「search run」の検索結果

Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g. "get my model's eval score up", "improve this agent/harness", "tune this pipeline", "beat the baseline on this benchmark", "run a search over approaches and keep the best", "do an MLE-bench / Kaggle-style optimization", or any long-horizon "make this artifact better and don't just memorize the dev set" task. Trigger it even when the user doesn't say "Arbor" or "hypothesis tree" but describes repeated experiment-and-evaluate loops, branching exploration of competing ideas, or worries about a dev/test gap. Runs Claude itself as the coordinator with subagent executors in isolated git worktrees; for the standalone `arbor` CLI tool see references/arbor-upstream.md.

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 and create Busabase-backed App-in-Skill packages with a canonical app project, Busabase-native setup and product onboarding, review/execution workflows, a standardized responsive UI, and AirApp-first delivery. Use when a user wants a Busabase research desk, review queue, planner, action console, operating dashboard, control panel, collaboration workspace, onboarding/readiness flow, or an existing Kelly App-based skill updated. Every generated skill contains a complete app/ project, deploys that source to Busabase AirApp by default, runs pnpm dev only when local preview is explicitly requested, follows the Kelly desktop and phone UI contract, delegates AirApp runtime, SDK, security, scaffolding, and deployment constraints to busabase-app-creator, and delegates repository-level conformance testing to kelly-app-skill-creator-tests.

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 Busabase-backed job-search outreach desk with a bundled Hono App-in-Skill deployable to AirApp. Use when the user invokes $kelly-jobhunt or /kelly-jobhunt, wants to turn a resume into a structured profile and a typeset PDF, wants to find target companies and their contact addresses instead of applying through a job board, wants one tailored application email drafted per company, or wants to review and approve each send. Four subcommands - setup, profile, research, send - plus the desk itself. One company receives exactly one email; mailbox credentials live in the Busabase Vault and never reach browser 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。

Deep literature review — PubMed, EuropePMC, bioRxiv preprints, citation networks, evidence synthesis. Disambiguates queries, runs collision-aware searches, grades evidence T1-T4, and produces structured reports. Use for systematic literature review, meta-analysis evidence collection, and detailed answer-with-citations 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。

Install, set up, verify, update, pin, uninstall, or troubleshoot the ToolUniverse plugin on OpenAI Codex. ALWAYS consult this skill for any of those — don't answer from memory, because the exact marketplace name (mims-harvard/ToolUniverse), the "codex plugin marketplace add" then "codex plugin add -m tooluniverse" flow, Codex's startup auto-upgrade behavior, the uvx tooluniverse MCP server, and the API-key env vars are easy to get wrong. Use it whenever someone wants to get ToolUniverse (or "the 1000+ scientific tools" / "the harvard tools") working on Codex, says the Codex plugin or its tools/skills won't load, hits a uvx or MCP-server startup error, asks how Codex updates it, wants to pin or remove it, or finds it running an old tool version — even if they never say the word "plugin". Not for the Claude Code plugin (use tooluniverse-claude-code-plugin), for running research with the tools, or for authoring new tools or skills.

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。

Build local BLAST databases and run searches using NCBI BLAST+ command-line tools. Use when running >50 queries, building custom databases with -parse_seqids and -taxid, downloading prebuilt NCBI databases via update_blastdb.pl, choosing -task variants (megablast/dc-megablast/blastn/blastn-short), tuning soft/hard masking, scaling threads, or extracting hits with blastdbcmd. Encodes BLAST v5 vs v4 database format, taxonomy filtering, makeblastdb pitfalls.

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。

Runs JACKS (Joint Analysis of CRISPR/Cas9 Knockout Screens; Allen et al 2019 Genome Research) which models per-sgRNA log-fold-change as the product of a treatment-dependent gene-essentiality term and a treatment-independent guide-efficacy term. Covers the Bayesian decomposition math, the hierarchical efficacy prior shared across screens performed with the same library, when JACKS outperforms MAGeCK (multi-screen joint analysis, libraries with broad efficacy variance) and when it does not (single screen, novel libraries with no prior efficacy), library-reuse efficacy transfer, downstream essentiality interpretation, and the 2.5x sample-size reduction enabled by efficacy-aware testing. Use when running multiple screens with the same library, when guide-level noise is suspected to dominate per-gene signal, when reusing published essentiality reference screens for efficacy priors, or when comparing screens performed across cell lines that share library but differ biologically.

