「token」の検索結果

Apply GitHub repository security protections tier by tier — rulesets, read-only Actions token, secret scanning + push protection, Dependabot, and (gated) required status checks / required PR with a GitHub App bypass for a CI auto-commit bot. Mutating and confirmation-gated: always assess first, apply the no-regret baseline, then decide required checks separately. Use when hardening a public user-owned repo after an audit, when a repo has no branch protection, when adding required checks without breaking a bot that pushes to the default branch, or when provisioning a GitHub App bypass actor for trusted automation.

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。

Select an OCR/HTR engine by benchmarking candidates on the same labelled samples — source ground truth from open datasets (e.g. Hugging Face PAGE-XML corpora) or hand-transcription, wrap every engine behind a transcribe(image_path) -> str adapter (vision-LLMs via any OpenAI-compatible endpoint, dedicated HTR REST APIs, cloud OCR), and score with zero-dependency raw CER, lenient CER, WER, and a critical name/date token diff. Use when choosing an engine for handwriting or historical-document transcription, when published accuracy claims need honest verification on your own material, or when a records workflow must surface confident-but-wrong names and dates that a low aggregate CER hides.

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。

Read-only audit of a GitHub repository's security posture. Gathers ref protection (rulesets AND classic branch protection), Actions token permissions, code and supply-chain features (Dependabot, secret scanning, push protection, CodeQL), and repo hygiene toggles via `gh api`, then classifies findings against essential / recommended / advanced tiers into a PASS/GAP report. Makes NO changes. Use when reviewing a repo before open-sourcing or a release, auditing a public user-owned repo whose CI auto-commits to the default branch, verifying a hardening change actually took effect, or producing a baseline security posture report for a repository.

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。

NestJS module structure, dependency injection, lifecycle, configuration, exception handling, and logging conventions. Apply when implementing or modifying NestJS backend code. Use this skill to: - Structure feature modules (one feature = one module). - Wire DI correctly (constructor injection, scopes, custom tokens). - Set up ConfigModule, ValidationPipe, exception filters in main.ts. - Use lifecycle hooks for init and graceful shutdown. - Pick the right exception class for each error case. Do NOT use this skill for: - Decorator-specific patterns (see decorator-patterns). - ORM/data access (see nest-data-layer). - GraphQL/WebSockets/Microservices (see nest-advanced). - Testing (see nest-testing).

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。

Flask web framework conventions: app factory pattern with create_app(), Blueprint registration with url_prefix, MethodView for class-based API views, Marshmallow schema validation, WTForms for HTML forms, Flask-Login for session auth, flask-jwt-extended for stateless API auth, Jinja2 template conventions, error handlers, and extension initialization. Activated automatically by flask-plugin/stack.md. Use this skill to: - Structure Flask applications with the app factory and per-feature Blueprints. - Validate JSON request data with Marshmallow and HTML forms with WTForms. - Implement session-based auth with Flask-Login or token auth with flask-jwt-extended. - Render Jinja2 templates safely or return JSON responses for API mode. - Register global error handlers for consistent error responses. Do NOT use this skill for: - SQLAlchemy ORM model patterns and Flask-Migrate — see flask-plugin:sqlalchemy-patterns. - Python language idioms — see python-foundation:python-conventions. - Testing patterns — see python-foundation:pytest-testing.

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 parser, protocol, or file format fuzzer stalls at fixed-token validation gates and needs a coverage dictionary. Not for patching the SUT: use fuzzing-obstacles.

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 /design-variants generates distinct design directions and a gallery for selection. Not for one polished artifact: use polished-web-prototype. Not for token-system picking: use design.

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 to build or modify production-quality components, layouts, state, and pages with WCAG 2.1 AA and real content. Not for token-system design: use frontend-design-deslop.

