35건 · 관련도순
Compose compact, structured prompts for coding, debugging, review, and research with Codex or GPT-5.4. This internal skill defines task scope, completion criteria, output format, verification steps, and evidence requirements using consistent XML tags.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Build, transform, audit, and migrate prompts for GPT-5.6 Sol using outcome-first contracts, explicit success criteria, evidence and tool rules, approval boundaries, output requirements, and stop conditions. Use when someone asks for a GPT-5.6 prompt, wants an existing prompt optimized for GPT-5.6, or needs a prompt stack adapted from an older model.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when the user asks about Higgsfield Assist (the built-in GPT-5 copilot), how to use the platform's native AI assistant, credit optimization strategies, plan selection, how to get more from fewer credits, or platform efficiency tips.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use this skill when stuck in circular debugging, when solutions aren't working despite multiple attempts, or when the user expresses frustration with lack of progress. Bring in GPT-5 as a third-party consultant to provide fresh perspective on complex technical problems, architectural decisions, or multi-system debugging issues. Ideal when you've tried multiple approaches without success, when the problem involves obscure edge cases or novel challenges, or when a second expert opinion would help break through an impasse. Gather all context from the conversation so far and present it comprehensively to GPT-5.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when user asks to leverage codex, gpt-5, or gpt-5.1 to implement something (usually implement a plan or feature designed by Claude). Provides non-interactive automation mode for hands-off task execution without approval prompts.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Build one-page HTML/PDF resumes from copy-paste YAML using one of 12 official templates. HARD GATES: deliver exactly one A4 page; never invent a layout — copy assets/templates/<id> into output/<id>/ and edit that copy only. Keep a full inventory in raw.data.yaml. For each job, COPY selected entries into resume.data.yaml (polish there), then apply that file to a template. Apply pasted YAML by replacing visible text in the official resume.html, then run QA. Default template is basic-a4. Use when creating, iterating, polishing copy, migrating, exporting, or designing resume/CV HTML/PDF. For polishing resume copy, prefer writing-oriented models (Claude Fable 5 / Claude Opus 4.6-4.7 or Opus 5 / Kimi K3 / GLM-5.1-5.3-max / Qwen 3.8 Max); do not use GPT-5.6 Terra/Luna or GPT-5.5 Instant.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
This skill should be used to spawn specialized OpenAI Codex CLI subagents for code review, debugging, architecture analysis, security audits, refactoring, documentation, comparative evidence adjudication, and autonomous /goal runs. It adds each persona through process-local developer instructions while preserving the project's AGENTS.md chain, including during parallel launches. Supports GPT-6-Astra across low, medium, high, xhigh, max, and ultra reasoning with default or priority service tiers, plus GPT-5.6 and GPT-5.5 models. Triggers on 'delegate to Codex', 'Codex Astra', 'Astra subagent', 'Codex subagent', 'code review agent', 'security audit', 'refactor with Codex', 'goal run', 'autonomous goal', 'have Codex weigh this'.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Azure OpenAI画像生成CLIツール (gpt-image-1.5 / gpt-5.1)。テキストから画像生成、画像のAI編集、画像の内容説明を行う。Use when the user wants to (1) generate images using Azure OpenAI, (2) edit existing images with AI, (3) explain image contents. Triggers on "画像を生成", "画像を編集", "画像の説明", "generate an image", "edit this image", "describe this image", "imgenで".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
OpenAI Codex CLIを使用してドキュメントやコードのレビューを依頼するスキル。GPT-5.5モデルをxhigh推論モードで呼び出し、深い分析によるレビューを実行。レビュー結果を指定フォルダに出力し、その内容を確認・分析する機能を提供。コードレビュー、ドキュメントレビュー、設計書レビュー、テスト計画レビューなど、専門的なレビューが必要な場面で使用。
