“dan”的搜索结果

协助使用FastAPI开发Python网页API，整理输入验证、错误处理和异步调用，并通过代码组织与缓存兼顾实现的可读性和响应性能。

• 设计API路由与输入验证
• 检查异步数据库与API调用
• 整理错误处理和日志

Find Danish jobs for graduates and highly educated candidates through Akademikernes Jobbank. Filter by industry, education, region, or remote work, then retrieve posting details for graduate trainee, Ph.d., postdoc, and other roles.

中文简介正在准备中。当前显示英语简介。

• Find graduate trainee positions
• Search for Ph.d. and postdoc openings
• Look for fully remote software jobs

Plan a simple daily attendance register covering check-in, check-out, hours, absences, and correction requests. When requested, generate empty templates in CSV, SQL, JSON Schema, or Notion mappings to prepare records for payroll input.

中文简介正在准备中。当前显示英语简介。

• Designing a daily check-in and check-out register
• Clarifying late arrival and half-day recording rules
• Creating empty attendance templates for payroll input

Build Claude Code plugin hooks: automated checks triggered by tool use or session events. Get guidance on prompt and command hooks for validating actions, checking task completion, loading context, and testing configurations.

中文简介正在准备中。当前显示英语简介。

• Checking dangerous commands before execution
• Verifying completion before the agent stops
• Loading project context when a session starts

Turn creative ideas into image and video generation prompts for character sheets, storyboards, and short films. The skill specifies consistent character details, reference image roles, camera movement, action sequences, and dialogue timing within the chosen model's limits.

中文简介正在准备中。当前显示英语简介。

• Write prompts for consistent character reference sheets
• Plan storyboard frames that show action progression
• Define how each reference image guides video generation

Design Google Cloud systems where multiple AI agents process live audio, video, or text and respond in real time. Guides requirements discovery, architecture diagrams, infrastructure code, deployment instructions, and validation for technical guidance or safety monitoring workloads.

中文简介正在准备中。当前显示英语简介。

• Design real-time technical guidance using live audio and video
• Plan hazard detection and visual inspection from video streams
• Create cloud architecture diagrams and deployment instructions

Keep repository contribution guidance consistent after workflow changes. Compare agent skills, coding guidance, contributor documentation, and issue and pull request templates, then fix contradictory instructions, outdated references, and mismatched inventories.

中文简介正在准备中。当前显示英语简介。

• Check guidance after adding or renaming skills
• Align issue and pull request conventions
• Find outdated workflow references

Create or review SECURITY.md guidance so Codex Security understands what to examine, which protections must hold, and what is excluded. Compare existing policies with repository evidence and preview proposed changes before writing.

中文简介正在准备中。当前显示英语简介。

• Define security review scope for a repository
• Document required security protections
• Check whether existing guidance matches the code

Create or review SECURITY.md guidance so Codex Security understands what to examine, which protections must hold, and what is excluded. Compare existing policies with repository evidence and preview proposed changes before writing.

中文简介正在准备中。当前显示英语简介。

• Define security review scope for a repository
• Document required security protections
• Check whether existing guidance matches the code

Audit AGENTS.md, rules, skills, and their references for broken paths or commands. Optional independent agent reviews assess redundant instructions and practical usefulness, producing reports that identify what to retain, review, or consider trimming.

中文简介正在准备中。当前显示英语简介。

• Checking paths and commands cited in agent instructions
• Finding redundant rules across skills and instructions
• Assessing which instruction files change agent behavior

Find the relevant DevOps guidance for version control, testing, delivery security, databases, performance, monitoring, and costs. This skill acts as an index, directing development and operations questions to the corresponding topic files.

中文简介正在准备中。当前显示英语简介。

• Finding guidance on Git branches and pull requests
• Locating testing strategies and delivery security guidance
• Finding database and performance optimization topics

Build Claude Code plugin hooks: automated checks triggered by tool use or session events. Get guidance on prompt and command hooks for validating actions, checking task completion, loading context, and testing configurations.

中文简介正在准备中。当前显示英语简介。

• Checking dangerous commands before execution
• Verifying completion before the agent stops
• Loading project context when a session starts

Create HTML stories where page progress controls a continuous camera journey. The workflow covers research, chapter planning, consistent AI images, Seedance scene and transition clips, interface design, media preparation, and browser checks.

中文简介正在准备中。当前显示英语简介。

• Create an immersive journey through connected scenes
• Present a timeline as a continuous camera journey
• Build a visual product story

Find language-specific guidance files for a code-testing pipeline. This reference catalog points agents to build and test commands, mocking patterns, common errors, and selected workflow examples across languages including .NET, Python, TypeScript, Go, and Java.

