3,071 件 ・ 関連度順
概要と使いどころ
Update Codex's pinned `v8` / `rusty_v8` versions, validate the release-candidate path, and investigate failed V8 canary or artifact builds. Use when asked to bump V8, update `rusty_v8` artifacts, prepare or validate a V8 release candidate, check `v8-canary`, or diagnose why a V8 version update no longer builds.
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 or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output should be a bitmap asset rather than repo-native code or vector. Do not use when the task is better handled by editing existing SVG/vector/code-native assets, extending an established icon or logo system, or building the visual directly in HTML/CSS/canvas.
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 creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.
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。
Update the title and body of one or more pull 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。
Guide for testing Codex TUI interactively
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。
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep watching open PRs so fresh review feedback is surfaced promptly. Use when the user asks Codex to monitor a PR, watch CI, handle review comments, or keep an eye on failures and feedback on an open PR.
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, modify, run, test, screenshot, record, and export Godot 4.x games with the gdx CLI. Use when Codex needs to create a new Godot game project, attach to an existing Godot project, generate GDScript, build scenes/resources from JSON specs, edit a running scene through the gdx daemon, capture screenshots, record animation clips, send input, inspect game state, run Godot tests, or produce exports through gdx.
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 asks for a phase-gated refactoring or redesign loop - session-blind workers map and trace the area, empirical probes precede the design, an approval gate guards implementation, and a conformance audit re-checks the branch after any design change. State persists in .episteme/DESIGN-<slug>.md. Requires the refactor agent roles registered by scripts/install-codex.sh. Keywords: refactor loop, redesign, design gate, enumerate before design, conformance audit.
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 asks to verify a story or ticket implementation against its spec - per-AC verdicts, code reuse and design conformance, dead code, then adversarial maintainer verification. Requires the qa/review agent roles registered by scripts/install-codex.sh. Keywords: story QA, acceptance criteria, spec conformance, AC coverage, QA this branch, verify story.
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 asks for a multi-agent .NET code review - five parallel reviewers (correctness, performance, security/observability, data/messaging/integration, generalist) plus an adversarial maintainer that refutes weak findings. Requires the review agent roles registered by scripts/install-codex.sh. Keywords: dotnet review pipeline, multi-agent review, parallel reviewers, maintainer pushback, review this branch, cynical review.
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。
Join Claude Code and Codex CLI to the Interlateral mesh in Warp panes by attaching Warp to the standard tmux socket; Warp is the visible terminal surface, tmux remains the transport.
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。
Initialize the standard Interlateral two-agent CLI mesh from a bootstrap agent by running me.sh, launching Claude Opus 4.7 plus Codex 5.5, proving live ACK, and waiting for "Reporting for Duty!". The bootstrap agent is not part of the mesh.
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。
Join Claude Desktop or Codex Desktop to the Interlateral mesh as a desktop peer with its own tmux inbox session, identity, direct ACK, and ledger mirror. This is separate from the standard CLI init flow.
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 two-agent independent review/redteam followed by peer collaboration to produce a consensus superset of findings and enumerated revision requests. Use when Codex 5.5 and Claude Opus 4.7 should first critique a matter independently, then exchange work, synthesize the best combined analysis, and finish with a single agreed revision list.
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。
Coordinate material messages between explicitly selected desktop-backed agents, including Claude, Codex and bb. Separates exact inbox delivery, native task wake, receiver ACK and completed 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。
Use quando o Codex está construindo ou iterando em um jogo web (HTML/JS) e precisa de um loop confiável de desenvolvimento + teste: implementar pequenas mudanças, executar um script de teste baseado em Playwright com rajadas curtas de input e pausas intencionais, inspecionar screenshots/texto e revisar erros de console com render_game_to_text.
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 quando o usuário pergunta como construir com produtos ou APIs da OpenAI e precisa de documentação oficial atualizada com citações (por exemplo: Codex, Responses API, Chat Completions, Apps SDK, Agents SDK, Realtime, capacidades ou limites de modelos); priorize ferramentas MCP de docs da OpenAI e restrinja qualquer fallback de navegação a domínios oficiais da OpenAI.
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。
[User-Invoked] Use ONLY when the user explicitly types /dual-ai or /dual-ai <workflow-id> — fans out one prompt, or one workflow invocation per tool, to two fresh parallel AI sessions (Claude Code + Codex CLI), both pre-set to xhigh reasoning effort and full-permission mode before the prompt executes. NEVER auto-activate.
