deneb-authoring
Author and debug Deneb visuals for Power BI, including dataset binding, PBIR persistence, report-theme integration, interactivity, and template metadata.
Skill by MylesMCook
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/mylesmcook-deneb-authoring
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: documents
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/deneb-authoring
What's inside
- Skill name
deneb-authoring- Description
- Author and debug Deneb visuals for Power BI, including dataset binding, PBIR persistence, report-theme integration, interactivity, and template metadata. Use this first for Deneb, Power BI, PBIR, report-theme, cross-filter, cross-highlight, or dataset-binding requests. Start with host constraints, default to Vega-Lite, and switch to raw Vega only when the requirement clearly needs lower-level control.
- License
- MIT
- Instructions
- 69 lines in SKILL.md · view on GitHub
Files (9)
- SKILL.md
- openai.yaml · agents/
- editor-workflow.md · references/
- interactivity.md · references/
- overview-and-dataset.md · references/
- pbir-guide-1-9.md · references/
- performance-and-theme.md · references/
- template-structure.md · references/
- templates-and-usermeta.md · references/
SKILL.md (first lines)
# Deneb Authoring Use this skill for Deneb in Power BI: dataset binding, PBIR, templates, interactivity, theme alignment, and editor workflow. ## Use when - The task is about Deneb, Power BI, PBIR, report-theme integration, dataset binding, template metadata, or Deneb interactivity. - You need to author or debug a Vega or Vega-Lite visual that must run inside Deneb. - The request mentions cross-filtering, cross-highlighting, Power BI tooltips, report themes, or editor workflow in Deneb. ## Do not use when - The task is plain Vega or plain Vega-Lite work outside Deneb and Power BI. - The user only needs generic chart grammar advice with no Deneb host constraints. - The requirement is a host-agnostic Vega or Vega-Lite example that should not be shaped by Power BI behavior. ## Precedence / handoff - This skill leads for Deneb and Power BI visual work, even when the embedded grammar is Vega or Vega-Lite. - Lock host constraints first: `dataset` binding, row identity, external-resource limits, interactivity implications, runtime/version caveats, and PBIR persistence rules. - Default to Vega-Lite after host constraints are clear. - Switch to raw Vega only when Vega-Lite cannot express the required behavior cleanly, especially for lower-level signal or event-stream work. ## Required reasoning steps 1. Confirm the Deneb host context, provider choice, and whether PBIR or template metadata is involved. 2. Lock the `dataset` contract, actual field/display names, and any field sanitization concerns before writing encodings. 3. Identify whether interactivity depends on preserving row identity and call out transforms or aggregation that could break reconciliation. 4. Choose Vega-Lite by default; escalate to raw Vega only when the requirement justifies it. 5. Produce the smallest working Deneb-ready spec or PBIR payload first, then add optional interactivity, theme integration, or template metadata. ## Output contract Always return: - the chosen grammar and why - assumptions about host context, data shape, field names, and provider/runtime - a minimal working Deneb-ready spec first - optional refinements separately - version caveats when Deneb's embedded runtime or PBIR behavior may lag upstream docs - likely host-specific risks - the next debugging step if the first attempt fails ## Version policy - Prefer stable Deneb docs over canary or `next` docs. - Pin PBIR guidance in this skill to the stable 1.9 line for this pass. - Treat Deneb's embedded Vega or Vega-Lite runtime as authoritative over upstream grammar docs when features conflict. - Keep copied reference text short and curated; do not mirror large doc pages. ## Known failure modes - Forgetting to bind `dataset` or using the wrong field names from the Values well. - Mutating or aggregating data in ways that break row reconciliation for Power BI interactivity. - Assuming certified Deneb visuals can fetch external resources. - Using upstream Vega or Vega-Lite features that are newer than Deneb's embedded runtime. - Mixing plain Vega or Vega-Lite template JSON with Deneb template metadata rules. ## Load references - Load `references/overview-and-dataset.md` first for dataset binding, field naming, and host constraints. - Load `references/editor-workflow.md` for advanced editor workflow, provider switching, debug panes, and runtime/version checks. - Load `references/interactivity.md` when selection, highlight, tooltips, or row reconciliation matter. - Load `references/performance-and-theme.md` when row limits, renderer choice, or report-theme integration matter. - Load `references/pbir-guide-1-9.md` for PBIR persistence and property structure. - Load `references/template-structure.md` for Deneb template metadata shape. - Load `references/templates-and-usermeta.md` when importing, exporting, or adapting templates.
