「trust」の検索結果

Audit agent skills, plugins, prompts, manifests, scripts, dependencies, and bundled assets for provenance, prompt-injection, permission, execution, exfiltration, persistence, and update risk. Use when evaluating a third-party skill before installing, enabling, updating, publishing, or distributing it; reviewing an untrusted SKILL.md, agent configuration, MCP integration, archive, or repository; comparing a package with a known-good version; or investigating unexpected tool, network, credential, or filesystem behavior.

日本語の概要は準備中です。原文の説明を表示しています。

Threat-model and harden AI agents, RAG systems, assistants, and tool-using workflows against direct, indirect, stored, cross-agent, and multimodal prompt injection. Use when reviewing an agent architecture, isolating untrusted content, constraining tools and egress, protecting secrets, adding injection-focused tests, investigating a suspected injection incident, or documenting residual prompt-injection risk.

日本語の概要は準備中です。原文の説明を表示しています。

Determine the TRUE cause of a failed retort run before attributing it. Ground-truth every failure (run its tests, read its agent logs, inspect its workspace) and classify it as an infrastructure false-fail, a genuine model miss, or an environment issue — never trust the gate verdict or a log signature alone. Use whenever a run is recorded failed (test_coverage=0 / gate fail), a pass rate looks low, or you're deciding whether a "failure" is real before reporting or proceeding.

日本語の概要は準備中です。原文の説明を表示しています。

Testing workflow skill for finding high-value test candidates, writing focused tests, generating realistic workloads, reviewing test value, and diagnosing test-suite health. Use for prompts about what to test next, adding or improving tests, reviewing whether a test is worth keeping, low-signal or flaky tests, workload scenarios, or test-suite trust. Do not use for general QA discussion unless the user wants a concrete testing workflow or artifact.

日本語の概要は準備中です。原文の説明を表示しています。

Facilitate a structured conversation to create a project-specific knowledge base document. Produces a knowledge-base.md that primes AI with the project's tech stack, architecture, trusted sources, and project structure. Use when the user says 'set up knowledge base', 'prime the project', 'onboard AI', 'create knowledge base', 'set up project context', or 'configure AI context'.

日本語の概要は準備中です。原文の説明を表示しています。

Load project-specific context -- tech stack, architecture overview, directory layout, trusted sources, and conventions -- so that all skills operate with awareness of what this project actually is. Use when a knowledge base document exists, or when the user asks about the project's tech stack, architecture, conventions, framework, directory layout, or says 'tell me about this project', 'what are we using?', 'what's our stack?', or 'what framework is this?'. Use the knowledge-priming-refiner to create a knowledge base document.

日本語の概要は準備中です。原文の説明を表示しています。

Research and collect social proof — testimonials, case studies, user reviews, social mentions, and community endorsements across platforms. Useful for marketing teams building trust content, landing pages, and sales collateral from authentic customer voices.

日本語の概要は準備中です。原文の説明を表示しています。

Audit paid-ad landing pages for message match, mobile experience, performance, accessibility, trust, forms, consent, tracking, security, and conversion friction. Use for landing-page audit, post-click experience, LP audit, conversion-rate optimization, form optimization, ad-to-page message match, redirects, blocked navigation, or requests involving private, loopback, link-local, or metadata IP destinations.

日本語の概要は準備中です。原文の説明を表示しています。

把凌亂的文件（會議逐字稿、多場會議混在一起的檔案、實驗／數據報告、論文、財報）變成可直接上台的設計感簡報的工作流。 Use this skill whenever the user wants to turn a document, meeting notes, transcript, report, spreadsheet, or raw data into slides / a presentation / a deck — 包括他們說「做成簡報」「整理成投影片」「幫我做一份簡報」「把這份報告變簡報」 「turn this into a presentation / slides / a deck」，即使沒有明說步驟。 也適用於「只有主題沒有素材」（如「幫我做一份 AI 發展趨勢的簡報」）——會先做主題研究再進入流程。 也適用於跨 session 銜接（「繼續做 xxx 的簡報」「接上次」）——會定位進度再銜接。 它會先清點內容並把敏感資料（姓名、薪資、競業條款、個資）攔進備援區、停下來等使用者確認範圍， 再把「有設計感」翻成具體色碼與版型規格、生成單一 HTML 簡報， 並對任何圖表用原始數據重算統計值、抓出原文寫錯的數字。 Also use it whenever the user needs figures or charts from a report recomputed from the source data rather than trusted blindly. 也支援 Keynote Magic Move 式的 Morph Transition 轉場（使用者說「Magic Move」「Morph」「物件飛過去的轉場」時）。

日本語の概要は準備中です。原文の説明を表示しています。

Hardens code against vulnerabilities. Use when handling user input, authentication, data storage, or external integrations. Use when building any feature that accepts untrusted data, manages user sessions, or interacts with third-party services.

日本語の概要は準備中です。原文の説明を表示しています。

Save a contact someone shared with you (a Contact card) as a local peer. agent-talk does NOT auto-import — review staged cards and import only ones from a peer you trust. `<user>` is this session's user directory (absolute path; from init).