中文简介正在准备中。当前显示英语简介。

• Finding test guidance for a project's programming language
• Locating build commands and test framework guidance
• Finding mocking patterns and common error references

Build Claude Code plugin hooks: automated checks triggered by tool use or session events. Get guidance on prompt and command hooks for validating actions, checking task completion, loading context, and testing configurations.

中文简介正在准备中。当前显示英语简介。

• Checking dangerous commands before execution
• Verifying completion before the agent stops
• Loading project context when a session starts

Guides authorized source code security reviews across dangerous functions, data flow, authentication, logic flaws, and dependencies. Helps agents prioritize review paths and organize code locations, reproduction evidence, and remediation advice before drawing conclusions.

中文简介正在准备中。当前显示英语简介。

• Prioritizing entry points in a large codebase
• Tracing user input to dangerous functions
• Reviewing authentication, logic, and dependency risks

Plan and carry a Seedance video from brief through references, storyboard, generation handoff, shot-level review, and targeted repair. Use for an end-to-end Seedance production request; use a narrower prompt skill for a single prompt.

中文简介正在准备中。当前显示原文说明。

Two stages: first a single-page sheet of numbered panels from an image model, then that sheet fed to Seedance as the reference. The sheet owns order, framing and timing, and the video prompt only has to connect the panels. Use when the user wants a Seedance 2.5 / 2.0 video prompt for this kind of clip (Storyboard grid to video; 中文触发词: 分镜网格转视频, 分镜图, 九宫格, 故事板), or asks how published cases of this type were prompted. Read references/cases.md before drafting.

中文简介正在准备中。当前显示原文说明。

Generate a single 4-15s vertical video clip with ByteDance Seedance 2.0 reference-to-video via fal.ai, for shots with no realistic face (a product hero, a product in motion, an empty set). Multi-image reference (product + setting), ambient audio, internal multi-cut handling within one render, 720p by default. Routes through the GooseWorks FAL proxy (bills the Ads agent). Seedance refuses photoreal faces, so talking heads and creators go to creator-h3 / video-h3max.

中文简介正在准备中。当前显示原文说明。

Use when recreating a trending reel, TikTok or Short with a different performer: the same dance, moves, timing and camera, performed by the user's own character from a reference sheet, optionally in another outfit or a redecorated room, keeping the original song in sync. Keywords: reel recast, trend remake, TikTok dance, replace the dancer, character swap, choreography transfer, video to video, keep the music, Seedance edit mode.

中文简介正在准备中。当前显示原文说明。

Use when exploring several Seedance video takes before paying for a final: cheap 480p previews, variations of one shot to compare, reviewing and ranking takes before a pick, or finalizing a chosen preview to 1080p without regenerating it, including within its 7-day window. Keywords: Seedance draft, draft mode, draft complete, finalize, 480p preview, variations, takes, review, rank, pick, Seedance 2.5.

中文简介正在准备中。当前显示原文说明。

Use when a Seedance video must hold continuous movement across shots: dance choreography, fights, sports, or any performance where limbs teleport, feet slide, or motion resets at every cut, or when turning a storyboard and character sheet into a multi-shot sequence that plays as one take. Keywords: storyboard to video, choreography, movement control, pose chain, timecoded shot script, first and last frame chaining, character sheet, multi-shot continuity, Seedance 2.5 and 2.0.

中文简介正在准备中。当前显示原文说明。

Use when generating or editing video with Seedance models on Scenario via MCP: text-to-video, image-to-video, first and last frame anchors, reference-to-video from identity, product, or world references, prompt-based editing, extending a clip, audio-conditioned motion or voice, shot sound without music, first-frame versus reference conditioning, or an output blocked by moderation. Keywords: Seedance 2.5 and 2.0, ByteDance, T2V, I2V, V2V, native audio, OutputVideoSensitiveContentDetected.

中文简介正在准备中。当前显示原文说明。

Turns a brief, script, scene breakdown, treatment, or story idea into ONE connected director's shotlist for Seedance 2.0 — a single editable HTML artifact with a global Style Prefix, an @-asset glossary, and named per-scene prompts (1a, 1b, 2a…) each in Style → Characters → Scene → CUT 1..N form. Use whenever the user says 'make a shotlist', 'break this script into prompts', 'generate Seedance prompts for this ad/film', 'turn this brief into a shot list', 'director's shotlist', or wants many connected scene prompts rather than one. Also use to revise an existing shotlist (edit-once-propagates: 'change the style prefix everywhere', 'rewrite scene 4', 'split prompt 6'). Each prompt targets 15s; longer scenes split across 1a/1b/1c under one scene number.

中文简介正在准备中。当前显示原文说明。