← all publishers

stencila

@stencila source repo

39 published skills

  1. Schema · stencila bundle
    An agent skill providing instructions for AI agents.
    0
    installs
  2. New · stencila
    Create a new, tracked Stencila document with scaffolded frontmatter.
    0
    installs
  3. Lint · stencila
    Lint Stencila documents and summarise the diagnostics.
    0
    installs
  4. Snap · stencila
    Screenshot a Stencila document and read it back for visual verification.
    0
    installs
  5. Doctor · stencila
    Check the health of the Stencila CLI installation - version, available upgrades, kernels, linters, external tools, and workspace configuration. The first thing to run when anything Stencila-related is not working.
    0
    installs
  6. Render · stencila
    Render a Stencila document - execute its code and encode to output formats.
    0
    installs
  7. Convert · stencila
    Convert a document between formats, reporting any conversion losses.
    0
    installs
  8. Execute · stencila
    Execute the code in a Stencila document and save the outputs into it.
    0
    installs
  9. Preview · stencila
    Open a live preview of a Stencila document or site in the browser.
    0
    installs
  10. Authoring · stencila bundle
    How to write Stencila Markdown (.smd) and work with executable documents in related flavours (.myst, .qmd). Use when creating or editing .smd files, adding executable code chunks, inline expressions, parameters, figures, tables, math, or document metadata, or when unsure how Stencila Markdown differs from plain Markdown.
    0
    installs
  11. Execution · stencila
    How Stencila executes documents - kernels, staleness-driven re-execution, execution options, and debugging chunks that error or do not re-run. Use when running stencila execute or render, when a code chunk is not re-running, when choosing a language/kernel, or when reading execution errors.
    0
    installs
  12. Conversion · stencila
    Converting documents between formats with stencila convert - lossless vs lossy targets, quantifying conversion losses, decoding options, and ingesting documents by DOI, arXiv, or PubMed Central identifier. Use when converting to or from DOCX, PDF, LaTeX, JATS, IPYNB, MyST, Quarto or other formats, or importing published papers.
    0
    installs
  13. Publishing · stencila
    Publishing Stencila documents - rendering to HTML/PDF/DOCX with themes, building and pushing workspace sites, publishing to Ghost or Zenodo, and signing outputs with content credentials. Use when the user wants to publish, deploy a site, apply a theme, produce final outputs, or push to Ghost, Zenodo or Stencila Cloud.
    0
    installs
  14. Workspaces · stencila
    Stencila workspace configuration and document tracking - stencila.toml sections, stencila init, track/status/untrack/clean, and what lives in the .stencila/ directory. Use when configuring a Stencila project, setting up remotes or outputs, interpreting stencila status, or deciding what to commit or clean.
    0
    installs
  15. Agent Review · stencila
    Critically review a Stencila agent and suggest improvements. Use when asked to review, audit, critique, evaluate, or improve an agent directory or AGENT.md file. Covers frontmatter validation, system instruction quality, configuration correctness, and adherence to the Agent schema.
    0
    installs
  16. Skill Review · stencila
    Critically review a workspace skill and suggest improvements. Use when asked to review, audit, critique, evaluate, or improve a SKILL.md file or skill directory. Covers frontmatter validation, instruction clarity, completeness, and adherence to the Agent Skills Specification.
    0
    installs
  17. Theme Review · stencila bundle
    Critically review an existing or proposed Stencila theme artifact for correctness, token usage, target coverage, cross-target portability, dark-mode handling, maintainability, and approval readiness. Use when asked to review, critique, assess, audit, or validate a theme.css file, theme patch, theme plan, site theme, document theme, plot theme, print or PDF theme, check design tokens, assess DOCX or email behavior, review dark mode support, or validate with stencila themes validate.
    0
    installs
  18. Figure Review · stencila bundle
    Critically review an existing or proposed Stencila figure artifact for structural correctness, caption quality, layout, overlay annotation safety, cross-references, measurement validity, and approval readiness. Use when asked to review, critique, assess, audit, validate, or improve a figure block, multi-panel figure, subfigure grid, executable chart figure, caption, SVG overlay, ROI annotation, scale bar, panel labeling, or figure plan.
