core
Skill3 starsChanged 8 months agoMITView on GitHub
Extraction schemas, QC criteria, provider routing rules, and page estimation for the reading-assistant plugin
29 other projects use a version of this.
Adopted by
Most recently taken up by
- oberemokis/skillstheir own version, first seen Nov 15, 2026
- gkurt/ai-soulstheir own version, first seen Nov 8, 2026
- ouestlabs/audio-uitheir own version, first seen Nov 2, 2026
- vercel-labs/json-rendertheir own version, first seen Oct 29, 2026
- fishzjp/qa-skillstheir own version, first seen Oct 21, 2026
- ryu111/claude-workflow-configtheir own version, first seen Oct 20, 2026
Used with
Projects with it also use ts-core, native-ui and 3 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
VercelSkillts-core
Authoring guide for the primary Native SDK app-logic path: TypeScript app cores - Model, Msg, update, and the pure functions they call, written in the closed app-core subset, checked by the @native-sdk/core frontend, and compiled ahead-of-time to native code by the external core compiler. Use for new apps unless the user explicitly chose Zig, when writing or modifying a src/core.ts app core, fixing subset checker errors (NS1001-NS1069), or deciding how to express state, messages, text (bytes and the byte-text string methods), text input, continuous controls (sliders, scroll), effects (Cmd), subscriptions (Sub), the host-event wiring channels (frameMsg, keyMsg, pinchMsg, dropMsg, appearanceMsg, chromeMsg, envMsgs, app manifest assets), derived values, the view_unbound lint opt-out, local mutation of owned arrays, or how to split a core into modules under src/ (relative imports, namespace imports, @native-sdk/core/text, @native-sdk/core/events). Use ts-services alongside this guide for src/services work.
Also in 3 projects that use this
VercelSkillnative-ui
Authoring guide for the Native markup (.native) view tier of native-rendered Native SDK apps. TypeScript cores are the default and use this skill together with ts-core; Zig cores are an explicit alternative and this guide labels their lower-level UiApp recipes. Use when building or modifying native UI (widgets, layout, bindings, messages), writing .native files, wiring views to Model/Msg/update, testing markup views, or verifying a native app through the automation harness.
Also in 3 projects that use this
- +3 more from vercel-labs
Other versions29 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 29
- vercel-labs/agent-browser★ 51ksame name
- vercel-labs/json-render★ 20ksame name
- microsoft/data-formulator★ 17ksame name
- microsoft/RD-Agent★ 15ksame name
- vercel-labs/native★ 7.8ksame name
- vercel-labs/zero-native★ 7.8ksame name
- ouestlabs/audio-ui★ 202same name
- vercel-labs/issue-graph★ 188same name
- vercel-labs/xref★ 188same name
- fishzjp/qa-skills★ 64same name
19 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository2 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- obsidian-zettelkastenSkill
The file
Files
Reading Assistant Core
Extraction Categories & JSON Schemas
Fact
{
"category": "fact",
"text": "the factual claim",
"chapter": 0,
"page_estimate": 1,
"context": "surrounding paragraph",
"confidence": "high|medium|low"
}Example
{
"category": "example",
"text": "the example/anecdote",
"chapter": 0,
"page_estimate": 1,
"context": "surrounding paragraph",
"illustrates": "what concept this illustrates"
}Metaphor / Analogy
{
"category": "metaphor",
"text": "the figurative language",
"chapter": 0,
"page_estimate": 1,
"source_domain": "what it compares from",
"target_domain": "what it compares to",
"context": "surrounding paragraph"
}Quote / Punch Line
{
"category": "quote",
"text": "exact quote from source",
"chapter": 0,
"page_estimate": 1,
"speaker": "author or character name",
"context": "surrounding paragraph",
"verified": false
}Glossary Term
{
"category": "glossary",
"term": "the term",
"definition": "as used in this book",
"chapter_first_seen": 0,
"related_terms": ["term1", "term2"]
}Page Estimate Derivation
page_estimate = chapter_start_page + (start_char / chars_per_page)
where:
chapter_start_page = sum(prior_chapter_word_counts) / 250
chars_per_page = 1500QC Thresholds
| Check | Pass | Warn | Fail |
| Quote verification | ≥95% match at ≥0.95 | ≥80% | <80% |
| Summary coverage | ≥80% topics covered | ≥60% | <60% |
| Category accuracy | ≥90% correct | ≥75% | <75% |
| Review fidelity | ≥90% traceable | ≥70% | <70% |
Overall: FAIL if ANY check FAIL. WARN if any WARN, none FAIL. PASS if all PASS.
Provider Routing
| Model spec | Provider | Behavior |
| haiku, sonnet, opus | Claude | Agent handles natively |
ollama:<model> | Ollama | Call scripts/llm_provider.py generate via Bash |
openai:<model> | OpenAI | Call scripts/llm_provider.py generate via Bash |
For external models: pipe prompt via stdin, read result from stdout.
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.