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 starting UI work, defining palettes or tokens, fixing AI-generic UI, or persisting a design system to DESIGN.md (modes: implement, persist). Not for live URLs: use web-design-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。

Use when asked to audit typography across a codebase. Produces a file:line report with concrete fixes ordered by impact and flags unverifiable rules. Not for building a type system or token scale.

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 user builds or styles a web frontend or asks to make it not look AI-generated. Not for component-level UI work without the token system: use frontend-ui-engineering.

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 an explorable HTML report of Claude Code session usage (tokens, cache, subagents, skills, expensive prompts) from ~/.claude/projects transcripts.

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。

Compress any conversation into a portable JSON context graph for handoff to a new chat or LLM. Trigger on: "compress this chat", "save context", "new chat", "hand off", "transfer context", "too many tokens", "start fresh", "export conversation", "context graph", "continue in new session". Also trigger proactively when the user mentions starting over in a long session.

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 ANY bug bounty, penetration test, or web/API/mobile security assessment: recon, testing endpoints, analyzing Burp traffic or any bug-bounty platform's MCP (HackerOne, Intigriti, Bugcrowd, YesWeHack, Immunefi), reviewing APKs, bypassing a WAF, enforcing scope, hunting a specific vuln class, validating findings, writing reports, or when you are stuck on a target and about to give up. Activates automatically for all bug-bounty and pentest sessions. Runs an autonomous, never-surrender predator methodology: refuses to conclude "secure", exhausts each vuln class to depth, proves a real attacker-path with impact and no false positives, tracks coverage so nothing is re-tested or skipped, diagnoses failed tooling from full logs, and hunts at maximum effort with intelligent token use until the goal is found. Activates and follows instructions in ANY language the operator writes in (the skill itself is English). Bundles a per-class web-exploitation KB, a writeup library, and PayloadsAllTheThings.

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, document, or normalize a product UI design system from code, screenshots, or brand sources. Use for visual tokens, theme variables, typography, spacing, colors, radii, shadows, component inventories, variants, states, or building a reusable UI library. Do not use for software architecture, database schemas, or generic system design.

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 writing, reviewing, refactoring, or modernizing CSS/Tailwind. Apply a policy-first approach: semantic tokens, explicit cascade order, static CSS, intrinsic component layouts, accessible state, measured performance, and progressive enhancement backed by current sources.

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。

Authenticate to GitHub with a token, an SSH key, or the gh 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。

Reads, searches and counts Claude Code session transcripts (the .jsonl files under ~/.claude/projects, subagents too) with the csift command-line tool, and ships hooks that re-inject compacted turns or record pending questions. Use when asked what a past or running session said, did, edited, spent or is doing now; when about to grep, jq or script over a transcript jsonl (a type=="user" filter overcounts the person's messages), count how many messages the person typed, tool calls or tokens, or claim something was never done or decided; to rebuild a lost file or plan from what a session wrote, extract pasted images, restore turns a compaction summary lost, find a subagent's own id when CLAUDE_CODE_SESSION_ID names the parent, wait on or message another session or subagent; or when csift prints "unknown label selector", "show needs an address", "looks like a session/agent id, not a project path" or "0 matches — a DEFINITIVE absence". Not for semantic or embedding search: csift matches regular expressions only.

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。

重采样：把已有多轮对话数据的每条 assistant 回答丢弃，用 verifier 模型/vLLM 服务逐轮重生成，产出可直接进训练的预分词样本（每行含 input_ids/loss_mask）。依赖支持 return_token_ids 的 OpenAI 兼容 chat 服务（服务需由用户提前就绪，本技能不负责拉起服务）。触发：用某模型对某个数据集做重采样/重生成（如“对这个数据集用这个模型做重采样”）、把对话回答用模型重写、生成预分词样本/on-policy/MTP 训练数据。

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。

Connect every external account NowStack Mobile needs (Convex, Expo/EAS, Apple Developer, Vercel, Stripe, Google Play) by acquiring PROGRAMMATIC API ACCESS for each, then doing everything automatically through that access. Use for "setup accounts", "connect my accounts", first-run onboarding, or when check-setup reports CLI/auth gaps. The skill obtains a token/key per service, stores it in the right place, and only asks the user for the irreducible manual steps (browser signup, 2FA, one-time key download). Every account is skippable.

