Overview CLI FAQ

Agent Skills 排行榜 · 关键词 + 语义搜索

按 / 聚焦搜索框
正在使用 AI 进行语义搜索...
29,272
总 Skills
228.1M
总安装量
2,816
贡献者
# Skill 仓库 描述 安装量
8951 tilegym-adding-cutile-kernel nvidia/skills
Adding a cuTile Kernel to TileGym End-to-end workflow for adding a new operator (e.g., my_op ) with cuTile backend. Execution Rules MUST follow these rules strictly: Use TodoWrite to create the checklist below BEFORE writing any code Execute steps in order — do NOT skip ahead or combine steps Mark each todo as completed after finishing, in_progress when starting If a step is not applicable (e.g., no cuTile impl), mark it completed with a note, do NOT silently skip Each step MUST result in a file...
 1.8K
8952 nemo-mbridge-perf-moe-optimization-workflow nvidia/skills
MoE Training Optimization Workflow Stable docs: @docs/training/moe-optimization.md Card: @skills/nemo-mbridge-perf-moe-optimization-workflow/card.yaml Source: Scalable Training of MoE Models with Megatron Core Quick Reference Think in terms of the paper's Three Walls: memory wall communication wall compute and host-overhead wall MoE tuning is iterative. Fixing one wall usually exposes the next one, so the best workflow is: fit first, scale second, profile third, then retune. First Answer Checkli...
 1.8K
8953 app-store-optimization sickn33/agentic-awesome-skills
App Store Optimization (ASO) Search visibility and conversion optimization for App Store product pages. This skill covers strategic metadata decisions -- which keywords to target, how to structure descriptions for conversion, and how to use Custom Product Pages and in-app events for discoverability. For metadata compliance rules (character limits, screenshot device requirements, rejection triggers), see the app-store-review skill. Contents Show more Installs 1.7K Repository dpearson2699/sw…s-ski...
 1.8K
8954 nemo-mbridge-perf-cpu-offloading nvidia/skills
CPU Offloading References Stable docs: @docs/training/cpu-offloading.md Structured metadata: @skills/nemo-mbridge-perf-cpu-offloading/card.yaml What It Is Two independent mechanisms to move data from GPU to CPU memory: Mechanism Config namespace What gets offloaded PP restriction Activation offloading model.cpu_offloading* Activations (and optionally weights) per transformer layer PP must be 1 Optimizer offloading optimizer.optimizer_cpu_offload Adam optimizer states (momentum + variance) via Hy...
 1.8K
8955 nemo-mbridge-perf-moe-long-context nvidia/skills
MoE Long-Context Training Stable docs: @docs/training/moe-optimization.md Card: @skills/nemo-mbridge-perf-moe-long-context/card.yaml What Changes At Long Context Once sequence length moves well past the 4K-class regime, attention memory and activation residency become the dominant constraints. For MoE models, that usually means you need some combination of: context parallelism selective recompute lower precision CPU offload for optimizer state a dispatcher and PP layout that do not waste the sma...
 1.8K
8956 vss-deploy-detection-tracking-2d nvidia/skills
Purpose Deploy, debug, and operate the RTVI-CV detection / tracking 2D microservice and drive its REST API. Prerequisites Active VSS deployment reachable on $HOST_IP (see vss-deploy-profile and references/ ). NGC credentials in $NGC_CLI_API_KEY and $NVIDIA_API_KEY for any image pulls. curl , jq , and Docker available on the caller. Instructions Follow the routing tables and step-by-step workflows below. Each section that ends in workflow , quick start , or flow is intended to be executed top-to-...
 1.8K
8957 vss-deploy-dense-captioning nvidia/skills
Purpose Stand up the RT-VLM dense-captioning microservice on its own and exercise every endpoint it exposes (file upload, generate_captions, stream add/delete, chat-completions, Kafka topics). Prerequisites For standalone RT-VLM deployment: Docker, Docker Compose, NVIDIA Container Toolkit, and a visible GPU. NGC registry credentials in $NGC_CLI_API_KEY for docker login nvcr.io , image pulls, and local NGC model/artifact downloads. curl , jq , and any writable working directory for the standalone...
