New to Claude Skills? Learn how to install them →

volcengine on GitHub

Add Paper to OpenViking

Free

Seamlessly ingest research papers into OpenViking.

Get this skill

Free · Opens the source repo

What Add Paper to OpenViking does

The Add Paper to OpenViking skill streamlines the process of importing and structuring research papers for use within the OpenViking framework. This skill is particularly useful for researchers and developers who need to transform academic papers into structured resources that can be easily managed and referenced in OpenViking. By automating the ingestion process, users can focus more on research and less on administrative tasks.

When a user provides a PDF or a URL of a research paper, the skill reads the entire document, including appendices and figures. It compiles the necessary ARA-style artifact directory based on predefined profiles, ensuring that the resulting structure meets the requirements for OpenViking ingestion. The skill also includes a validation step, which checks for any errors in the generated artifact before it is submitted to OpenViking, thus enhancing the reliability of the ingestion process.

This skill is designed for anyone who regularly works with academic papers and needs to integrate them into OpenViking. It caters to researchers, data scientists, and developers who require a systematic way to manage literature and evidence in their projects. By providing a clear workflow that includes validation and error handling, the skill ensures that users can efficiently add valuable resources to their OpenViking environment without the usual hassles.

In summary, the Add Paper to OpenViking skill automates the ingestion of research papers, validates the resulting artifacts, and integrates seamlessly with OpenViking, making it an essential tool for anyone looking to enhance their research management capabilities.

When to use it

Use this skill when you need to import a research paper into OpenViking, especially if it includes figures, tables, or claims that need to be structured.

When not to use it

This skill is not suitable for papers that do not conform to the expected format or for users who do not require integration with OpenViking.

What you can build with it

Ingesting a New Research Paper

When you have a new research paper to add to OpenViking, this skill automates the ingestion process, ensuring it is structured correctly.

Validating Paper Ingestion

If you are concerned about the accuracy of your ingestion, this skill validates the generated artifact and reports any issues.

Integrating Literature into Projects

Use this skill to efficiently integrate academic literature into your OpenViking projects, enhancing your research capabilities.

How to install Add Paper to OpenViking

View source

1. Install with the skills CLI

npx skills add volcengine/openviking/ov-add-paper --agent claude-code

2. Or install it manually

Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.

Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs

Inside SKILL.md

Written by volcengine

ov-add-paper

Goal

Turn a research paper into an OpenViking-ready structured resource, then complete ingestion with ov add-resource. The job is not done until the generated artifact directory has been validated and submitted to OpenViking.

Inputs

  • Required: a paper source, usually a local PDF path or paper URL.
  • Optional: output directory, OpenViking target URI, domain notes, related repo/source files, and whether to wait for OV processing.
  • If the paper source is missing or inaccessible, ask for it before starting.

Workflow

  1. Read the paper completely, including appendices and all numbered figures/tables.
  2. Compile an ARA-style artifact directory using references/ara-compiler-profile.md.
  3. Validate the artifact with scripts/validate_ara.py.
  4. Fix validation failures unless the user explicitly accepts them.
  5. Ingest the validated artifact directory with ov add-resource directly.
  6. Confirm the target with ov stat/ov tree and return the artifact path, OV target/root URI, validation result, ingest result, and any unresolved gaps.

Output Contract

The generated artifact must include:

  • PAPER.md
  • logic/problem.md, logic/claims.md, logic/concepts.md, logic/experiments.md, logic/related_work.md
  • logic/solution/constraints.md
  • src/environment.md
  • trace/exploration_tree.yaml
  • evidence/README.md
  • Markdown plus PNG evidence files for every filed numbered table and figure

The final response must include the ov add-resource command result, or the recovery checks proving the target landed despite a broken --wait, or the exact blocker that prevented ingestion.

Verification

Run from this skill directory, or use an absolute path to the validator:

python3 scripts/validate_ara.py <artifact-dir>

Then ingest with the OV CLI:

ov add-resource <artifact-dir> --to viking://resources/papers/<slug> --wait --timeout 300

Before ingest, use ov -o json stat <target-uri> to check whether the target already exists. After ingest, verify with ov -o json stat <target-uri> and ov tree <target-uri>.

Permissions

  • Writing a new OpenViking resource is allowed when the user asked to add or ingest the paper.
  • Ask before intentionally reusing a target URI that may overwrite or replace an existing resource.
  • --skip-validation may be used only when the user explicitly accepts the listed validation errors.

Boundaries

  • Do not use ov add-skill; this skill creates paper resources, not OV skills.
  • Do not silently skip ov add-resource; if ingestion fails, report the command, error, and recovery path.
  • If ov add-resource --wait exits with a connection error after creating the target, do not immediately retry the same URI. Run ov stat, ov wait --timeout <seconds>, ov observer queue, and ov tree to determine whether ingestion completed.
  • Do not invent claims, evidence, source refs, code, numbers, or research history.
  • Do not overwrite an explicit existing OV target unless the user asked for that target.
  • Mark unsupported or unreadable content as unavailable instead of filling it in.

Runtime Resources

  • Load references/ara-compiler-profile.md before compiling the artifact.
  • Load references/openviking-ingest.md before running OV ingestion or debugging an ingestion failure.
  • Use scripts/validate_ara.py for deterministic checks.

Frequently asked questions about Add Paper to OpenViking

Similar skills