From MylesMCook/mcook-skills, MIT.
More from MylesMCook/mcook-skills
- 0.529score
base-ui-stylex
MylesMCook
Build, review, or debug React components using Base UI and StyleX with live official documentation lookup and source citations.
SkillBFreshness: BClaude Code +9 - 0.524score
archive-stale-codex-tasks
MylesMCook
Inspect and safely archive stale idle Codex tasks when the user asks to clean up old Codex tasks, threads, or processes.
SkillBFreshness: BClaude Code +9 - 0.479score
american-inkblot-illustrations
MylesMCook
Use when creating, planning, prompting, generating, or editing quirky US English article illustrations: blog, newsletter, essay, Notion, document body art…
SkillCFreshness: CClaude Code +9 - 0.479score
adversarial-review
MylesMCook
Use this skill when you need a serious code review, diff review, or implementation-plan review from independent reviewers.
SkillCFreshness: CClaude Code +9 - 0.450score
goalie
MylesMCook
Use when the user wants to turn a rough idea, dirty goal, messy long-run prompt, sidechat thought, or under-scoped Codex task into clean Goal objective text…
SkillCFreshness: CClaude Code +9 - 0.450score
fugu-second-opinion
MylesMCook
Use only when the user explicitly invokes $fugu-second-opinion or asks for Sakana Fugu or Fugu Ultra by name to provide a second opinion, external model…
SkillCFreshness: CClaude Code +9 - 0.414score
browser-probe
MylesMCook
Exploratory browser QA for real web apps.
SkillDFreshness: DClaude Code +9 - 0.414score
laws-of-software-los
MylesMCook
Use this skill for software architecture, system design, ADRs, migration plans, code review, refactors, APIs, data changes, reliability, performance…
SkillDFreshness: DClaude Code +9 - 0.414score
dogfood
MylesMCook
Formal repro-first browser QA for real web apps.
SkillDFreshness: DClaude Code +9 - 0.414score
electron-best-practices
MylesMCook
Practical Electron guidance for building and maintaining desktop apps with clear main process, renderer, preload, IPC, BrowserWindow, packaging, Electron…
SkillDFreshness: DClaude Code +9 - 0.414score
agent-skills-architect
MylesMCook
Create, audit, improve, rewrite, or package Agent Skills and Codex skills.
SkillDFreshness: DClaude Code +9 - 0.411score
brainerd
MylesMCook
Initialize or update a repo-local `brain/`: create the `brain/` folder and managed `AGENTS.md` block, reflect durable repo learnings into principles or notes…
SkillDFreshness: DClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Mar 26, 2026 (7 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/MylesMCook/mcook-skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from MylesMCook
- 0.529score
base-ui-stylex
MylesMCook
Build, review, or debug React components using Base UI and StyleX with live official documentation lookup and source citations.
SkillBFreshness: BClaude Code +9 - 0.524score
archive-stale-codex-tasks
MylesMCook
Inspect and safely archive stale idle Codex tasks when the user asks to clean up old Codex tasks, threads, or processes.
SkillBFreshness: BClaude Code +9 - 0.479score
american-inkblot-illustrations
MylesMCook
Use when creating, planning, prompting, generating, or editing quirky US English article illustrations: blog, newsletter, essay, Notion, document body art…
SkillCFreshness: CClaude Code +9 - 0.479score
adversarial-review
MylesMCook
Use this skill when you need a serious code review, diff review, or implementation-plan review from independent reviewers.
SkillCFreshness: CClaude Code +9 - 0.450score
fugu-second-opinion
MylesMCook
Use only when the user explicitly invokes $fugu-second-opinion or asks for Sakana Fugu or Fugu Ultra by name to provide a second opinion, external model…
SkillCFreshness: CClaude Code +9 - 0.450score
goalie
MylesMCook
Use when the user wants to turn a rough idea, dirty goal, messy long-run prompt, sidechat thought, or under-scoped Codex task into clean Goal objective text…
SkillCFreshness: CClaude Code +9
Cite this page
deneb-authoring skill. Agent Mart. https://agentmart.dev/skills/mylesmcook-deneb-authoring (last updated 2026-10-24)