    0
    installs
  19. Agent Creation · stencila
    Create a new Stencila agent. Use when asked to create, write, scaffold, or set up an agent directory or AGENT.md file. Covers workspace and user-level agents with model, provider, tool, trust, and MCP configuration.
    0
    installs
  20. Skill Creation · stencila
    Create a new Stencila workspace skill. Use when asked to create, write, or scaffold a SKILL.md file or skill directory.
    0
    installs
  21. Theme Creation · stencila bundle
    Create, update, or plan a Stencila theme for documents or published sites. Use when asked to choose a theme direction, write or patch theme.css, recommend semantic or module token families, customize site navigation or branding, tune PDF and print page tokens, align web, Python, and R plots with a Stencila design system, list available builtin tokens with `stencila themes tokens`, or validate a theme file with `stencila themes validate`.
    0
    installs
  22. Figure Creation · stencila bundle
    Create, edit, or plan figures in Stencila Markdown — simple image figures, executable code figures, multi-panel subfigure layouts with grid arrangements, and SVG annotation overlays using overlay components. Use when asked to add or revise a figure, chart, plot, caption, subfigure grid, panel layout, overlay annotation, callout, scale bar, arrow, region-of-interest highlight, or figure design plan for a Stencila document.
    0
    installs
  23. Mira Annotation · stencila
    Annotate Markdown documents with MIRA research objects and source-local relations. Use for md, smd, qmd, and myst files when identifying claims, evidence, questions, protocols, requests, typed claims, and relation attributes while preserving the original Markdown flavor and author wording. Not for general copyediting, prose rewriting, or extracting a separate knowledge graph without annotating the source.
    0
    installs
  24. Workflow Review · stencila
    Critically review a Stencila workflow and suggest improvements. Use when asked to review, audit, critique, evaluate, or improve a workflow directory or WORKFLOW.md file. Covers frontmatter validation, DOT pipeline quality, workflow structure, agent selection quality, discovery metadata, ephemeral workflow conventions, workflow composition, and adherence to Stencila workflow patterns.
    0
    installs
  25. Workflow Creation · stencila
    Create a new Stencila workflow. Use when asked to create, write, scaffold, or set up a workflow directory or WORKFLOW.md file. Covers workflow discovery, duplicate-name checks, ephemeral workflows, WORKFLOW.md frontmatter, DOT pipeline authoring, goals, agents, branching, composition, and validation.
    0
    installs
  26. Site Config Review · stencila bundle
    Review a Stencila site configuration (stencila.toml) for correctness, completeness, best practices, and rendered appearance. Use when asked to review, audit, validate, check, or assess a site config, stencila.toml, site routes, redirects, site layout, layout presets, site nav, navigation, site access, access control, or site deployment readiness.
    0
    installs
  27. Site Config Creation · stencila bundle
    Create or update the [site] section of stencila.toml for published Stencila sites. Use when asked to configure site domain, title, author, logo, icons, labels, descriptions, socials, featured content, navigation, routes, access, layout presets and regions, glide, search, formats, reviews, uploads, remotes, actions, auto-index, or specimen. Covers reading existing TOML, generating valid configuration, editing while preserving comments and formatting, and snap-based visual verification.
    0
    installs
  28. Software Code Review · stencila
    Evaluate source code for correctness, quality, security, style conformance, and maintainability, producing a structured review report with findings and recommendations. Use when the user wants to review, critique, audit, evaluate, or inspect source code — checking for bugs, logic errors, unhandled error paths, security vulnerabilities, naming and readability issues, complexity, duplication, coupling, testability, and API design. Discovers codebase conventions independently and produces an actionable report with severity-graded findings grouped by category, prioritized recommendations, and open questions.
    0
    installs
  29. Software Plan Review · stencila
    Critically review a software delivery plan and suggest concrete improvements. Use when the user wants to review, critique, audit, evaluate, or strengthen a delivery plan, implementation plan, project plan, phased roadmap, or test plan. Reviews plans produced by the software-plan-creation skill, checking task breakdown quality, sequencing, dependencies, testing strategy, TDD slice design and sizing, design coverage, risks, and actionability. Produces a structured critique with prioritized recommendations.
