Imbue

Skills from Imbue

• architect

  Generates an architecture document for a feature by reading the existing spec, analyzing the codebase deeply, and conducting guided Q&A with the user to…

  Claude Code · about 4K tokens · pinned 6 days ago

• build

  This skill executes a multi-step implementation plan by working through task files sequentially.

  Claude Code · about 1.1K tokens · pinned 6 days ago

• build-sculptor-extension

  Build or modify Sculptor extensions, which are runtime ES modules that add panels, overlays, widgets, home views, or settings UI to the Sculptor frontend.

  Contains scripts

  Claude Code, Codex, Cursor +3 · about 3.3K tokens · pinned 6 days ago

• fix-bug

  Fixes bugs using test-driven development with an interactive or autonomous workflow.

  Claude Code · about 9.8K tokens · pinned 6 days ago

• handoff

  This skill hands off ongoing work to a fresh agent, either in the same workspace or a new isolated workspace, while preserving context through a synthesized…

  Claude Code · about 1.1K tokens · pinned 6 days ago

• help

  This skill fetches the latest Sculptor documentation from GitHub and answers user questions about how to use Sculptor's features, including workspaces…

  Claude Code · about 880 tokens · pinned 6 days ago

• mock

  Creates interactive HTML mocks for features through guided iteration with users in exploration mode (generating 3+ variants to explore ideas) or confirmation…

  Claude Code · about 3K tokens · pinned 6 days ago

• openhost-environment

  This skill documents how to operate a Sculptor coding agent when deployed on OpenHost, including persistent storage locations, GitHub authentication setup…

  Claude Code, Codex, Cursor +4 · about 1K tokens · pinned 6 days ago

• plan

  Produces a detailed implementation plan from a spec and architecture document, breaking work into self-contained task files that a developer can execute one…

  Claude Code · about 5.2K tokens · pinned 6 days ago

• restack

  This skill propagates changes from a parent branch down through stacked child branches by merging each parent's updates into its children in order.

  Claude Code · about 1.7K tokens · pinned 6 days ago

• review

  This skill performs a final review of a feature implementation by verifying the diff against the spec, checking that tests were written and pass, invoking a…

  Claude Code · about 2.7K tokens · pinned 6 days ago

• sculpt-cli

  This skill provides CLI access to the Sculptor API for managing workspaces, agents, and workflows.

  Claude Code · about 1.7K tokens · pinned 6 days ago

• setup-repo

  Creates or updates three Sculptor configuration files that teach other workflow skills how to build, test, and document a specific codebase.

  Claude Code · about 5K tokens · pinned 6 days ago

• spec

  This skill guides users through writing implementation specifications via structured conversation before code is written.

  Claude Code · about 7.4K tokens · pinned 6 days ago

• stack

  This skill creates a new stacked workspace branched from the current branch, enabling parallel work where the new branch targets the current branch as its base.

  Claude Code · about 670 tokens · pinned 6 days ago

• offload

  Offload is a parallel test runner that executes tests across multiple sandboxes, either locally or on Modal.

  Claude Code, Codex, Cursor +4 · about 3K tokens · pinned 6 days ago

• offload-onboard

  This skill onboards a repository to use Offload, a parallel test runner that executes tests across Modal cloud sandboxes.

  Claude Code · about 7.1K tokens · pinned 6 days ago

• edit-theory

  This skill enables an agent to modify and extend scientific theories by reading existing theory documents, designing and running validation experiments…

  Claude Code · about 1.9K tokens · pinned 6 days ago

• execute-proposal

  This skill receives a proposal ID, retrieves the proposal from a database, determines whether it is an experiment, literature search, or solution candidate…

  Claude Code · about 1.1K tokens · pinned 6 days ago

• expand-theory

  This skill expands a scientific theory by implementing suggestions from expansion reviews.

  Claude Code · about 2.5K tokens · pinned 6 days ago

• falsify-hypothesis

  This skill acts as a hypothesis falsifier that systematically tests scientific claims to find their breaking points.

  Claude Code · about 1.6K tokens · pinned 6 days ago

• improve-adherence

  This skill refines a scientific theory based on adherence review findings that identify constraint violations or explanatory gaps.

  Claude Code · about 2.2K tokens · pinned 6 days ago

• integrate-interpretations

  Integrates recent interpretations from an interpretation log into an existing scientific theory, reconciling new experimental results, literature findings, or…

  Claude Code · about 2.6K tokens · pinned 6 days ago

• interpret-result

  This skill interprets results from completed experiments, literature searches, or solution candidates within a research context.

  Claude Code · about 1.5K tokens · pinned 6 days ago

• literature-review

  This skill searches arXiv for relevant papers on a given research topic, downloads their source files, and synthesizes findings into a structured literature…

  Claude Code · about 1.4K tokens · pinned 6 days ago

• polish-theory

  This skill restructures and rewrites scientific theory documents to improve clarity and readability without changing core content.