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Keep GPT-5.6 and other coding-agent work proportional to the request by locking scope, choosing the smallest sufficient implementation, matching verification to risk, and stopping when success is proven. Use for implementations, bug fixes, refactors, reviews, or maintenance where scope creep, speculative abstractions, unrelated cleanup, repeated test runs, unnecessary dependencies, or polishing beyond the request are risks.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Build with OpenAI's stateless APIs - Chat Completions (GPT-5, GPT-4o), Embeddings, Images (DALL-E 3), Audio (Whisper + TTS), and Moderation. Includes Node.js SDK and fetch-based approaches for Cloudflare Workers. Use when: implementing chat completions with GPT-5/GPT-4o, streaming responses with SSE, using function calling/tools, creating structured outputs with JSON schemas, generating embeddings for RAG (text-embedding-3-small/large), generating images with DALL-E 3, editing images with GPT-Image-1, transcribing audio with Whisper, synthesizing speech with TTS (11 voices), moderating content (11 safety categories), or troubleshooting rate limits (429), invalid API keys (401), function calling failures, streaming parse errors, embeddings dimension mismatches, or token limit exceeded.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing. Uses GPT-5.2 by default for state-of-the-art software engineering.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Leverage OpenAI Codex/GPT models for autonomous code implementation, code review, and plan review. Triggers: "codex", "use gpt", "gpt-5", "let openai", "full-auto", "adversarial review", "second opinion review", "用codex", "让gpt实现", "对抗式审查", "让codex审查计划", "第二意见". Use this skill whenever the user wants to delegate coding tasks to OpenAI models, run code or plan reviews via codex, get a second-opinion review from a different model, or execute tasks in a sandboxed environment.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Build a near-complete company list for any ICP by learning how your real customers label themselves, pulling every industry and keyword they use, judging every single row with a cheap AI model (Jev or gpt-5-nano), and running a Claygent lookalike loop until it runs dry. The method from the SCULPT 2026 talk "Build the perfect company list". Use when a database filter feels too narrow or too noisy, when someone says "find every company like our customers", "our TAM looks too small", or "why is this list full of junk".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Answer a hard question by fanning it out to a PANEL of models running in parallel — each answering independently with web search and bash, none seeing the others' work — then having Opus 4.8 judge every response into a structured analysis (consensus, contradictions, partial coverage, unique insights, blind spots) and write a final answer grounded in it. The panel is two independent Opus 4.8 runs (slug opus4.8-4.8), Opus 4.8 + GPT-5.5 via codex (opus4.8-gpt5.5), Opus 4.8 + Gemini 3.1 Pro via agy (opus4.8-gemini3.1pro), or all three (opus4.8-gpt5.5-gemini3.1pro). Opus always judges and writes the final answer — the pipeline can't be reversed. Runs on local CLI subscriptions (no metered API), and saves a timestamped provenance .md per run. Use this whenever the user asks to "run it through Fusion", says /fusion, wants a multi-model / panel / ensemble answer, wants a question cross-checked across models, or wants a higher-confidence answer with consensus and blind spots surfaced — even if they don't say "fusion". General-purpose: any topic (research, law, strategy, technical, personal). Best for high-stakes research, design calls, and debugging where being confidently wrong is expensive.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Produce a high-confidence, CONCISE implementation / architecture / strategy PLAN that follows the OMC plan system end to end. It first runs OMC's real requirements interview (auto-chains the `omc-plan` skill: one question at a time, explore-first, Analyst consult) to produce an initial plan in `.omc/plans/`, then DEEPENS that plan with a 3-round ITERATIVE fusion loop — each round an Opus 4.8 panelist (Agent subagent) and a GPT-5.5 panelist (via codex) critique/improve it IN PARALLEL and BLIND, then Opus 4.8 (the orchestrator) judges and synthesizes one tighter plan that seeds the next round, stopping early on convergence. Writes the final dense plan back to the same `.omc/plans/<slug>.md`, then offers the OMC handoff (`/omc-plan --review` → `/team` or `/ralph`). Use for high-stakes planning, architecture decisions, strategy calls, and hard debugging — especially when the user runs /plan or asks how to approach a non-trivial build. Reuses the `fusion` skill's run_codex.sh + judge rubric. NOT for trivial tasks (single pass is enough).
