2,330 件 ・ 関連度順
概要と使いどころ
This skill should be used when picking or diagnosing a training move (SFT, LoRA, DPO/KTO/ORPO, RFT, GRPO/PPO/RLOO, RLHF), or when the user mentions fine-tuning, post-training, training recipe, reward design, or weight updates. Decision tree by reward shape, smoke-run gate, three failure diagnostics, five false-progress patterns. Provider recipes and I/O contract in references/.
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。
Continues interrupted Codex work only after read-codex-history verifies rollout identity and fork/compaction lineage — restores the original outcome, unfulfilled requests, and the next action. Use when given a Codex Session ID, asked to pick up a prior Codex run, told Codex was interrupted, fused, compacted or stuck, or asked to take over without `codex resume`. Not for a conversation Codex already natively resumed.
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。
Diagnose and resolve Claude Code plugin and skill issues. This skill should be used when plugins are installed but not showing in available skills list, skills are not activating as expected, or when troubleshooting enabledPlugins configuration in settings.json. Triggers include "plugin not working", "skill not showing", "installed but disabled", or "enabledPlugins" 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。
MUST be used right after changing any CLI color config (delta/bat/themes/lazygit pager) — renders the terminal's colored output to a PNG so Claude can actually SEE contrast, alignment, and highlighting instead of raw ANSI codes. Use for delta git diff colors, bat syntax highlighting, starship prompt, eza/ls colors, or ripgrep matches. Trigger phrases: 看终端效果, 终端截图, 验证配色, terminal screenshot.
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。
This skill should be used when comparing two videos to analyze compression results or quality differences. Generates interactive HTML reports with quality metrics (PSNR, SSIM) and frame-by-frame visual comparisons. Triggers when users mention "compare videos", "video quality", "compression analysis", "before/after compression", or request quality assessment of compressed videos.
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。
This skill should be used when setting up, auditing, or enforcing internationalization/localization in UI codebases (React/TS, i18next or similar, JSON locales), including installing/configuring the i18n framework, replacing hard-coded strings, ensuring en-US/zh-CN coverage, mapping error codes to localized messages, and validating key parity, pluralization, and formatting.
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。
MUST be used first for tunnel / proxy-path connectivity failures or slow throughput (网络故障 / 连不上 / 代理或隧道下超时). Diagnoses Tailscale, proxy, TUN, DNS and SSH-tunnel problems on macOS and Windows/WSL, e.g. Tailscale ping works but SSH fails, curl works but browser gets 503, Git/Docker fails behind the proxy, or downloads crawl despite a reachable proxy. Not for application-layer bugs (use debugging-network-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。
Review a pull request or diff like a thoughtful senior engineer — prioritized, kind, and focused on what matters. Use when reviewing code, giving PR feedback, or asked to 'review this change'. Produces a structured review: a correctness/design pass, comments ranked by severity (blocking → nit), what's done well, and a clear approve / request-changes call — feedback that improves the code and the author.
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 tailored code review checklist for any pull request based on the language, type of change, and risk level. Use when asked to review code, check a PR, review a pull request, or generate a code review checklist. Produces a focused checklist with language-specific checks, risk-level-appropriate depth, and a clear approve/request-changes recommendation.
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。
Extract pixel-level data from an image of a chart or graph and produce a structured data table. Use when asked to extract data from a chart image, transcribe numbers from a graph, digitise a chart, or turn a screenshot of data into a table. Produces a structured table with extracted values, confidence levels, and a reconstructed chart source. Best used with Claude Opus 4.7 or newer for reliable chart data extraction.
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 复盘 (fupan), the structured project review widely used in Chinese companies: review the goal, assess the result, analyse why, and draw rules for next time, with a blame-free tone and owned actions. Use when asked 帮我做复盘, 项目复盘, 活动复盘, 复盘会怎么开, or a fupan or retrospective in Chinese. Produces the 复盘 document in Chinese with goal versus result, root causes split into controllable and uncontrollable, lessons stated as reusable rules, and an action list with owners and dates, plus a meeting agenda.
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 blameless postmortem for an incident caused by an AI agent or LLM feature — hallucinated facts shipped to users, runaway tool use, prompt injection, cost blowouts, or wrong actions taken autonomously. Use when asked to write up an AI incident, analyse why an agent did something wrong, or produce corrective actions after an LLM failure. Produces a structured postmortem with trace reconstruction, a root-cause layer analysis, and corrective actions including a permanent regression case. For non-AI production incidents use incident-postmortem.
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 a content library, docs site, or blog for AI-generated filler that's eroding trust and search performance — and triage what to fix, rewrite, or delete. Use when asked to find slop in a content library, audit AI-written content quality, explain why content engagement or rankings dropped after scaling with AI, or set a quality bar for AI-assisted publishing. Produces an audited inventory with per-piece verdicts, the detection signals used, a triage plan, and a publishing quality gate that prevents recurrence. For a single article's AI-citability use aeo-optimizer; for the strategy itself use content-calendar or seo-content-brief.
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。
Review AI-authored code for its characteristic failure modes — plausible-but-wrong logic, hallucinated APIs, over-engineering, dead scaffolding, and silent security shortcuts. Use when reviewing an AI-generated or heavily AI-assisted PR, when AI-written code keeps shipping subtle bugs, or when setting review standards for a team using coding agents. Produces a focused review with AI-specific findings, verification steps per risk class, and a team checklist for AI-authored changes. For general PR review use code-review-checklist — this skill covers what that one assumes a human wouldn't do.
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。
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
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。
Core conventions and patterns used in the Squad codebase
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。
Go and find the reels that are actually working right now in the user's niche, rank them by how far each beat its own account, name the hook formula each one used, and turn that into a swipe file they can shoot from. Use when the user says "find viral videos", "what's working right now", "what are people posting in my niche", "reverse engineer this account", "build me a swipe file", "why is this reel doing numbers", or asks what to make next and has no evidence to answer with.
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。
Pre-launch and pre-commit audit for vibe coding projects. Use when asked to check whether a project is ready to ship, deploy, merge, or commit, especially for common AI-built app mistakes: broken project structure, committed secrets or cache files, environment variable hygiene, database migrations, ORM/schema drift, unsafe raw SQL, unused legacy code, dead routes/components, weak auth, missing tests, build failures, and deployment footguns.
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。
A minimal, fully spec-conformant fixture skill used to exercise the happy path.
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。
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.
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。
Use when the user wants to pull data out of one or more PDFs (invoices, bank/credit-card statements, receipts, reports, tables) and put it into a spreadsheet. pdf_read is one of the most-used tools; this codifies the read-PDF → structure → write-Excel workflow. Powered by LMCP on macOS and Windows.
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 for UI/UX design, product flows, frontend or native interface design, design audits, design translation, asset planning, motion direction, design tokens, or distinctive non-generic apps and websites. Covers web and React, Windows and WinUI/Mica, Apple and SwiftUI, Android and Jetpack Compose/Material, cross-platform UI, and token export. Route to the focused skill, then load only the references required for the selected surface and failure mode.
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。
This skill should be used when the user asks to "agentize a website", "transform a website", "create an agentfront", "build a WWA app", "make an agent-first website", "turn a website into an agent experience", "agentizer", "wwa transform", or mentions "agentfront" in context of building one from a URL.
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。