    0
    installs
  30. Software Test Review · stencila
    Evaluate the quality of TDD tests against slice acceptance criteria, codebase conventions, and Red-phase execution results, producing a structured review with Accept or Revise recommendations. Use when tests written during the Red phase of red-green-refactor need quality review — checking coverage of acceptance criteria, conformance with codebase test conventions, test quality (naming, assertions, isolation, readability, triviality), edge-case and error-path coverage, and whether Red-phase failures indicate correctly missing implementation. Flags trivial low-value tests that add more maintenance cost than testing value. Discovers codebase conventions independently and produces an actionable review report.
    0
    installs
  31. Mira Annotation Review · stencila
    Review MIRA annotations in Markdown documents for semantic correctness, Markdown dialect validity, preservation, and relation integrity. Use for md, smd, qmd, and myst files containing research objects such as claims, evidence, questions, protocols, requests, typed claims, ids, and relations. Produces actionable findings without modifying files by default.
    0
    installs
  32. Software Design Review · stencila
    Critically review a software design specification and suggest concrete improvements. Use when the user wants to review, critique, audit, evaluate, or strengthen a design spec, technical specification, feature design, architecture proposal, or implementation plan. Focus on clarity, completeness, correctness, feasibility, tradeoffs, risks, assumptions, and actionable recommendations that improve the design without turning the task into code generation or workflow design.
    0
    installs
  33. Software Plan Creation · stencila
    Create delivery plans for software design specifications. Use when the user wants to plan implementation, break a design into delivery phases, create an implementation roadmap, produce a test plan, or structure a TDD approach for a feature. Reads the latest design spec by default and produces a phased plan covering implementation, testing, and documentation, with TDD slices sized to be logically coherent without degenerating into micro-slices.
    0
    installs
  34. Software Test Creation · stencila bundle
    Write failing tests for a TDD slice based on acceptance criteria and codebase conventions. Use when the "red" phase of red-green-refactor requires tests that define expected behavior before implementation exists. Discovers codebase test conventions first, writes test files that compile or parse but fail because the implementation does not yet exist, and reports test metadata. Works with any language or test framework.
    0
    installs
  35. Software Implementation · stencila bundle
    Write the minimal production code needed to make failing TDD tests pass (Green phase of red-green-refactor). Use when failing tests exist and production code must be written or modified to satisfy them. Reads and interprets failing test output, discovers codebase conventions (module layout, naming, import patterns, error handling, coding style), writes focused production code that satisfies test expectations without over-engineering, integrates new code with existing modules, types, and APIs, handles revision feedback from failed test runs, and verifies implementation compiles or parses before handing off to test execution. Works with any language or framework.
    0
    installs
  36. Software Test Execution · stencila bundle
    Run scoped tests for a TDD slice, determine the appropriate test framework and command, and report structured pass/fail results. Use when tests need to be executed after writing, implementing, or refactoring code. Reads test metadata, discovers the test framework if needed, executes the scoped test command, parses output into structured results, and reports whether tests passed or failed. Handles compilation errors, missing dependencies, timeouts, and works with any language and test framework.
    0
    installs
  37. Software Design Creation · stencila
    Create software design specifications for new features or standalone software. Use when the user needs help turning a brief idea into a concrete design spec by eliciting missing requirements, clarifying scope, defining users and constraints, outlining architecture and interfaces, identifying risks and assumptions, and writing acceptance criteria that developers can later use for planning and implementation.
    0
    installs
  38. Software Slice Selection · stencila
    Mark the just-completed slice or slice batch (if any), update the completed slices list, select the next unfinished execution unit from a delivery plan based on phase ordering and dependency constraints, and report whether more slices remain. Determines slice exhaustion, not full plan completion — does not verify plan-level Definition of Done items. Combines completion tracking with next-work selection in a single step. Reads plans from .stencila/plans/, parses phase and slice structure, validates package references against the codebase, and can normalize overly narrow plan slices by combining adjacent compatible slices into one execution unit.
    0
    installs
  39. Software Code Refactoring · stencila bundle
    Improve production code quality while preserving all existing test behavior. Commonly used for the Refactor phase of TDD red-green-refactor, but applicable to any codebase with tests. Use when production code works but needs cleanup — reducing duplication, improving naming, simplifying complexity, aligning with codebase style, extracting functions or types, or removing dead code. Discovers conventions, applies safe transformations, verifies compilation after each change, and produces a structured summary. Works with any language or framework.
    0
    installs