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Run benchmark-selected GPT-5.6 work through the Codex CLI.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Provides Codex CLI delegation workflows for complex code generation and development tasks using OpenAI's GPT-5.3-codex models, including English prompt formulation, execution flags, sandbox modes, and safe result handling. Use when the user explicitly asks to use Codex for complex programming tasks such as code generation, refactoring, or architectural analysis. Triggers on "use codex", "delegate to codex", "run codex cli", "ask codex", "codex exec", "codex review".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Evaluate WooAIAssistant against a structured scenario suite with hard invariants + LLM-as-judge rubric scoring. Runs live against the demo store + gpt-5.1 via the woo-mobile-ai backend wrapper, writes a JSONL run record, compares against stored baselines, and surfaces regressions. Always delegated to a subagent so the main context only sees the markdown report.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
当需要在基础身份之上叠加可切换的人格风格层时调用此 skill。典型场景包括：为同一产品提供多种人格选项（如 GPT-5.1 的 friendly/professional/quirky 模式）、设计人格切换机制、防止人格泄露到用户内容中。 不适用于：定义 AI 的核心角色定位（应使用 persona-design）、设计安全规则（应使用 safety-guardrails）。 关键 trigger 信号：产品需要多种语气风格、用户可切换 AI 性格、需要防止 AI 人格污染用户文本、存在 "personality" 或 "tone" 配置项。
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Audit whether a paper's EVALUATION DESIGN actually measures what it claims and whether its reporting is complete — the validity layer family D (experiment-forensics) cannot reach. Three patterns: train/test leakage means the reported score may not measure generalization (HP-EVAL-LEAKAGE — adopts the Kapoor & Narayanan 8-type / 3-category leakage taxonomy; the illegitimate-proxy / sampling-bias / pretraining-contamination subtypes hand off as needs_external_check, naming but NEVER running Oren-2023 exchangeability / Shi-2023 Min-K% / Golchin-2023 Time-Travel / BIG-bench canary); a load-bearing LLM judge is conflicted (same model/family as a compared system) or unvalidated (no human-agreement, no bias control) (HP-JUDGE-VALIDITY); a declared condition/metric is dropped or switched to favor the method, or 'best' is chosen with no held-out set (HP-SELECTIVE-REPORTING). Verdict-bearing at L0/L1 from the DESCRIBED protocol — NOT repo-gated like experiment-forensics; L2 only CONFIRMS against split/preprocessing/result files. A fresh cross-model reviewer (gpt-5.6-sol xhigh, read-only, fresh thread per pass) PROPOSES findings, each span-anchored to a ledger claim_id; tools/adjudicate_findings.py DECIDES the verdict. Leakage and under-reporting are usually HONEST methodological errors — every finding describes a discrepancy to CHECK, never an accusation. An LLM generating GROUND-TRUTH labels is HP-FAKE-GT (experiment-forensics) — routed there, not here. Emits eval-design-forensics.findings.json; computes NO verdict. Detect-only. Triggers: "eval design audit", "evaluation validity", "train/test leakage", "data leakage", "is the score measuring generalization", "LLM judge bias", "is the judge validated", "selective reporting", "cherry-picked results", "评估设计审计", "评测有效性", "数据泄漏", "训练测试集泄漏", "裁判模型有没有验证", "选择性报告".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Audit whether a paper's baseline comparisons are COMPLETE, FAIR, and SIGNIFICANT: a required recent SOTA baseline is missing while 'best/SOTA' is claimed (HP-MISSING-BASELINE); a baseline is undertuned / given less compute-tuning-data, run at a mismatched config, or the equal-budget ablation-as-baseline is absent (HP-WEAK-BASELINE); 'outperforms' is asserted over overlapping error bars or with no variance/seeds (HP-SIG-OVERLAP); and a cross-row 'improves over baseline by X%' is arithmetically wrong (HP-DELTA-ERROR, cross-row form only). A versioned per-domain baseline profile + a live leaderboard/recency search are assembled by the EXECUTOR as structured facts; a fresh cross-model reviewer (gpt-5.6-sol xhigh, read-only, fresh thread per dimension) PROPOSES findings, each span-anchored to a ledger claim_id; tools/adjudicate_findings.py DECIDES the verdict. Works at L0 (stated comparisons) and deepens at L2 (configs/result files). A completeness question it cannot settle internally becomes needs_external_check, never a guessed missing baseline. Emits baseline-comparison-audit.findings.json; computes NO verdict. Detect-only. Triggers: "baseline audit", "missing baselines", "is the comparison fair", "weak baseline", "baseline 误报", "SOTA earned?".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Expert guide for multimodal vision UI auditing (Gemini 4 Pro / Flash Vision, Claude 3.7 / 5.1 Sonnet, GPT-5 Vision) against Anti-Slop Pillar 7, 1px crisp borders, 3-tier radius scales, tabular numerals, and WCAG 2.2 AA / Panduan ahli audit visual UI berbasis vision multimodal.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use for cheap parallel web discovery (gpt-5.6-luna). Triggers: Luna search, parallel research, 루나검색, 루나 서치, 병렬 웹검색, 싸게 많이 찾아봐.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.