771 件 ・ 関連度順
概要と使いどころ
Audit an LLM eval pipeline and surface problems: missing error analysis, unvalidated judges, vanity metrics, etc. Use when inheriting an eval system, when unsure whether evals are trustworthy, or as a starting point when no eval infrastructure exists. Do NOT use when the goal is to build a new evaluator from scratch (use error-discovery, write-judge-prompt, or validate-evaluator instead).
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。
Write a Chinese workplace weekly or monthly report (周报 / 月报) for a manager: results with numbers, progress against goals, risks raised early, next week's plan and the support needed, in the structure Chinese managers expect. Use when asked 帮我写周报, 写月报, 整理本周工作, weekly report in Chinese, or turn my notes into a 周报. Produces the report in Chinese with 本周完成, 关键数据, 问题与风险, 下周计划 and 需要的支持, plus a one-line summary for chat apps.
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 asked 帮我设计一节班会, 主题班会方案, 班会课教案, 开学第一课, 安全教育班会, 心理健康班会, or plan a class meeting as a 班主任. Produces a 主题班会 plan in Chinese with the background and goals, preparation, a timed sequence of student-led activities, discussion questions, the 班主任's closing words, follow-up actions for the following weeks, and notes for sensitive topics.
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。
Interview the user with sharp, one-at-a-time questions to turn a vague request into a tight, complete brief any other skill can run on. Use when a request is fuzzy, under-specified, or 'help me think this through', or before running a skill that needs inputs the user hasn't given. Produces a structured brief (goal, audience, constraints, success criteria) and hands off to the right skill — by interrogating, not guessing.
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。
Act as a body-double for a work session — a present, low-pressure companion that keeps you accountable and moving through the task without doing it for you. Use when asked be my body double, keep me company while I work, help me focus on this task, or I work better with someone there. Produces a session structure (goal, time block, check-in cadence), gentle presence and momentum nudges at intervals, distraction rescue when you drift, and an end-of-session acknowledgment — recreating the focus that comes from someone just being there.
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。
Specify an autonomous or tool-using AI agent before building it. Use when asked to design an AI agent, define an agent's tools and guardrails, scope what an agent is allowed to do, or write an agent spec/PRD. Produces an agent spec — goal & scope, tools with permissions, the control loop, guardrails & approval gates, memory, escalation/handoff, evaluation, and failure handling.
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。
Help users design and execute a press strategy that moves beyond vanity metrics to achieve specific business goals like funding, user acquisition, or B2B credibility.
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。
Help users move beyond ambitious goal-setting to create a rigorous diagnosis of challenges and a clear, actionable plan for winning in their specific market.
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。
Explore goals, constraints, and alternative approaches before choosing a design. Use when the user requests ideation or design exploration.
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 fast, progressive experiments to map tunable parameters and their effects. Use when optimizing code, prompts, configurations, or other artifacts against a goal or benchmark, or when a long research run needs a planned hypothesis queue, focused trials, and durable findings.
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。
Turn a product goal or feature request into a clear Agiflow project plan with small, testable tasks in Planning status. Use when starting a project, decomposing a feature, clarifying requirements, or converting an idea into an actionable backlog.
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。
Turn a list of goals, tasks, deadlines, and working constraints into a practical schedule with next actions and follow-ups.
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。
Reapply and repair Windows Codex Desktop after Store upgrades, including custom provider models hidden by Statsig available_models filtering, the dependent blue-purple Power slider and its Ultra toggle, Fast Mode request/UI gates, locale i18n, plugin UI gates, Chrome/browser_use gates, Goal command gates, Windows Computer Use availability gates and plugin/runtime repair, phone remote-control pairing under third-party/API-key main app usage, Desktop dynamicTools/inputSchema thread-start schema drift, local conversation visibility recovery after model_provider switches, restored-conversation missing-cwd continuation repair, ASAR integrity repair, signing/installing patched MSIX packages, SDK cleanup, Fast Mode wire verification, local plugin marketplace registration, and optional custom model_instructions_file setup (the bundled system prompt, also called 听话水).
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。
End-to-end cold email outreach orchestration. Handles goal alignment, lead ingestion from any source (CSV, paste, CRM export, database), sequence design, email generation, campaign setup in the user's chosen outreach tool, and launch. Tool-agnostic — supports Smartlead (full MCP automation), Instantly, Lemlist, Apollo, or manual CSV export.
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。
Set up a complete outbound email campaign in Smartlead. Asks the user for campaign goal, audience, messaging, schedule, and mailbox allocation. Creates the campaign, adds leads, saves email sequences, sets schedule, and assigns available mailboxes. Use when a user wants to launch email outreach via Smartlead.
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。
End-to-end LinkedIn outreach campaign builder. Takes leads from Supabase, upstream skills, or CSV. Aligns on campaign goal and tone, writes personalized LinkedIn message sequences (connection request + follow-ups + optional InMail), presents for review, and exports for the user's outreach tool (Dripify, Botdog, Expandi, or manual CSV). Logs to Supabase outreach_log.
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 a complete marketing campaign brief from a launch goal, ICP, and product context. Pure reasoning skill. Outputs channel plan, messaging angles, content types, timeline, and success metrics. Designed for seed/Series A founders and small GTM teams who aren't professional marketers but need to run focused campaigns. No scripts — pure reasoning.
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。
Take someone from a business goal to a verified, paused-then-live Meta/Facebook/Instagram campaign without making them learn Meta's hierarchy. Use automatically for requests to launch, run, create, publish, set up, or plan Meta ads; use reporting skills for analysis-only requests.
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。
Turn a brand's facts, a campaign brief and the product into a one-minute Meta ad strategy with its reasoning — goal, audience, objective and placements, budget split, how many ads and how different they must be (generate 3x so the user can choose), the test frame, the success metric, and safety rules for the user to accept. Decides what launch-meta-ad-campaign then executes, and re-reads the strategy after a deep check to show which assumption changed. Use it after intake and before any creative is generated or any campaign is built.
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 novel molecules using REINVENT 4 (de novo, scaffold decoration, linker design, R-group, molecular optimization), MolMIM, Diffusion-based generators (DiGress, DiffSMol), and JT-VAE with explicit handling of multi-parameter optimization (MPO), goal-directed scoring functions, transfer/reinforcement/curriculum learning, synthetic accessibility scoring, and chemical space exploration vs exploitation. Use when designing new chemical matter against a target, decorating a scaffold, linking fragments, or optimizing a hit for multiple ADMET / activity properties simultaneously.
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。
Trim multiple sequence alignments using ClipKIT, trimAl, BMGE, Divvier, or HMMcleaner with mode selection guidance per downstream goal. Use when removing unreliable columns or contaminating residues before phylogenetic inference, HMM building, or selection 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。
Align protein structures using Foldseek 3Di, TM-align, US-align, DALI, or Foldmason for structural MSA. Predict, score, and superpose backbone coordinates when sequence identity is below the twilight zone or remote-homology detection is required. Use when sequence MSA fails (<25% identity), when the dark proteome is the target, when AlphaFoldDB / ESM Atlas search is needed, or when structural superposition is the goal.
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。
Install, instrument and verify a web app end to end without pausing for a human. Use in an autonomous or goal-mode agent, in CI, or in any client that asks for approval on every command: it never says "restart your client" or "open a browser", because it takes a route that needs neither. Prefer the normal install-and-verify skill when a human is present and can answer.
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。
Report the compatibility redirect to `ap-independent-checker`; this retired role cannot perform new work.
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。