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 an interactive HTML brand playground that shows your brand rendered live — palette, typography, logo, voice — with a social card and OG image preview that updates as you tweak tokens. Opens in browser. The visual approval step for the /cmo flow: /visual-style writes the brand, this skill shows it. Use when the user says "show me my brand", "brand playground", "preview my brand", "what does our brand look like", "visual preview", "brand kit", "see my colors", "how does my brand look", or after /visual-style completes and the user needs to approve the visual identity before moving to content generation. Also use when someone says "I want to see it" during any brand-building conversation.

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。

Read tweets, threads, bookmarks, articles, and user timelines on X (formerly Twitter) using an authenticated GraphQL flow. Use this skill whenever the user mentions a tweet URL, a Twitter thread, an X bookmark, a Twitter article, reading their X bookmarks, pulling a thread, or grabbing X content — even if they don't explicitly say 'use mktg-x'. Requires MKTG_X_AUTH_TOKEN and MKTG_X_CT0 env vars. Do NOT firecrawl x.com URLs — Twitter serves a degraded logged-out page and firecrawl will return the login wall. mktg-x is the only path for auth-walled X content.

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。

Rate limiting for serverless and edge apps with the @upstash/ratelimit TypeScript/JavaScript SDK backed by Upstash Redis. Use when adding a rate limiter or throttling to an API route, Next.js middleware, Vercel Edge, Cloudflare Workers, or any HTTP endpoint; returning 429 Too Many Requests; choosing between fixed window, sliding window, and token bucket algorithms; limiting per user, IP, API key, or tenant with prefixes and custom keys; protecting login, signup, form, or AI endpoints from abuse, bots, and brute force; using deny lists, ephemeral caching, analytics, timeouts, and multi-region rate limits; or estimating the Redis command cost of rate limiting. Also use when the user says rate limit, rate-limiting, throttle, quota, request limits, or traffic protection.

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。

用前端渲染生成图片 —— 不依赖模型的多模态能力，任何能写 HTML/CSS 的模型 (DeepSeek / Claude / Kimi / GPT 等) 都能用。 当用户要「生成/做/画一张图」且属于以下任意一种时使用：头像、图标、公众号封面、 OG 分享图、Banner/横幅、小红书封面、知识卡片、金句卡、代码片段图、数据卡、 功能发布图、对比图、步骤图、视频封面/缩略图、幻灯片单页、活动海报、名片、 二维码卡、配图、题图、缩略图、poster、cover、thumbnail、banner、avatar。 也用于：批量出多个尺寸/多平台的同一张图；把一段文字/数据/代码变成图； 给文章配图；做一套风格统一的系列图。 支持指定视觉风格，共 32 套：手绘/涂鸦/白板、黑板、水彩、拼贴/剪贴、博物图鉴、 瑞士国际主义、杂志编辑部、报纸、工程蓝图、档案手稿/打字机、包豪斯、装饰艺术 Art Deco、 双色印刷 Riso、粗野主义、孟菲斯、美漫波普、像素 8-bit、千禧 Y2K、蒸汽波、霓虹赛博朋克、 街头海报/喷漆、日式侘寂、中式水墨、国潮/新中式、终端 CLI、极光渐变、玻璃拟态、 奢侈品黑金、极简产品、电影海报、复古未来 70s、极简线条。 用户没指定时主动报 3~4 个候选让他选；说了库里没有的风格就按四步法拆成 token。 产出一个可预览的画板工作台页面，多种画幅并排展示，点按钮即可导出 PNG (页内零依赖导出 + 本机 Chrome 精确出图两条通道)。 不适用：需要照片级真实内容的图（人像、风景、材质渲染）—— 那需要真正的图像模型。

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。