6,713 件 ・ 関連度順
概要と使いどころ
Delegate implementation (or, when explicitly requested, research) to GPT-6.1 Sol (high reasoning; xhigh on request) via Codex CLI. Claude plans, orchestrates, and reviews; Sol writes the code.
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。
麦哲伦舵手（彼得·林奇）投资智能体。以 GARP（Growth at a Reasonable Price）视角寻找"十倍股"，关注 PEG 比率、营收增长加速和商业模式理解，输出 [林奇分析信号]。 在 Phase 1 分析阶段由 hedge-fund-lead 主理人并行调用。 擅长：PEG 比率、十倍股特征识别、营收增长加速、品类扩张潜力、分拆/困境反转机会。
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。
INCIDENT MODE: Bypass standard PRD/Planning phase for emergency hotfixes. Requires immediate execution, a post-mortem ticket, and a patch release note.
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。
Digital Garden & Visual Architect. Use this agent to manage the Obsidian Knowledge Base, create visual logic maps via JSON Canvas, and maintain the automated development journal. It bridges the gap between abstract ideas and structured documentation. When the host supports them, use the Obsidian-focused skills and integrations for CLI, Bases, Markdown, Canvas, and defuddling workflows. When the host supports them, use the Obsidian-focused skills and integrations for CLI, Bases, Markdown, Canvas, and defuddling workflows.
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 an operational workflow, release procedure, incident pattern, or support process needs to be captured as a repeatable runbook.
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。
Design, validate, and optimize schema.org structured data for eligibility, correctness, and measurable SEO impact.
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 behavioral science and mental models to revenue (cuan) decisions, prioritized using a psychological leverage and feasibility scoring system.
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 a release needs launch framing, sequencing, channel choices, and rollout logic across product, growth, and support.
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 documentation, READMEs, release notes, or operating docs have drifted from the current shipped behavior and need synchronized updates.
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 a feature launch needs experiment design, test sequencing, rollout guardrails, and measurement logic before exposure to users.
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。
Reviews construction plans for architecture consistency and implementation feasibility. Use when reviewing implementation plans before approval.
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 a feature or code change made by Claude is complete and the developer wants to confirm they actually understood it before shipping. Triggers on "handoff", "quiz me", "comprehension check", "did I understand this", "verify I read the code", "test my understanding", or after finishing a feature when the developer wants to take ownership of AI-written code. Also triggers on requests for an interactive or clickable quiz ("interactive mode", "let me answer with the mouse", "mode interactif", "je réponds à la souris"). Quizzes the developer on WHERE the logic lives (file/function) and WHY decisions were made (trade-offs, behavior, debugging), with the number of questions scaled to the size of the change. Multiple-choice questions are clickable by default (asked through `AskUserQuestion`) and fall back to typed answers. Points to file:line on wrong answers, allows one retry, then reveals the answer, and ends with a score plus the weak areas to re-read. Conducts the quiz in the developer's language.
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。
Maintain Keep a Changelog files with Hyalo's changelog profile and add/release commands.
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 a dogfooding session for hyalo — build from source, exercise the CLI against real knowledgebases (own KB, MDN, GitHub Docs, VS Code docs), find bugs, verify recent fixes, assess UX, measure performance, and write a structured report. Use this skill whenever the user says /dogfood, "dogfood", "run a dogfood session", "test hyalo against real data", or wants to exercise hyalo on real knowledgebases to find issues.
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 evidence needs grading before anyone reasons from it — the user asks "how reliable is this?", "grade this source", "check this report", "can I trust this article?", "is this corroborated?", or hands over a URL, a pasted report or a Liberty91 event ahead of an ACH or assessment. The Quality of Information Check from the CIA Tradecraft Primer, adapted for vendor and press CTI reporting. Resolves each document to its originating source, splits it into claims, and grades every claim on two written elements, access level (how the source knows) and claim support (what backs the statement), with a stated rationale, using a fixed rubric with hard caps. The grade is not an Admiralty rating. Five outlets citing one vendor report count as one source; anything that cannot be traced to a primary is capped, not guessed. Returns a graded claim table, gaps, a deception screen and JSON. /ach, /threat-assessment and /writing-assessments run it first by default.
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 challenging a prevailing analytical judgment, the user asks "what is the opposing case?" / "argue the other side" / "play devil's advocate", or wants an assessment stress-tested before release. Takes the team's own lead judgment and builds the strongest case that it is wrong. A contrarian technique. It does not model what an adversary would do next, which is Red Team Analysis. Formerly /red-team-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。
Detect and remove the tells of AI-generated writing in BOTH English and Spanish, and read back the evidence honestly. Use when the user asks to "de-AI" / "humanize" / "un-slop" a draft, to examine whether text carries the tells (delve, tapestry, "it's not just X, it's Y", "here's the thing", em-dash overuse, an assistant's own closing line left in the document), to compare documents for overlap, or mentions signs-of-ai / SignsOfAI. Backed by the SignsOfAI engine — for a measured 0–100 score, sentence-rhythm burstiness, originality, citations, a writer baseline or perplexity, hand off to that engine (web app, CLI or MCP server) as described below. It cannot determine who wrote a text and must never imply that it can.
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。
Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.
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 complex problems require systematic step-by-step reasoning with ability to revise thoughts, branch into alternative approaches, or dynamically adjust scope. Ideal for multi-stage analysis, design planning, problem decomposition, or tasks with initially unclear scope.
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。
Performance profiling principles. Measurement, analysis, and optimization techniques.
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。
Reasoning data lost across agent steps and missing low-confidence fallback Keywords: sqlite, triangulation, escalation, confidence
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 prompt engineer specializing in designing, optimizing, and managing prompts for large language models. Masters prompt architecture, evaluation frameworks, and production prompt systems with focus on reliability, efficiency, and measurable outcomes.
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。
Generate AGENT.md files with proper YAML frontmatter, role definitions, expertise areas, and prompt templates following Babysitter SDK conventions.
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。
Guide for authoring specialized AI agents. Use when creating, updating, or improving agents, choosing models, defining focus areas, configuring tools, or learning agent best practices.
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。