Borrowing it
Nothing to install: this file belongs to ianlkl11234s/mini-taiwan-pulse. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ianlkl11234s/mini-taiwan-pulse/master/.claude/skills/layer-onboarding/SKILL.mdgit clone --depth 1 https://github.com/ianlkl11234s/mini-taiwan-pulseWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ianlkl11234s/mini-taiwan-pulse/layer-onboarding)<a href="https://agentmods.dev/skills/ianlkl11234s/mini-taiwan-pulse/layer-onboarding"><img src="https://agentmods.dev/badge/skills/ianlkl11234s/mini-taiwan-pulse/layer-onboarding/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ianlkl11234s/mini-taiwan-pulse/layer-onboarding"><img src="https://agentmods.dev/badge/skills/ianlkl11234s/mini-taiwan-pulse/layer-onboarding.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 168 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00172 | $0.02774 |
| Opus 5 | $0.00086 | $0.01387 |
| Sonnet 5 | $0.00034 | $0.00555 |
| Haiku 4.5 | $0.00017 | $0.00277 |
Grade A, and why
layer-onboarding scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Layer Onboarding SOP
目的:把「從 taipei-gis-analytics 資料落地 → mini-taiwan-pulse 上線」變成無法漏項的流程。
何時觸發
- 「新 layer 要接」「PMTiles 好了要怎麼上」
- 「這 layer 點怎麼少了」「這 layer 為什麼有些點顯示不出來」
- 「透明度 / 半徑 / popup / 圖例 該怎麼設」
- 「上游改了欄位下游要動嗎」
- Review 一個剛完成的 layer 前
步驟總覽
Step 0 規劃 (feature 資料夾 + upstream handoff)
Step 1 資料完整性驗收 (count / attrs / 檔名契約)
Step 2 接線 (走 /new-layer 或手動:manifest 一筆 + spec 一筆 + 邏輯檔)
Step 3 UX baseline 套用 (radius / opacity / cluster / min-zoom)
Step 4 四鐵則自檢 (slider / legend / popup / dropdown)
Step 5 跨 repo 對齊 (handoff 反向引用 + commit hash)
Step 6 驗收 (tsc / test / browser All Off 單測)
Step 7 收尾 (changelog + backlog 標 ✅)
Step 0 — 規劃
- 選 slug:kebab-case,例如
air-quality-station - 開 upstream handoff(若還沒):
taipei-gis-analytics/docs/handoff/<slug>.md - 開 downstream feature 資料夾:
cp -r docs/features/_TEMPLATE docs/features/<slug> - 開 branch:
git checkout -b feat/<slug>
Step 1 — 資料完整性驗收(⚠️ 最常漏的地方)
從 upstream 拿到產物後先驗數字對得上,不要急著接線。
PMTiles
# 檢查 tile 數 + zoom 範圍
tippecanoe-decode public/xxx.pmtiles | head -20
# 檢查 keep_attrs 是否帶到(隨機挑 tile)
tile-join --version && python3 -c "
import subprocess
# 從 PMTiles 抽 feature 屬性看 keep_attrs 齊不齊
"
常見漏項:
- keep_attrs 沒帶 → 前端 popup 空白 / 分色失效 → 回上游改 tippecanoe 參數重出
- 扁平檔名契約斷了 → nginx 找不到 → 檢查
public/命名(不要加子資料夾)
GeoJSON
# 點數
jq '.features | length' public/xxx.geojson
# 屬性 key 齊不齊
jq '.features[0].properties | keys' public/xxx.geojson
Supabase RPC
-- 直接跑 EXPLAIN ANALYZE
EXPLAIN (ANALYZE, BUFFERS) SELECT * FROM public.get_xxx(...);
若 > 1s 或 > 10k rows → 立刻套 pre-aggregate pattern(見 supabase-optimize skill)。
座標系統
|Response_X| > 1000 → 是 TWD97 TM2 → 要轉 WGS84。
Step 2 — 接線
優先走 /new-layer <slug> slash command(自動產骨架 + 跑 tsc / vitest)。
若手動,強制順序(CLAUDE.md §5 / development-rules §4)—— ⚠️ 2026-08-12(AR-22 Phase 4)起登記簿不再手寫:
src/types/index.ts→LayerVisibility加 key(可點選再加FeatureInfo["layerType"])src/data/layerManifest.ts→ 一筆完整 entry。LAYER_COLORS/LAYER_ICONS/ THEMES 的 LayerDef /LAYER_LABELS/UPSTREAM_REGISTRY全部由它派生,不要手寫- ⚠️
legend/popup/params寫null= 豁免鐵則 2/3/1 → 必須同步layerConsistency.test.ts的對應 ledger 並寫理由,否則測試紅
- ⚠️
src/components/sidebar/layerCatalog.ts→ THEMES 對應子群加一行fromManifest("key")(只放位置;SECTIONS / LAYER_LABELS 自動派生)src/data/layerParamsSpec.ts→ 一筆key: [ opacitySlider("keyOpacity", 0.8), … ](⚠️ 禁去useLayerParamsRuntime.ts加useState/case/ deps)src/data/xxxLoader.ts→ loader + loadingRegistry(⚠️ 禁靜默 rpc().then())src/hooks/useXxxLayer.ts→ React hook(⚠️ 動態圖層禁 currentTime 進 deps)src/map/overlayRegistry.ts或 CustomLayer(sourceId要與 manifest 的source逐字相同)src/App.tsx→ 接線- 預設開啟的層才需要碰
src/state/layerVisibilityStore.ts的DEFAULT_ON(現為空集合;key 全集自動派生)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 204 lines · 172 tokens per session scan A 9e219952f609
layer-onboarding is a skill published in the GitHub repository ianlkl11234s/mini-taiwan-pulse (504 stars, last pushed yesterday), licensed MIT. It adds 172 tokens to every session and 2,774 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
claude-api-in-prototypes
Call Claude from your HTML artifacts via window.claude.complete.
core
Core package for defining schemas, catalogs, and AI prompt generation for json-render. Use when working with @json-render/core, defining schemas, creating catalogs, or building JSON specs for UI/video generation.
langchain
Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG…
playwright
Playwright E2E testing patterns. Trigger: When writing Playwright E2E tests (Page Object Model, selectors, MCP exploration workflow). For Prowler-specific UI conventions under ui/tests, also use prowler-test-ui.
thinking-orbs
Add accessible animated AI loading and agent-status indicators with the React thinking-orbs library. Use when a chat, copilot, voice, search, generation, or tool-running interface needs a semantic working, searching, solving, listening, composing, or shaping state; when replacing a generic spinner with an AI activity…
globe-gl
Use when implementing globe.gl (Globe.GL) for 3D globe data visualization with WebGL/ThreeJS, including setup, data layers (points, arcs, polygons, labels), and integration patterns in plain HTML or React.