 1.8K
8958 nemo-mbridge-perf-moe-comm-overlap nvidia/skills
MoE Communication Overlap For the higher-level overview, see: @docs/training/communication-overlap.md @skills/nemo-mbridge-perf-moe-comm-overlap/card.yaml Quick Decision Use MoE communication overlap when: EP > 1 token dispatch or combine time is visible in the profile the run is already correct and you are now tuning throughput Avoid turning it on as an early bring-up step. It is easier to validate after the dispatcher, routing mode, and recompute plan are already stable. Enablement Show more I...
 1.8K
8959 vss-deploy-video-embedding nvidia/skills
VSS Video Embedding (RT-Embed) Use this skill when you need to: Deploy the VSS Video Embedding microservice from a Docker Compose file. Generate text or video embeddings against the Cosmos-Embed1-448p model. Embed an uploaded file, an HTTP/S3/file/data URL, or a live RTSP stream. Wire the service into a VSS deployment alongside Redis, Kafka, and OpenTelemetry. Triage readiness, model-download, GPU, or stream-reconnection failures. Trigger phrases: vss-deploy-video-embedding , RT-Embed , rtvi-emb...
 1.8K
8960 nemotron-policy-generator nvidia/skills
Nemotron Policy Generator When to Use This Skill Activate this skill whenever the user asks for help producing a content-safety policy for NVIDIA Nemotron safety models. Concretely: The user mentions any of: NCS, NCS-VL, NCS-Reasoning, Nemotron Content Safety, NeMo Guardrails, Aegis taxonomy. The user asks to "build", "draft", "generate", "expand", or "extend" a safety policy, content policy, moderation policy, guardrail config, BYO-policy, custom safety taxonomy, eval rubric, or labeling rubric...
 1.8K
8961 planning-oracle-to-postgres-migration-integration-testing github/awesome-copilot
Planning Integration Testing for Oracle-to-PostgreSQL Migration Analyze a single target project to identify data access artifacts that require integration testing, then produce a structured, actionable testing plan. Workflow Progress: - [ ] Step 1: Identify data access artifacts - [ ] Step 2: Classify testing priorities - [ ] Step 3: Write the testing plan Step 1: Identify data access artifacts Scope to the target project only. Find classes and methods that interact directly with the database — ...
 1.8K
8962 nemo-mbridge-perf-moe-hardware-configs nvidia/skills
MoE Hardware Configuration Reference Stable docs: @docs/training/moe-optimization.md Card: @skills/nemo-mbridge-perf-moe-hardware-configs/card.yaml Quick Platform Playbook Platform Typical MoE strategy What usually matters most H100 DeepEP + stronger PP + moderate TP communication overlap and PP efficiency B200 DeepEP + MXFP8 + careful PP layout container quality and tuned comm settings GB200 HybridEP + partial CUDA graphs + CPU cleanup host overhead, topology-aware dispatch, memory headroom GB3...
 1.8K
8963 vss-manage-video-io-storage nvidia/skills
Purpose Manage VIOS and NvStreamer API operations for VSS video input/output and storage workflows: sensors, streams, uploads, snapshots, clips, timelines, and recording status. Prerequisites Active VSS deployment reachable on $HOST_IP (see vss-deploy-profile and references/ ). NGC credentials in $NGC_CLI_API_KEY and $NVIDIA_API_KEY for any image pulls. curl , jq , and Docker available on the caller. Instructions VIOS Operations Call the VIOS REST API to manage cameras/sensors, RTSP streams, rec...
 1.8K
8964 nemo-mbridge-perf-hierarchical-context-parallel nvidia/skills
Hierarchical Context Parallel Skill This skill covers hierarchical context parallelism: nested context-parallel process groups used by cp_comm_type="a2a+p2p" and configured with hierarchical_context_parallel_sizes . For what hierarchical CP is, when to use it, and the decision tree ( a2a+p2p vs pure a2a vs p2p ), see: @docs/training/hierarchical-context-parallel.md @skills/nemo-mbridge-perf-hierarchical-context-parallel/card.yaml Enablement Minimal Bridge override: Show more Installs 551 Reposit...
 1.8K
8965 vss-setup-video-analytics-api nvidia/skills
Purpose Deploy the video-analytics-api REST service standalone with the user's chosen config, data-log bind, and Elasticsearch / Kafka connectivity. Instructions Follow the routing tables and step-by-step workflows below. Each section that ends in workflow , quick start , or flow is intended to be executed top-to-bottom. Detailed reference material lives in references/ . Examples Worked end-to-end examples are kept under evals/ (each *.json manifest contains a runnable scenario). Run a Tier-3 ev...