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 between coding-agent runs (Codex, Claude Code, Cursor, Aider, etc.) to stop the project from drifting, overbuilding, or accumulating dead weight. Forces a read-only audit that classifies every active item as KEEP / DELAY / REMOVE and ends with a single, unambiguous next action. Trigger on "audit before continuing", "what should I do next", "this project got too big", "between runs", "trim scope", "stop adding stuff", or any signal that the project feels noisy and the next step is unclear. Do NOT load for trivial one-line fixes, when the next action is already obvious, or when you're mid-run and just need to keep going.
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。
Project-level visual direction skill for WeChat Official Account articles. Use when planning, improving, diversifying, generating, or reviewing cover images and body illustrations for公众号文章, especially when Codex image generation should be used without being constrained by repetitive preset-based illustration 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。
Audit and safely clean local project repositories or workspaces with excessive generated files, old project residue, dirty Git status, stale worktrees, build caches, duplicate nested projects, confusing roots, or agent context/token waste. Use when the user asks to organize a repo, remove useless files, classify valid project files, clean untracked/deleted files, reduce disk usage, migrate from an old repo layout to a canonical project, or prepare a repository for future Codex/agent 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。
中国药品权威数据库查询 — NMPA(国家药监局) + CDE(药品审评中心) + DrugBank(英文名/ATC) + PubChem(化学结构) 多源融合,提供(通用名 ↔ 商品名 ↔ 英文名 ↔ 适应症 ↔ NMPA 批文号 ↔ 上市日期)精确映射。Make sure to use this skill whenever the user mentions 药品名 / 通用名 / 商品名 / NMPA / 国药准字 / 药监局 / CDE / drug brand name / generic name / drug registry / pharmaceutical lookup / drug verification / 药物核验 / 商品名对应 / drug cross-check / drug authority lookup. 在任何 medical / market-sizing / clinical / disease-research 报告生成阶段,**所有药品提及必须先调 lookup_drug() 验证**,严禁 LLM 凭训练记忆拼凑通用名↔商品名↔英文名对应关系。LLM 训练截止后药企会更换商品名、新药持续上市,记忆完全不可信。Iron Law:lookup 返回 None → 调用方必须 raise UnverifiedDrugError,不允许 fallback 到记忆。免费公开数据源,跨平台:Claude Code / Codex / Gemini CLI 三端均可 auto-trigger,实现仅依赖 httpx + beautifulsoup4 标准生态,不绑定任何厂商 SDK。
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。
医学证据等级排序与编排层 skill - evidence grading orchestrator. 当用户请求"证据等级 / GRADE / 证据排序 / 医学证据评估 / 系统评价排序 / 临床证据排序 / 证据金字塔 / 给 PMID 打分 / Practice Guideline 优先 / Cochrane 优先 / 反向证据交叉验证 / evidence grading / quality of evidence / evidence pyramid / GRADE assessment / Cochrane review ranking / clinical evidence ranking"时,**调用本 skill 进行医学证据自动分级,自动选择最佳信息源**。本 skill 是编排层(L2)·不直接打 NCBI/Europe PMC/ClinicalTrials API,而是编排 6 个底层原子 skill(pubmed-eutils / europepmc-search / clinical-trials-v2 / aact-bulk-trials / bioc-fulltext-fetch / pubtator-entity-search)的召回结果,按证据金字塔(指南 > Meta > RCT > Cohort > Case-Control > Case Report)做 GRADE A/B/C/D 自动评级,自动剔除 editorial/letter/comment。优先使用 BioMCP MCP server 做 fan-out(genomoncology/biomcp);无 BioMCP 时走自建 slow-path 兜底。跨平台无锁(Claude Code / Codex / Gemini CLI)。
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。
当用户询问 ClinicalTrials.gov / 临床试验 / NCT / 试验注册 / 招募状态 / phase 1/2/3 / RCT lookup / sponsor 检索 / interventional trial / observational study / 主次要终点 / trial outcomes / 试验招募中 / recruiting status 时,通过 ClinicalTrials.gov API v2 实时检索官方注册数据。专注实时单次查询(≤1000 条/请求),典型场景: "某 NCT 试验最新状态"、"BTK 抑制剂 Phase 3 在招募试验"、"某试验已发布的主次要终点结果"。明确边界: 批量 >10k 试验 / 全库 SQL 历史分析 → aact-bulk-trials; 关联 PubMed 文献 → pubmed-eutils; RCT 自动 GRADE 评级 → medical-evidence-grading; 引用入报告附录 → evidence-appendix-sync。跨平台无锁(Claude Code / Codex / Cursor 通用)。
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。