  Claude Code · about 1.6K tokens · pinned 6 days ago

• predict-experiments

  This skill predicts experimental outcomes based on a given theory without running the experiments.

  Claude Code · about 1.2K tokens · pinned 6 days ago

• propose-experiment

  This skill designs and proposes the next research step by reviewing the current theory and research goal, then selecting between conducting a focused…

  Claude Code · about 2.3K tokens · pinned 6 days ago

• rank-experiments

  This skill ranks experiments by their importance for evaluating scientific theories against a phenomenon.

  Claude Code · about 760 tokens · pinned 6 days ago

• rank-proposals

  This skill analyzes and ranks multiple proposals by reading their metadata, grouping them by type (experiments, literature searches, or solution candidates)…

  Claude Code · about 880 tokens · pinned 6 days ago

• refine-hypothesis

  This skill refines a scientific hypothesis by analyzing falsification results from peer reviews and iterating on improvements through experiments and…

  Claude Code · about 3.2K tokens · pinned 6 days ago

• run-experiment

  This skill sets up and executes Python-based experiments within a managed environment.

  Claude Code · about 910 tokens · pinned 6 days ago

• score-guidance-adherence

  This skill evaluates how well a theory in theory.md adheres to user guidance found in phenomenon.txt or GUIDANCE.txt.

  Claude Code · about 420 tokens · pinned 6 days ago

• score-length

  This skill measures the length of a theory's main body content and calculates a normalized score using a formula that compares word count against a standard…

  Claude Code · about 370 tokens · pinned 6 days ago

• score-soundness

  This skill evaluates the mathematical soundness of a theory by examining falsification reports and assigning a numerical score from 0 to 1.

  Claude Code · about 450 tokens · pinned 6 days ago

• score-theory-local-subscores

  This skill scores a scientific theory across three dimensions: length, guidance adherence, and soundness.

  Claude Code · about 560 tokens · pinned 6 days ago

• score-theory-solutions

  This skill evaluates solution candidates against a research goal, assigns verification adherence and ranking scores, and updates parent theory scores in a…

  Contains scripts

  Claude Code · about 1.3K tokens · pinned 6 days ago

• search-literature

  This skill runs targeted searches to find academic papers directly addressing a specific research finding or question that emerged during theory development.

  Claude Code · about 1.5K tokens · pinned 6 days ago

• streamline-theory

  This skill streamlines an existing theory document by identifying its core narrative and removing extraneous details while maintaining scientific rigor.

  Claude Code · about 1.6K tokens · pinned 6 days ago

• suggest-expansions

  This skill reviews a scientific theory and identifies concrete expansion opportunities such as generalizations, missing cases, unproven corollaries, or…

  Claude Code · about 1.2K tokens · pinned 6 days ago

• summarize-goal-progress

  This skill reviews the best solution found in scientific research, summarizes its design and verification results, extracts key open questions from the parent…

  Claude Code, Codex, Cursor +4 · about 1.6K tokens · pinned 6 days ago

• summarize-research

  The skill analyzes top scientific theories from research context, evaluates their validation status through reviews, identifies surprising discoveries, and…

  Claude Code, Codex, Cursor +4 · about 1.7K tokens · pinned 6 days ago

• support-idea

  This skill helps agents build rigorous mathematical and experimental support for a provided theory by running literature searches, deriving proofs, and…

  Claude Code · about 2.8K tokens · pinned 6 days ago

• write-theory

  This skill guides an agent to develop rigorous, mechanistic theories explaining scientific phenomena.

  Claude Code · about 2.8K tokens · pinned 6 days ago

• deburr-edge-cases

  Removes accumulated cruft from code branches by eliminating defensive runtime checks better handled by types, redundant validation, over-abstraction, and…

  Claude Code, Codex, Cursor +4 · about 2.4K tokens · pinned 6 days ago

• find-agent

  This skill resolves an agent name or description to an exact agent identifier by querying available agents and handling common input formats like git branch…

  Claude Code · about 210 tokens · pinned 6 days ago

• message-agent

  Send a message to another mngr agent within a distributed system.

  Claude Code · about 490 tokens · pinned 6 days ago

• mngr-help

  This skill enables the agent to learn about and use mngr, a command-line tool for managing agents and hosts.

  Claude Code, Codex, Cursor +4 · about 190 tokens · pinned 6 days ago

• release-to-crates

  This skill automates releasing a Rust crate by bumping the version in Cargo.toml, merging the change via pull request with CI verification, and publishing to…

  Claude Code, Codex, Cursor +4 · about 2.3K tokens · pinned 6 days ago

• wait-for-agent

  This skill monitors another agent until it reaches a ready state (WAITING, DONE, or STOPPED), then executes follow-up instructions provided by the user.

  Claude Code · about 520 tokens · pinned 6 days ago

Open roles at Imbue