_list_external_reference_searches, or export a Reading Report to show whether each target is resolved_imported, resolved_not_imported, failed_import, ambiguous, or unavailable.

For a published DOI, do not pass it to an arXiv loader or claim metadata is an imported paper. Explain the supported inputs: arXiv source, local LaTeX, or a local born-digital PDF. Identify an unambiguous legally accessible full-text source, or ask for the user's local PDF; never bypass a paywall. A root paper requested by the user is distinct from newly discovered external references, which still require a reviewable import plan before downloads.

For v1.2.0 servers advertising discover_doi_paper, use it to find exact DOI metadata/body candidates without downloading. Review access reports, provider outcomes and reported versions. When the user's reading policy allows automatic loading of a requested root, use workspace_add_doi_paper: it imports only when one exact-identity public PDF candidate is eligible. For multiple candidates ask the user to select, then use workspace_import_doi_candidate with confirmed=true. Report actual import state and provenance. Never treat this as permission for recursive external-reference downloads. These tools are available in the pinned v1.2.0 package; historical versions may not provide them.

If available, workspace_get_dependency_reading lists source-backed main-result candidates without silently choosing one. Pass a user-selected target to separate statement references, direct/recursive proof-local evidence, reading order and external import plans. Check order_status before presenting bottom_up as a local prerequisite order; cycles block ordering, and unknown/external prerequisites remain outside it. Paper Map/queue exploration routes are not prerequisite orders.

For PDF papers, use result_count/evidence_counts and import_state; old theorem/citation counters describe the LaTeX statement graph. Keep provider_metadata display titles distinct from extracted PDF contents. Inspect proof_entry for explicit author-declared introductory correspondence: a corresponding proof keeps its original result owner and is not a verified mathematical equivalence. Ambiguous/missing/cyclic/bounded entries stay unresolved; do not silently choose a target or present their blocked order as complete.

Interpret dependency_extraction_basis as the legacy statement graph only, not the whole server's capabilities. Inspect dependency_capabilities when available. For proof questions use workspace_get_proof_dependencies, workspace_get_result_reading_path, and source-backed reading context. Neither statement refs nor proof-local evidence establish complete mathematical dependency coverage; empty output does not prove independence.

Show full SKILL.md (923 more words)Show less
What is missing

Run read-only detection when the host permits it:

text
python scripts/check_onboarding.py

Use its facts for git, uv, and uvx; also detect the active MCP client without mutation. Infer the client only from reliable host or executable evidence. If it remains ambiguous, ask one concise question: “Which MCP client should I configure?”

The default pinned PyPI launch requires uv and uvx, index access, and no Git or checkout. PyPI 1.2.0 is published; Git-free clean-cache acceptance passed CLI, stdio MCP and PDF reading. The checker defaults to pypi; --install-source pypi is also explicit. Do not install Git solely for a PyPI consumer. Missing repository/Git context and unknown checkout freshness are separate from index-launch readiness. The published doctor still recommends Git source and may emit a nonfatal Git-context warning outside a checkout; report that separately from actual launch failure.

The optional Git-source launch requires Git as well as uv and uvx. Inspect that route with python scripts/check_onboarding.py --install-source git. If Git is missing, explain that route's prerequisite and stop before claiming Git-source readiness; do not misdiagnose it as an API-key or MCP handshake problem. Installing Git needs the user's installation approval too.

After selecting the client, read references/client-configuration.md completely and use only its matching verified recipe. State the detected facts, proposed next mutation, and the next required approval.

There are three separate approval boundaries:

  1. install approval: if uv or uvx is missing, show the official platform-specific installer source and command, explain that uvx provides the reproducible launch, and ask before running it. Never reinstall or upgrade an existing installation automatically. Verify both uv --version and uvx --version; if either fails, stop before configuration.
  2. configuration approval: show the exact client change and ask before a native command or any edit outside this repository. For file-based configuration, parse first, preserve unrelated servers, and create a timestamped adjacent backup. If parsing fails, stop and show the error. If safe mutation is unavailable, provide the minimal snippet and exact placement guidance instead.
  3. restart approval: after configuration and launch validation, ask before controlling or restarting the client. If control is unavailable or permission is declined, provide one direct manual restart instruction.

