all publishers

allenai

@allenai source repo

30 published skills

  1. ▌
    Add Benchmark · allenai
    Add or improve a simulation benchmark in vla-eval, including evaluation protocol, assets, adapter lifecycle, and runtime validation.
    45 repo stars
  2. ▌
    Run Evaluation · allenai
    Run, debug, and scale VLA evaluations in vla-eval while preserving evaluation conditions and verifying complete results.
    45 repo stars
  3. ▌
    Add Model Server · allenai
    Add or improve a VLA model integration in vla-eval, covering checkpoint setup, inference parity, per-episode state, and serving validation.
    45 repo stars
  4. ▌
    Update Pr Body · allenai
    Update the body of a GitHub pull request. Use when the user asks to update, edit, or modify a PR description/body.
    45 repo stars
  5. ▌
    Monitor Experiment · allenai
    Monitor Beaker experiments until completion. Use when the user asks to monitor, check, or track a Beaker experiment.
    45 repo stars
  6. ▌
    Run · allenai
    Router skill that advances the project autonomously. Examines project.md Pending Work, dispatches to do-work for ready items or plan-work otherwise, and loops until no actionable work remains. Use when the user says "keep going", "work on the project", "run the next step".
    45 repo stars
  7. ▌
    Asta CLI · allenai
    Install or update the `asta` CLI to the version pinned by this plugin. Invoke whenever `asta` is not on PATH (e.g. `command not found` for `asta`) or when a subcommand/flag appears missing — that signals a stale install needing an update.
    45 repo stars
  8. ▌
    Feedback · allenai bundle
    Interview the user about their experience with the Asta plugins and tools, write a narrative feedback report, and submit it (with optional supporting files) to the Asta team for analysis. Use when the user wants to "give feedback", "send feedback to the Asta team", "report how this went", or "tell Ai2 what I think".
    45 repo stars
  9. ▌
    Artifacts · allenai
    Use this skill to export and open A2A agent task outputs — "export the task results", "convert the task output to HTML", or work with the structured artifacts produced by an A2A agent task run.
    45 repo stars
  10. ▌
    Workspace · allenai bundle
    Show the user the agent's work on a research project and save iterations on the user's behalf. Scaffold rendering and deploy infrastructure (Quarto today, GitHub Pages, dev container), show the rendered output, save iterations. Doesn't handle research execution (use `asta-flows`).
    45 repo stars
  11. ▌
    Asta Flows · allenai bundle
    Plan and execute autonomous research as a graph of typed tasks tracked in beads. Use when working from a mission.md to drive multi-step research with explicit dependencies and structured outputs.
    45 repo stars
  12. ▌
    Experiment · allenai
    Run scientific (software) experiments. Use when the user asks to "run an experiment", "run an investigation", or "research with Asta." Also use this skill to analyze experimental data generate a research report from it. The user may refer to this system by its internal project name, "Panda."
    45 repo stars
  13. ▌
    Do Work · allenai
    Execute the approved plan in work/<slug>/README.md (status ready), write outputs into work/<slug>/data/, record what happened in the Results section, then hand off to review-work. Use when there is a ready work item.
    45 repo stars
  14. ▌
    Improve Skills · allenai
    Report or fix a behavior gap in Asta skills. Use when an agent does the wrong thing, doesn't do what was asked, or lacks a capability that's wanted.
    45 repo stars
  15. ▌
    Analyze Data · allenai
    This skill should be used when the user asks to "analyze this dataset", "run datavoyager", "run data voyager", "explore this data", "what's in this CSV", "statistical analysis of", "find patterns in", or wants an AI-driven, code-executing analysis of a tabular dataset that answers a specific research question.
    45 repo stars
  16. ▌
    PDF Download · allenai bundle
    Download PDFs for a list of academic papers identified by title, DOI, arXiv ID, or other paper IDs. Use when the user asks to "download these papers", "grab the PDFs", "fetch full text for this list", or supplies a list of citations and wants the source PDFs on disk. Resolves open-access PDFs automatically and drives a real browser (via Playwright, with a persistent profile) so the user can authenticate to paywalled publishers.