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。

Manage project learnings. Review, search, prune, and export what gstack has learned across sessions. Use when asked to "what have we learned", "show learnings", "prune stale learnings", or "export learnings". Proactively suggest when the user asks about past patterns or wonders "didn't we fix this before?"

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。

Build local BLAST databases and run searches using NCBI BLAST+ command-line tools. Use when running >50 queries, building custom databases with -parse_seqids and -taxid, downloading prebuilt NCBI databases via update_blastdb.pl, choosing -task variants (megablast/dc-megablast/blastn/blastn-short), tuning soft/hard masking, scaling threads, or extracting hits with blastdbcmd. Encodes BLAST v5 vs v4 database format, taxonomy filtering, makeblastdb pitfalls.

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。

Runs JACKS (Joint Analysis of CRISPR/Cas9 Knockout Screens; Allen et al 2019 Genome Research) which models per-sgRNA log-fold-change as the product of a treatment-dependent gene-essentiality term and a treatment-independent guide-efficacy term. Covers the Bayesian decomposition math, the hierarchical efficacy prior shared across screens performed with the same library, when JACKS outperforms MAGeCK (multi-screen joint analysis, libraries with broad efficacy variance) and when it does not (single screen, novel libraries with no prior efficacy), library-reuse efficacy transfer, downstream essentiality interpretation, and the 2.5x sample-size reduction enabled by efficacy-aware testing. Use when running multiple screens with the same library, when guide-level noise is suspected to dominate per-gene signal, when reusing published essentiality reference screens for efficacy priors, or when comparing screens performed across cell lines that share library but differ biologically.

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。

Convex is the backend agents get right on the first try: an all-TypeScript reactive platform where the database, server functions, scheduling, file storage, auth, and realtime sync are one type-safe system, every function is a transaction, and `tsc` catches most mistakes before deploy. Ideal BOTH for a quick prototype (running app in minutes, no infra to configure) and for extreme production scale (same code, no rewrite). Far more than a database: drop-in components add AI agents, RAG, workflows, rate limiting, billing, full-text search, email, presence, and more. Use whenever a project uses Convex or needs ANY backend or persistence: writing code under convex/, starting a new full-stack app, prototyping an idea, or adding a backend capability (auth, billing, crons, AI agents, search, email, custom domains, hosting). Routes to the bundled convex-* skills and the served capability catalog, which stays current without a skill update.

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。

Add a capability to the CURRENT Convex app — consults the served Convex capability catalog for always-current procedures (billing, crons, auth, agent, search, …); falls back to built-in hosting or @convex-dev component search. TRIGGER when the user runs /add, or asks to add hosting/publishing or any backend capability to an existing Convex app.

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。

Interactive review sessions with academic PDFs (lectures, research papers, book chapters). Extract concepts, run Q&A sessions, generate quizzes with scoring. Preserves mathematical formulas in LaTeX format. Privacy-preserving local processing - PDFs never uploaded. Use when studying academic materials, reviewing research, or preparing for exams.

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。

Free web search via DuckDuckGo — text, news, images, videos. No API key needed. Prefer the `ddgs` CLI when installed; use the Python DDGS library only after verifying that `ddgs` is available in the current runtime.