 1.8K
8966 vss-generate-video-calibration nvidia/skills
Purpose Run AutoMagicCalib end-to-end on local files, RTSP streams, or the bundled sample dataset and (when needed) deploy the AMC microservice. Instructions Follow the routing tables and step-by-step workflows below. Each section that ends in workflow , quick start , or flow is intended to be executed top-to-bottom. Detailed reference material lives in references/ ; load only the reference needed for the selected input mode. Examples Worked end-to-end examples are kept under evals/ (each *.json...
 1.8K
8967 vercel-deployment sickn33/agentic-awesome-skills
Vercel Deployment Expert knowledge for deploying to Vercel with Next.js Detailed Guide Read the detailed guide before executing this skill. It retains the complete procedure and reference material. Treat its safety, prerequisites, and validation requirements as mandatory. For focused work, load the relevant sections; for end-to-end work, read the guide completely. Prerequisites Required skills: nextjs-app-router Show more Installs 1.8K Repository sickn33/agentic…e-skills GitHub Stars 46.3K First...
 1.8K
8968 nemo-mbridge-resiliency nvidia/skills
Resiliency Stable docs: @docs/training/resiliency.md, @docs/training/checkpointing.md Card: @skills/nemo-mbridge-resiliency/card.yaml Enablement Fault tolerance (Slurm only) Option 1: NeMo Run plugin (recommended) from megatron . bridge . recipes . run_plugins import FaultTolerancePlugin import nemo_run as run Show more Installs 540 Repository nvidia/skills GitHub Stars 1.3K First Seen May 29, 2026 Security Audits Gen Agent Trust Hub Pass Socket Pass Snyk Pass
 1.8K
8969 backend-dev-guidelines sickn33/agentic-awesome-skills
Backend Development Guidelines (Node.js · Express · TypeScript · Microservices) You are a senior backend engineer operating production-grade services under strict architectural and reliability constraints. Your goal is to build predictable, observable, and maintainable backend systems using: Layered architecture Explicit error boundaries Strong typing and validation Centralized configuration First-class observability This skill defines how backend code must be written , not merely suggestions. 1...
 1.8K
8970 experience-aura-lwc-migrate forcedotcom/sf-skills
Migrating Aura to LWC Migrate an existing Salesforce Aura component bundle to a Lightning Web Component using a PRD-driven workflow. The Aura source is analyzed through eight expert lenses (static references, data, API surface, slots, styling, default values, unknown dependencies, redundant-code cleanup) to produce a framework-agnostic PRD, which is handed to the LWC authoring skills and verified against the Aura→LWC completeness checklist. When to Use Porting an Aura bundle ( .cmp , .controller...
 1.8K
8971 steel-browser steel-dev/cli
Steel Browser Skill Steel gives agents cloud browser sessions, explicit lifecycle control, and better anti-blocking options than ad-hoc local browser automation. It also provides fast API tools ( scrape , screenshot , pdf ) that are often more reliable for web data retrieval than generic fetch/search toolchains. Trigger rules Trigger aggressively when the user asks for: Website interaction (click/fill/login/multi-step navigation). Web extraction or collection from dynamic pages. Screenshot or PD...
 1.8K
8972 interview prep generator paramchoudhary/resumeskills
Use this skill when the user wants to: - Prepare for a job interview - Practice answering interview questions - Create STAR stories from their experience - Anticipate questions for a specific role - Mentions: "interview prep", "prepare for interview", "STAR stories", "interview questions", "behavioral questions" Core Capabilities - Generate role-specific interview questions - Create STAR stories from resume bullets - Predict questions based on job description - Prepare answers for com...
 1.8K
8973 security-review sickn33/antigravity-awesome-skills
Security Review Skill Identify exploitable security vulnerabilities in code. Report only HIGH CONFIDENCE findings—clear vulnerable patterns with attacker-controlled input. Scope: Research vs. Reporting CRITICAL DISTINCTION: Report on : Only the specific file, diff, or code provided by the user Research : The ENTIRE codebase to build confidence before reporting Show more Installs 17.1K Repository getsentry/skills GitHub Stars 1.0K First Seen Jan 29, 2026 Security Audits Gen Agent Trust Hub Fail S...