    45 repo stars
  17. ▌
    Plan Work · allenai
    Write a detailed, executable plan for a single unit of work, then get it approved by review-plan. Updates work/<slug>/README.md with concrete instructions and sets status to ready (or needs-input if review repeatedly rejects).
    45 repo stars
  18. ▌
    Save Work · allenai
    Persist completed work. For each work/<slug>/README.md with status done, move it from Pending to Completed in project.md, index the README in work/index.yaml via asta-documents, and commit the artifacts to git. Use after one or more work items finish.
    45 repo stars
  19. ▌
    Autodiscovery · allenai bundle
    Create, configure, and monitor AutoDiscovery runs — either via the hosted service (`asta autodiscovery`) or via the local CLI (`asta-autodiscovery`). Use when the user asks about their runs, experiments, discoveries, wants to check status, or wants to start a new discovery run.
    45 repo stars
  20. ▌
    Brainstorm · allenai
    Converse with the user to identify the next most productive units of work for the current project, and record them in project.md under Pending Work. Use when the user wants to plan what to work on next, or when there is no project.md yet.
    45 repo stars
  21. ▌
    Asta Documents · allenai
    Local document metadata index for files used by Asta skills and tools. Use this skill when the user asks to store a document "in Asta" or retrieve "from Asta". Use it when the user references an "Asta document" or anything with an `asta://` URI.
    45 repo stars
  22. ▌
    PDF Extraction · allenai
    Extract text from PDFs using olmOCR or remote OCR. Use when user asks to "extract text from PDF", "OCR a document", "read a PDF", or needs to process scanned documents.
    45 repo stars
  23. ▌
    Review Plan · allenai
    Critic skill. Given a plan in work/<slug>/README.md (status pending-review), check that the steps are concrete, the tools are appropriate, and the plan is realistic. Write a verdict and feedback back into the README.
    45 repo stars
  24. ▌
    Review Work · allenai
    Critic skill. Given an executed work item (status pending-assessment), assess whether the Goal was actually accomplished. Identify the root cause when it was not (incorrect assumption, technical blocker, missing data). Updates work/<slug>/README.md Assessment section.
    45 repo stars
  25. ▌
    Find Literature · allenai
    This skill should be used when the user asks to "find papers", "search for papers", "what does the literature say", "find research on", "academic papers about", "literature review", "cite papers", or needs to answer questions using academic literature.
    45 repo stars
  26. ▌
    Research Challenge · allenai bundle
    Summarize a research project conducted with Asta skills and submit it to the asta-research-challenge repository. Use when the user wants to reflect on a finished (or in-progress) project and/or share it with the Asta team. The user may say "reflect on this project", "submit my research challenge", or "write up what we did".
    45 repo stars
  27. ▌
    Semantic Scholar · allenai
    Look up or search papers, authors, citations, and full-text snippets on Semantic Scholar. Use for fast, targeted queries about a paper, author, or specific named research artifact (benchmark, dataset, model, method, etc.) — not comprehensive reports.
    45 repo stars
  28. ▌
    Generate Theories · allenai
    This skill should be used when the user asks to "generate theories", "theorize about", "what theories explain", "form scientific theories", "literature-driven theories", "hypothesize", "form hypotheses", "generate hypotheses", "what hypotheses explain", "run the theorizer", or wants AI-generated, literature-grounded scientific theories or hypotheses about a research question.
    45 repo stars
  29. ▌
    Literature Report · allenai
    Create or update literature reviews/reports. Use whenever you need to research, summarize, or synthesize the literature.
    45 repo stars
  30. ▌
    Local Paper Index · allenai bundle
    Build a searchable Asta document index from a collection of local PDF files. Use when the user asks to "index these PDFs", "put these PDFs into an Asta index", "index these PDFs using Asta", "build a local paper index", "make these PDFs searchable", or "create an index from these papers".
    45 repo stars