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 PRIMARY development workflow for the Archon project (remote-coding-agent). Use this skill instead of any PRP skills when working on Archon code. Routes to 10 specialized cookbooks based on what the user is trying to do: RESEARCH — "how does the orchestrator work?", "where is session state defined?", "trace the workflow execution flow", "what is IWorkflowStore?" INVESTIGATE — "should we use Drizzle or Prisma?", "what's the best way to add WebSockets?", "can we migrate to Turso?", "how do other projects handle rate limiting?" PRD — "write a PRD for dark mode", "spec out the notification feature", "product requirements for webhook retry" PLAN — "plan the auth refactor", "design the caching layer", "create an implementation plan for #42" IMPLEMENT — "implement the plan", "execute .claude/archon/plans/auth.plan.md", "build the feature from the plan", "code this up" REVIEW — "review PR #123", "review my changes", "code review the diff" DEBUG — "debug the failing test", "why is streaming broken?", "root cause analysis on the timeout issue" COMMIT — "commit these changes", "commit the auth refactor" PR — "create a PR", "open a pull request for this branch" ISSUE — "report this to gh", "create a gh issue", "log it in github", "file a bug for this", "create a feature request" This skill triggers on ANY development task: researching, investigating, planning, building, reviewing, debugging, committing, or shipping code. NOT for: Running Archon CLI workflows in worktrees (use /archon 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。

Run 150+ AI apps via inference.sh CLI (infsh) — image generation, video creation, LLMs, search, 3D, social automation. Uses the terminal tool. Triggers: inference.sh, infsh, ai apps, flux, veo, image generation, video generation, seedream, seedance, tavily

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。

Route a task by complexity and run the gated Forge pipeline (research → plan → implement → ship). Use when the user runs /forgemaster or wants the full guided feature pipeline.

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 researcher asks where to start, which project skill fits the current stage of a study, or in what order literature scoping, source access, vault upkeep, drafting, citation verification, disclosure, and review response should run.

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。

Comprehensive persistence tradecraft for authorized red team engagements covering Windows and Linux mechanisms. Windows techniques include registry Run/RunOnce keys, scheduled tasks, WMI event subscriptions, DLL search order hijacking, COM object hijacking, Startup folder drops, service creation, Security Support Provider (SSP) DLL injection, and Active Directory persistence (AdminSDHolder abuse, DCShadow, Golden Ticket, Silver Ticket, Skeleton Key, SID History injection). Linux techniques include cron and at jobs, systemd timers and services, SSH authorized_keys injection, shell profile backdoors (.bashrc/.bash_profile), PAM module backdoors, LD_PRELOAD hijacking, kernel module rootkits, web shells, and Git hook abuse. Provides operator-ready command sequences for SharPersist, Impacket ticketer, schtasks, sc.exe, crontab, and systemctl with OPSEC considerations for each method. Maps to MITRE ATT&CK T1547 (Boot or Logon Autostart), T1053 (Scheduled Task/Job), T1546 (Event Triggered Execution), T1556 (Modi...

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。

Long-running design anthropologist that builds comprehensive visual databases from 500-1000 real-world examples, extracting color palettes, typography patterns, layout systems, and interaction design across any domain (portfolios, e-commerce, SaaS, adult content, technical showcases). This skill should be used when users need exhaustive design research, pattern recognition across large example sets, or systematic visual analysis for competitive positioning.

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。

作業の依存関係を整理し、独立した調査・実装・検証を並行して進めるためのスキルです。変更先の競合を避け、各作業の完了状況と確認結果を表にまとめます。

• 独立したファイル調査の一括実行
• 複数エージェントでの分担実装
• Git worktreeで変更先を分けたいとき

AndroidやKotlin Multiplatformの非同期処理とデータ更新を実装し、並行実行、画面状態の管理、キャンセル、エラー処理、テストまで扱うスキル。

• 複数データを並行して読み込みたいとき
• StateFlowによる画面状態の管理
• 検索入力の間引きや通信の再試行

初期設定で選んだアプリや利用目的を引き継ぎ、最初の依頼を具体的な成果物にします。仕事の要約、HTMLページ、自動化スクリプト、アプリ導入などの小さな作業を進めます。

• 接続したアプリで最初の仕事要約
• 仕事用リンクのスタートページ作成
• Downloads整理スクリプトの作成

言語モデルに指示への応答や好ましい回答を学習させるため、TRLによる追加学習を案内するスキル。データ準備、学習方式の選択、報酬モデルの学習や評価を扱います。

• 回答例で指示に従うモデルを学習
• 回答の好みをDPOで学習したいとき
• 報酬モデルを使うRLHFの構築