日本語の概要は準備中です。原文の説明を表示しています。

Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.

日本語の概要は準備中です。原文の説明を表示しています。

Use when the user wants WorkBuddy or another agent to remember an account's positioning, voice, boundaries, data, trust assets, personal IP story, and content rules across sessions. Trigger phrases: "账号档案", "记住我的账号", "写入记忆", "人设垂直", "信任名片", "brand profile", "account memory", "style guide". Do not use for one-off post drafting unless profile data is missing.

日本語の概要は準備中です。原文の説明を表示しています。

Use when the user wants to start or reposition a Xiaohongshu account but is asking "what should I post" before clarifying monetization, timing, personal IP direction, or trust path. Trigger phrases: "小红书定位", "不知道做什么赛道", "怎么变现", "个人IP", "账号方向", "XHS positioning", "monetization first". Do not use for drafting a specific post; use topic or copy skills after positioning is clear.

日本語の概要は準備中です。原文の説明を表示しています。

Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result). Local by default; commit it when a reviewer needs the trail to trust the result. Use for /show-me-your-work, autonomous or multi-phase runs, or work a human reviews after stepping away.

日本語の概要は準備中です。原文の説明を表示しています。

Find what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it's safe because of by running real code instead of writing it up. Use for 'blast radius of X', 'what could this break', or reviewing a small diff you don't trust.

日本語の概要は準備中です。原文の説明を表示しています。

Apply when wiring validation, error handling, or framework adapters. Concentrate guards at system boundaries (CLI, config, network, external APIs); trust internal types and keep business logic in pure functions.

日本語の概要は準備中です。原文の説明を表示しています。

Use when the user wants to start or reposition a Xiaohongshu account but is asking "what should I post" before clarifying monetization, timing, personal IP direction, or trust path. Trigger phrases: "小红书定位", "不知道做什么赛道", "怎么变现", "个人IP", "账号方向", "XHS positioning", "monetization first". Do not use for drafting a specific post; use topic or copy skills after positioning is clear.

日本語の概要は準備中です。原文の説明を表示しています。

Use when the user wants WorkBuddy or another agent to remember an account's positioning, voice, boundaries, data, trust assets, personal IP story, and content rules across sessions. Trigger phrases: "账号档案", "记住我的账号", "写入记忆", "人设垂直", "信任名片", "brand profile", "account memory", "style guide". Do not use for one-off post drafting unless profile data is missing.

日本語の概要は準備中です。原文の説明を表示しています。

Plans a controlled experiment (A/B test) so its result can be trusted: writes the hypothesis, picks one primary metric and the guardrails, computes sample size and run time, specifies how visitors are assigned and when exposure is logged, and reads out the result with a confidence interval. Use when someone says "set up an A/B test", "split test this page", "how many visitors do I need", "how long should the experiment run", "is this result significant", "can I stop the test early", or wants to test a headline, price, layout or onboarding change against the current version.

日本語の概要は準備中です。原文の説明を表示しています。

Run AI agent and LLM evaluations in CI/CD pipelines — automated quality gates that fail the build when AI output quality drops. Use when someone asks to "test my AI agent", "add evals to CI", "catch prompt regressions", "compare models", "evaluate LLM output quality", "set up AI quality gates", or "benchmark my agent before deploying". Covers eval frameworks (Cobalt, Promptfoo, Braintrust), LLM-as-judge scoring, threshold-based assertions, and GitHub Actions integration.

日本語の概要は準備中です。原文の説明を表示しています。

Core marketing principles for startups. Covers positioning, messaging, channels, and growth. Focus on what works for resource-constrained teams. Battle scars included: I've watched startups burn $1M on Instagram ads because "that's where competitors are", seen "growth hacks" destroy brand trust overnight, and advised founders who scaled marketing before finding product-market fit. Contrarian take: Most startup marketing advice is backwards. The best marketing doesn't feel like marketing. Distribution comes before product features. And your first 100 customers should never come from paid ads. Use when "marketing strategy, positioning, messaging, customer acquisition, growth channels, brand, go-to-market, " mentioned.

日本語の概要は準備中です。原文の説明を表示しています。

The craft of communicating technical concepts clearly to developers. Developer communications isn't marketing—it's about building trust through transparency, accuracy, and genuine utility. The best devrel content helps developers solve real problems. This skill covers technical documentation, developer tutorials, API references, changelog writing, developer blog posts, and developer community engagement. Great developer communications treats developers as peers, not leads to convert. Use when "documentation, docs, tutorial, getting started, API reference, changelog, release notes, developer guide, devrel, developer relations, code examples, SDK docs, README, documentation, devrel, tutorials, api-docs, developer-experience, technical-writing, getting-started, changelogs" mentioned.

日本語の概要は準備中です。原文の説明を表示しています。

Expert in running the day-to-day operations of thriving communities. Covers moderation systems, onboarding flows, crisis management, scaling operations, and team management. The engine room that keeps communities healthy and safe. Use when "community operations, community moderation, community management, onboarding flow, crisis management, trust and safety, community team, " mentioned.

日本語の概要は準備中です。原文の説明を表示しています。