Build Secure Caffeine Inference Features
Caffeine applications need LLM access without exposing provider keys or misconfiguring canister outcalls. This skill provides the supported authenticated Motoko integration pattern.
安裝前請停止並請求確認。
請審查安裝計畫，並在變更檔案前取得使用者明確同意。
將此請求複製給你的智慧代理，其中包含權威 Skill 頁面和清單。
Review the Skillstore skill "extension-inference" from https://skillstore.io/skills/caffeinelabs-extension-inference.md and its manifest at https://skillstore.io/api/skills/caffeinelabs-extension-inference/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.你的智慧代理仍應顯示其計畫，並依安全政策請求必要確認。
當 AI Agent、爬蟲或腳本需要乾淨脈絡、而不是讀取完整頁面時，請使用這些連結。
正在使用「extension-inference」。 Add a summarization feature to my Caffeine application without asking users for an API key.
預期結果:
A backend integration plan using platform credentials, a router-based chat request, validated response handling, and a simple pending frontend state.
正在使用「extension-inference」。 Check whether my canister inference method is ready for production.
預期結果:
正在使用「extension-inference」。 Can this integration generate images and stream partial responses?
預期結果:
No. This host supports chat completions with complete responses, not image generation or streaming.
All 59 static findings are false positives caused by Markdown code formatting, documentation links, and relative links. However, the canonical public chat endpoint lacks authorization, quotas, and rate limits, creating a high-confidence resource-abuse risk.
分享版本化評估報告、中性徽章、嵌入卡片與引用。Skillstore 只報告證據，不判斷該 Skill 是否安全。
https://skillstore.io/skills/caffeinelabs-extension-inference/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report[](https://skillstore.io/skills/caffeinelabs-extension-inference?utm_source=security_passport_badge)<a href="https://skillstore.io/skills/caffeinelabs-extension-inference?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/caffeinelabs-extension-inference/security.svg" alt="Skillstore security assessment" loading="lazy"></a><iframe src="https://skillstore.io/embed/skills/caffeinelabs-extension-inference.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>caffeinelabs. (2026). extension-inference security audit report (audit version 1) [Author version 0.1.0]. Skillstore. https://skillstore.io/skills/caffeinelabs-extension-inference/audits/1@techreport{caffeinelabs-caffeinelabs-extension-inference-2026,
author = {caffeinelabs},
title = {extension-inference security audit report (audit version 1)},
institution = {Skillstore},
year = {2026},
number = {1},
url = {https://skillstore.io/skills/caffeinelabs-extension-inference/audits/1},
note = {Author version 0.1.0}
}cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "extension-inference security audit report (audit version 1)"
version: "0.1.0"
type: report
authors:
- name: "caffeinelabs"
date-released: "2026-08-29"
url: "https://skillstore.io/skills/caffeinelabs-extension-inference/audits/1"
identifiers:
- type: other
value: "skillstore:caffeinelabs-extension-inference:audit:1"
description: "Skillstore immutable audit report identifier"
Create a Motoko backend method that sends prompts through Caffeine Inference and returns validated text.
Check that credentials remain backend-only and requests use supported configuration, model, and replication settings.
Confirm whether chat completions meet product requirements before designing frontend states and backend interfaces.
Add a basic Caffeine Inference chat method to my Motoko canister. Use platform credentials and explain each changed file.
Integrate Caffeine Inference into this existing Motoko backend. Preserve current architecture and handle empty or missing response content.
Review this Caffeine Inference endpoint for credential exposure, replicated outcalls, unauthorized usage, cycle costs, and missing request limits.
Design a production Caffeine Inference workflow with authorization, per-principal quotas, prompt limits, usage accounting, retries, and user-facing failure states.
作者
caffeinelabs授權
MIT
作者版本
v0.1.0
Skillstore 修訂
r1
引用
2197f31c95ebfaf5ee9b50f95c8ecb53afcd7380
維護新鮮度
2026/8/29
使用量
1 次下載 · 0 次瀏覽
檔案結構
📄 SKILL.md
Expose Canister Data Through OQL
Structured canister data is difficult for intelligence agents to query safely. This skill adds OQL entities, schema discovery, query execution, relationships, and per-entity authorization.
Troubleshoot Motoko Migration Failures
Motoko migration errors can conflict with current source code and put deployed state at risk. This reference explains diagnostics and forward-only repairs while preserving migration history.
Build TMDb Movie and TV Features
Movie and TV integrations often fail because generated clients hide authentication, response shapes, and unsupported operations. This skill gives Caffeine developers a tested implementation path for catalog reads, credential handling, and service limits.
為 Caffeine AI 應用程式新增使用者核准機制
應用程式需要一套受控機制，在開放受保護功能前核准使用者存取。本技能提供後端核准檢查與前端管理工作流程的指引。
Query OQL Canisters with the ICP CLI
Writing OQL queries requires exact schema names, JSON types, Candid escaping, and careful pagination. This skill provides practical patterns for reliable, read-only canister queries.
Add Object Storage to Caffeine AI Apps
Large files need storage beyond Internet Computer canister limits. This skill guides Caffeine AI projects through backend integration, browser uploads, cached display, downloads, and troubleshooting.
建構可投入生產環境的 AI 產品功能
由 sickn33
當提示詞、檢索、成本與安全被視為事後考量時，AI 功能往往會失敗。此技能會引導可靠 LLM 功能的生產環境模式。
建置生產級 ML 與 RAG 系統
由 davila7
生產級 ML 系統難以一致地設計、部署及監控。此技能可協助 MLOps、LLM 整合、RAG 架構及本機工作流程骨架建立。
Review Defects and Verify Root-Cause Repairs
由 aakashh242
Reviews can miss failure conditions or accept fixes without reliable evidence. Gauntlet guides scoped adversarial reviews, authorized repairs, and revision-bound verification within a finite budget.
分析跨框架的測試品質
由 C0ntr0lledCha0s
薄弱的測試會隱藏缺陷、拖慢重構，並讓覆蓋率數字產生誤導。此技能會分析測試套件，並針對可靠性、可維護性、覆蓋率與突變測試提供優先排序的指引。
精通進階 Git 工作流程
由 AutumnsGrove
複雜的 Git 歷史可能很難在不遺失工作的情況下修復。此技能提供 rebase、衝突、bisect、復原和分支管理的引導式工作流程。
建立可靠的 Jest 測試套件
由 C0ntr0lledCha0s
Jest 專案通常需要一致的設定、模擬和斷言模式。此技能為 JavaScript、TypeScript、React 和 Vitest 風格的測試提供聚焦的指引、範本和檢查。