axhub-prototype-context
Skill145 starsChanged 19 days agoMITView on GitHub
Use when an annotated prototype URL exposes PRD, directory, annotation, or source context that an AI Agent needs for review, implementation planning, production work, source handoff, or optional review-report submission.
In this repository14 other files it gives its agents.
- axhub-annotation-standaloneSkill
- axhub-commentarySkill
- build-design-systemSkill
- china-customer-researchSkill
- clone-pageSkill
- design-system-searchSkill
- extract-axure-dataSkill
- extract-page-dataSkill
- figma-content-operatorSkill
- generate-themeSkill
- git-repo-beginner-guideSkill
- mcp-installerSkill
- react-to-figma-makeSkill
- search-design-systemSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 13
Wait until the app renders, then poll briefly for window.__AXHUB_ANNOTATION_SOURCE__.
- Very specific: line 15
When full Markdown annotation text is needed, also read window.__AXHUB_ANNOTATION_SOURCE_DOCUMENT__?.markdownMap.
- Distinctive: line 16
If the snapshot is missing, report the URL, page title, relevant console errors, and that the annotated prototype context snapshot was not …
- Very specific: line 17
If the user asks to submit a review report back to Axhub Make, read references/review-report-submission.md.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Annotated Prototype Context
Read the published context from an annotated prototype so an AI Agent can understand its pages, PRD, annotations, and available source before continuing with review or production work. Treat the page as read-only unless the user asks to submit a review report back to Axhub Make.
Workflow
- Open the requested annotated prototype URL with Playwright, Browser, Chrome, or an equivalent tool that can evaluate page JavaScript.
- Wait until the app renders, then poll briefly for
window.__AXHUB_ANNOTATION_SOURCE__. - Evaluate and return that value. Do not modify the object or write anything back to
window. - When full Markdown annotation text is needed, also read
window.__AXHUB_ANNOTATION_SOURCE_DOCUMENT__?.markdownMap; report when it is unavailable. - If the snapshot is missing, report the URL, page title, relevant console errors, and that the annotated prototype context snapshot was not published.
- If the user asks to submit a review report back to Axhub Make, read
references/review-report-submission.md.
Minimal page evaluation:
await page.waitForFunction(() => window.__AXHUB_ANNOTATION_SOURCE__, { timeout: 10000 });
const source = await page.evaluate(() => window.__AXHUB_ANNOTATION_SOURCE__);What To Report
- Page navigation from
source.directory(folder,route, andlinknodes). - PRD/document outline and article bodies from
source.documents(folder,markdown, andhtmlnodes). Read each Markdown article's inlinemarkdownand each HTML article's inlinehtml; report a missing body when onlymarkdownPathorhtmlPathis present. Also check legacydirectorydocument nodes when present. - Annotation count and the important node fields:
id,title,pageId,locator,annotationText,aiPrompt,color, andcontrols. - Markdown annotation bodies for
source.nodeswithhasMarkdown: trueare in the source document'smarkdownMap[node.id]; do not mistake them for PRD articles. Includesource.targetswhen explaining document links to unannotated page elements. - Source handoff from
source.sourcewhen present. Reportrootandmanifest; when source is needed, read the manifest and relevant files viaroot. - Mention whether images are attached by checking
images.length; do not download images unless the user asks.
Data Shape
type AnnotationSourceRuntimeSnapshot = {
directory: AnnotationDirectory | null;
documents: AnnotationDocumentDirectory | null;
nodes: AnnotationNode[];
targets?: AnnotationElementTarget[];
presentation?: AnnotationSourcePresentation;
source?: {
root?: string;
manifest?: string;
};
};directory.nodesis the page navigation tree. New PRD documents belong indocuments.nodes; older sources may still containmarkdownnodes indirectory.documents.nodescontainsfolder,markdown, andhtmlnodes. Readable Markdown nodes have an inlinemarkdownbody and may includemarkdownPath; HTML nodes have an inlinehtmlbody and may includehtmlPath. In Make, these files typically live undersrc/prototypes/<prototype-id>/docs/. The host must inline their contents before publishing the snapshot; the runtime does not fetch document files from their paths.readerMode: "full" | "split"controls an article's initial layout; omitted values default tosplit. Documents and pages have separate directory entries.- Relative links between articles resolve through unique, normalized
markdownPathorhtmlPathvalues. Standard HTML#anchorlinks are bridged to the reader so they use the same controlled in-document navigation as Markdown, while a link such as[View element](#axhub-target:element-id)refers to an annotation node or a lightweighttargetsentry in both Markdown and HTML. Cross-page positioning requires host routing (onTargetRoute, or a matching directory route fallback); the snapshot alone does not establish that navigation works. nodesis the full annotation list, independent of current page, selected state, and color filter.- Each annotation node includes
id,index, optionaltitle, optionalpageId,locator,aiPrompt,annotationText,hasMarkdown,color,images, optionalcontrols,createdAt, andupdatedAt. sourceis only a source-code discovery reference. In HTML published with source included,manifestpoints tosource/manifest.json; resolve its paths relative tosource.root.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