For ordinary installation, use this fixed published package version; never substitute a branch, a mutable default, or an unreleased revision:

text
papergraph-mcp==1.2.0

The GitHub Release and immutable Git tag are available. Optional Git-source installation uses git+https://github.com/lotchuazzz-crypto/papergraph-mcp.git@v1.2.0 in --from; validate both version and doctor with the same selected source. Switching an existing client's source requires configuration approval and a backup. An explicitly requested development test is separate: use the requested checkout's locked environment or install its built wheel in a separate environment, then launch that exact interpreter. Check CLI version, doctor.build_identity (source commit, tracked changes and source-tree digest), and MCP initialization version. A dirty build's commit is its base; unknown build provenance is unknown. Release diagnostics name the package version's tag but do not themselves establish tag availability. Ordinary setup uses the verified PyPI 1.2.0 commands below; future package versions or tags must be verified before they are recommended. Keep the user's active MCP registration intact unless they explicitly authorize a configuration change, and never invent a development release/tag.

For PDF reading, surface text_coverage and unverified statement/proof completeness. Use its continuation-source locator before interpreting truncated text. Adjacent context is not additional proof evidence, and delayed proof ownership remains unresolved unless supported. Author partial_overlap is not full-list equivalence.

Never request credentials, upload papers, guess the identity of ambiguous references, recursively import newly discovered literature, bypass paywalls, or place a workspace database inside the Git repository. When a reference trail reaches an old paper with no electronic source, a metadata-only record, a paywalled target, or conflicting candidates, explain that PaperGraph reached a boundary and needs a user-supplied source or selection.

What changed

Only after actions occur, list the executable version checks, the PaperGraph entry added or confirmed, the validation result, and any backup path. Configuration success requires the pinned command below to exit successfully with version 1.2.0; file presence alone is insufficient:

text
uvx --from papergraph-mcp==1.2.0 papergraph-mcp --version

Also validate the pinned diagnostics command:

text
uvx --from papergraph-mcp==1.2.0 papergraph-mcp doctor

The expected output is:

text
papergraph-mcp 1.2.0

Before restart, say “launch command validated”; never say “client has loaded the PaperGraph tools.” Tool loading can be confirmed only after the restarted client discovers the server.

What to do now

Request restart approval or give the client-specific manual restart instruction. Remind the user that future conversations can use the reusable prompt. Stop after this instruction: do not persist setup state, create a handoff file, schedule work, or imply an automatic continuation.

Failure branches

  • If install approval is declined, change nothing, retain the reusable prompt, and give the official uv installation URL.
  • If uv installation or either executable check fails, report the failing check and do not configure a client.
  • If the client remains ambiguous, ask for its name before showing configuration; do not read the client reference or show generic JSON until the client is selected.
  • If the identified client is unsupported or the user explicitly chooses a generic route, show the generic JSON entry, ask for its official documentation, and never guess a path.
  • If the configuration is already equivalent, do not rewrite it; validate the pinned launch command and continue to restart guidance.
  • If an existing papergraph entry differs, show the difference and ask before replacing only that entry.
  • If configuration parsing fails, leave the file unchanged and report the exact error.
  • If the launch check fails, keep any valid configuration, report setup as incomplete, and do not claim readiness.
  • If restart is unavailable or declined, give the manual instruction and stop without persisted state or continuation.

© lotchuazzz-crypto, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (references) in .agents/skills/setting-up-papergraph of lotchuazzz-crypto/papergraph-mcp.

  • SKILL.md
  • agents/openai.yaml
  • references/client-configuration.md
  • references/usage-prompt.md

Open the folder on GitHubat commit ff1604a

Compare with similar skills

Setting Up Papergraph next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Setting Up Papergraph compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Setting Up Papergraph this skilllotchuazzz-crypto/papergraph-mcp282—~3.3kAutomated safety check: PassMIT
Arxiv MCP Serverblazickjp/arxiv-mcp-server3.2k—~353Automated safety check: PassApache-2.0
Nature Academic SearchTai609/NebulaMat100—~1.2kAutomated safety check: PassCustom licence
Literature Review Toolsbrycewang-stanford/Auto-Empirical-Research-Skills4.6k—~2.5kAutomated safety check: NotesCustom licence
Nature Academic Searchaiskillstore/marketplace433—~1.1kAutomated safety check: PassNone
Papers Skillsickn33/agentic-awesome-skills47k1 repos~2.1kAutomated safety check: PassMIT

Similar skills

  • Arxiv MCP Server

    blazickjp/arxiv-mcp-server

    A skill your agent uses when finding, comparing, reading, or monitoring arXiv papers, including requests for abstracts, citation graphs, original LaTeX, section-level technical details, or…

    3.2k GitHub stars~353 tokensUpdated 2 days ago
    Research & ScienceAuto-check passed

  • Nature Academic Search

    Tai609/NebulaMat

    Multi-source literature search, citation verification, strict independent other-citation audits, article-level citation metric tables, influential citer profiling with citation-context extraction…

