「guard」の検索結果

Analyzes hazards in systems or AI agents: STPA, guardrails, safety cases, incident analysis. Use when an agent can take actions or send payments.

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。

Configures Claude Code hooks and Codex hooks.json/notify. Use when adding PreToolUse guards, Stop hooks, managed hooks, format-on-save, preflight, audits, or worktree/budget hooks.

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。

Designs approval and sandbox policy for local coding agents: permission modes, isolation, network and destructive-command guards. Use when setting approvals. Not cloud sandboxes.

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。

Prospect discovery, enrichment, scoring, and reporting against an Ideal Customer Profile

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 needs to run GitNexus CLI commands like analyze/index a repo, check status, clean the index, generate a wiki, or list indexed repos. Examples: "Index this repo", "Reanalyze the codebase", "Generate a wiki"

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。

Fetches YouTube video metadata and transcripts (genesis web_fetch MCP tool first, yt-dlp via Bash as the fallback). Activate when the user shares a YouTube URL (youtube.com, youtu.be), asks to 'fetch this video', 'get the transcript', 'what does this video say', 'summarize this YouTube video', or references video content that needs to be retrieved. Also activate when processing multiple YouTube URLs in batch. Do NOT use for non-YouTube video platforms, local video files, or audio-only podcast URLs.

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。

Evidence-driven web and open-source research for questions that require multiple sources, factual verification, comparisons, or an adopt/adapt/build decision. Use for substantial research in foreground sessions, the genesis-researcher subagent, and research-profile background sessions. Skip for a single stable fact or a known URL that only needs fetching.

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。

Foundational voice authority and AI humanizer — writes content in the user's authentic voice with built-in AI detection, and supports stealth / anti- attribution writing (forum personas, anonymous posts, "write as not-me"). Use when asked to write/draft/generate content, invoke /voice, /write-as-me, or /humanize, run voice calibration, check "does this sound like me?", "make this sound human" / "de-AI this", "write a forum post as [persona]", or run AI detection ("does this sound like AI?", "check for AI patterns", "anti-slop check"). Do NOT use this skill for code, technical docs, or any output the user has not asked to be written in their voice — code styling defers to the separate code-voice skill.

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。

This skill should be used when a session's job is POST-MERGE VERIFICATION — taking merged PRs and establishing whether the change actually does what it claimed, then recording the result against its `pr_verifications` obligation. "validate the merged PRs", "work the verification backlog", "did that PR actually work", "run the post-merge E2E". It owns the obligation ledger the repo-pulse worker fills. Do NOT load it for building a change and opening its PR (that is `genesis-development`), or for driving open PRs to merge (that is `closing-session`).

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。

Evaluate content for personal relevance to the user using the user model

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 Codex needs Genesis capabilities through MCP without joining Genesis's session lifecycle. Covers tool selection, explicit state changes, and session-boundary limits.

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。

Download, transcribe, analyze, and clip video content — vertical shorts, captions, thumbnails

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。

Anti-detection behaviour for Genesis browser automation - what the Camoufox tools already do, what the agent must still do, Cloudflare Turnstile handling, and per-site notes for bot-hostile sites

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。

Post-interaction retrospective analysis — use after completing a significant task, conversation, or phase to extract lessons, identify process improvements, and update procedures

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。

Deep research on a topic — use when investigating unfamiliar domains, answering complex questions requiring multiple sources, or when an evaluation flags something for deeper analysis

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。

This skill should be used when the user asks to "research this company", "look into this person", "find the best angle for reaching out to", "who should I contact at [company]", "what does [company] care about", or when preparing outreach to a specific target. Also triggered by "help me prepare for an interview with [company]" or "I want to apply to [company]". Combines lead-generation intelligence with LinkedIn-specific approach planning.

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。

OSINT investigation — discover, track, and report on people, companies, and technologies

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。

First-run onboarding — guides new users through Genesis setup on their first CC session. Configures user profile, essential API keys, Telegram, GitHub backup, and service verification. Triggered automatically while the install is not yet FUNCTIONAL (the setup floor — Claude Code login + an LLM key + an embedding key — is unmet), not merely while ~/.genesis/setup-complete is absent. Re-runnable by asking Genesis to "run setup" or "reconfigure [section]".

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。

Resolve obstacles using fallback chains — use when an approach fails, a dependency is unavailable, an API returns errors, or a task is blocked and needs an alternative path forward

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。

This skill should be used when the user asks to "optimize my LinkedIn profile", "update my LinkedIn headline", "rewrite my LinkedIn summary", "improve my LinkedIn about section", or when Genesis identifies that the user's profile doesn't align with their current goals or target audience.

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。

This skill should be used when the user asks to "write a LinkedIn post", "draft a post about", "help me post on LinkedIn", "create LinkedIn content", or when Genesis proactively generates post ideas during surplus compute. Also triggered by content calendar execution or when the user shares a topic they want to write about.

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。

This skill should be used when the user asks to "write a hook for my post", "give me opening lines", "help me start this LinkedIn post", "I need a better opener", or when the linkedin-post-writer skill needs strong opening options. Also triggered by "my posts aren't getting clicks" or "how do I get people to read my posts".

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。

This skill should be used when the user asks to "write a LinkedIn message", "draft a connection request", "help me reach out to someone on LinkedIn", "write an InMail", "message this person", or when the prospect-researcher skill identifies a high-value contact worth reaching out to. Also triggered by "how should I approach [person/company]" in a LinkedIn 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。

This skill should be used when the user asks to "plan my LinkedIn content", "create a content calendar", "what should I post about this week", "plan my posting schedule", or when Genesis proactively suggests a weekly content plan during surplus compute. Also triggered by "I need post ideas" or "I don't know what to write about".

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。