    100 GitHub stars~1.2k tokensUpdated 1 mo ago
    Research & ScienceAuto-check passed

  • Literature Review Tools

    brycewang-stanford/Auto-Empirical-Research-Skills

    Recommend AND run open-source AI tools, agents, Claude Code / Codex skills, and MCP servers for any stage of a literature review — searching, reading, extracting, synthesizing, screening…

    4.6k GitHub stars~2.5k tokensUpdated 5 days ago
    Research & ScienceAuto-check: notes

  • Nature Academic Search

    aiskillstore/marketplace

    Multi-source literature search, citation verification, MeSH search strategy, citation file management (.nbib/.ris/.bib conversion), and reference management (BibTeX, related articles, ID conversion)…

    433 GitHub stars~1.1k tokensUpdated today
    Research & ScienceAuto-check passed

  • Papers Skill

    sickn33/agentic-awesome-skills

    Skill for academic research workflows: search Semantic Scholar (200M+ papers), inspect citations, download arXiv PDFs, and extract PDF text.

    47k GitHub starsUsed in 1 repo~2.1k tokens
    Research & ScienceAuto-check passed

  • Nature Academic Search

    wp-a/nature-academic-search

    A skill your agent uses when users ask to 找文献、做文献检索、查论文、查临床试验、核验引用、去重文献、设计 PubMed/MeSH 检索式、追踪上下游引文、解析 DOI/PMID/PMCID/arXiv/OpenAlex/Semantic Scholar/NCT ID， 或导出 RIS、BibTeX、NBIB、ENW；also use for…

    304 GitHub stars~1.4k tokensUpdated 9 days ago
    Research & ScienceAuto-check passed

Works with

Categories

Questions about Setting Up Papergraph

What does Setting Up Papergraph do?

A skill your agent uses when a user has cloned PaperGraph MCP and asks to install, initialize, configure, set up, or start using it with an agent or MCP client. Setting Up Papergraph is an agent skill from lotchuazzz-crypto/papergraph-mcp. Use when a user has cloned PaperGraph MCP and asks to install, initialize, configure, set up, or start using it with an agent or MCP client.

When should I use Setting Up Papergraph?

Setting Up Papergraph fits situations like: A user has cloned PaperGraph MCP and asks to install; start using it with an agent.

How do I install Setting Up Papergraph in Claude Code?

Run `npx skills add lotchuazzz-crypto/papergraph-mcp --skill setting-up-papergraph -a claude-code`. Or copy the skill folder (.agents/skills/setting-up-papergraph in lotchuazzz-crypto/papergraph-mcp) into .claude/skills/setting-up-papergraph in your project. Claude Code loads it when a task matches its description.

How do I install Setting Up Papergraph in Codex?

Run `npx skills add lotchuazzz-crypto/papergraph-mcp --skill setting-up-papergraph -a codex`. Or copy the skill folder (.agents/skills/setting-up-papergraph in lotchuazzz-crypto/papergraph-mcp) into .agents/skills/setting-up-papergraph in your project. Codex loads it when a task matches its description.

Can I use Setting Up Papergraph in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add lotchuazzz-crypto/papergraph-mcp --skill setting-up-papergraph -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/setting-up-papergraph, .gemini/skills/setting-up-papergraph, .github/skills/setting-up-papergraph and .opencode/skills/setting-up-papergraph in your project.

What does Setting Up Papergraph need to run?

Going by SKILL.md and its folder, Setting Up Papergraph needs the command-line tools its instructions call (uvx, python, git and uv). Our summary lists: Python 3.

Does Setting Up Papergraph access the network?

SKILL.md contains no URLs. Its commands use uvx, git and uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Setting Up Papergraph safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Setting Up Papergraph use?

Setting Up Papergraph is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Setting Up Papergraph use?

About 3.3k tokens (SKILL.md is roughly 13k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.4k tokens, read only when the agent opens those files.

What are the alternatives to Setting Up Papergraph?

Skills that share tags, products or a category with Setting Up Papergraph: Arxiv MCP Server (blazickjp/arxiv-mcp-server, 3.2k stars), Nature Academic Search (Tai609/NebulaMat, 100 stars), Literature Review Tools (brycewang-stanford/Auto-Empirical-Research-Skills, 4.6k stars) and Nature Academic Search (aiskillstore/marketplace, 433 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Setting Up Papergraph?

lotchuazzz-crypto (a GitHub user) maintains it in lotchuazzz-crypto/papergraph-mcp, which has 282 GitHub stars. The repository was last updated on October 7, 2026.

Source: lotchuazzz-crypto/papergraph-mcp on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.