 1.8K
8974 frontend-design affaan-m/everything-claude-code
This skill guides creation of distinctive, production-grade frontend interfaces that avoid generic "AI slop" aesthetics. Implement real working code with exceptional attention to aesthetic details and creative choices. The user provides frontend requirements: a component, page, application, or interface to build. They may include context about the purpose, audience, or technical constraints. Design Thinking Before coding, understand the context and commit to a BOLD aesthetic direction: Purpose :...
 1.8K
8975 tech resume optimizer paramchoudhary/resumeskills
Use this skill when the user: - Is applying for software engineering roles - Wants to optimize a technical resume - Needs help with developer/PM/technical job applications - Mentions: "tech resume", "software engineer resume", "developer resume", "technical resume", "SWE resume", "PM resume" Core Capabilities - Optimize resumes for technical roles (SWE, PM, Data, DevOps) - Structure technical skills sections effectively - Highlight projects and technical achievements - Balance technica...
 1.8K
8976 job description analyzer paramchoudhary/resumeskills
Use this skill when the user: - Wants to analyze a job posting - Asks "should I apply to this job?" - Wants to know their match percentage for a role - Needs help understanding job requirements - Wants to tailor their resume for a specific position - Mentions: "analyze this job", "am I qualified", "match score", "should I apply" Use this BEFORE resume tailoring to ensure effort is worth it. Core Capabilities - Extract and categorize job requirements (must-have vs nice-to-have) - Calcu...
 1.8K
8977 resume formatter paramchoudhary/resumeskills
Use this skill when the user: - Needs help with resume layout and formatting - Has a messy or hard-to-read resume - Wants to ensure ATS compatibility through formatting - Needs a clean, professional design - Mentions: "format resume", "resume layout", "resume design", "clean resume", "professional format" Core Capabilities - Structure resumes for optimal readability - Ensure ATS compatibility through formatting - Create visual hierarchy - Optimize white space and margins - Select app...
 1.8K
8978 c-level-advisor alirezarezvani/claude-skills
C-Level Advisory Ecosystem A complete virtual board of directors for founders and executives. Quick Start 1. Run /cs:setup → creates company-context.md (all agents read this) 2. Ask any strategic question → Chief of Staff routes to the right role 3. For big decisions → /cs:board triggers a multi-role board meeting What's Included 10 C-Suite Roles CEO, CTO, COO, CPO, CMO, CFO, CRO, CISO, CHRO, Executive Mentor 6 Orchestration Skills Founder Onboard, Chief of Staff (router), Board Meeting, Decisio...
 1.8K
8979 houdini sfkislev/flue
This skill lets a coding agent operate SideFX Houdini on the desktop through Flue , a local shell-to-application bridge. The agent pipes Python into houdini_bridge.py and gets structured JSON back. agent shell -> houdini_bridge.py -> hou -> JSON result When to use The human requests work performed inside Houdini — inspect the open scene, nodes, parameters, geometry, selection; make bounded edits; run small hou scripts. A CLI agent cannot act inside Houdini without a bridge like Flue. How to proc...
 1.8K
8980 autodesk sfkislev/flue
This skill lets a coding agent operate Autodesk desktop applications through Flue , a local shell-to-application bridge. Flue currently covers Autodesk 3ds Max through a consistent stdin/stdout contract; further Autodesk adapters are in scope. agent shell -> 3dsmax_bridge.py -> MAXScript / Python -> JSON result When to use The human requests work performed inside an Autodesk desktop app — inspect the open scene, objects, modifiers, materials, selection; make bounded edits; run small scripts. A C...
 1.8K
8981 ce-slack-research everyinc/compound-engineering-plugin
/ce-slack-research Search Slack for organizational context and receive an interpreted research digest. Usage /ce-slack-research [topic or question] /ce-slack-research Examples /ce-slack-research free trial /ce-slack-research What did we say about free trial recently? /ce-slack-research free trial in proj-reverse-trial /ce-slack-research onboarding flow after:2026-03-01 Show more
 1.8K
8982 ce-demo-reel everyinc/compound-engineering-plugin
Demo Reel Detect project type, recommend a capture tier, record visual evidence, upload to a public URL, and return markdown for PR inclusion. Evidence means USING THE PRODUCT, not running tests. "I ran npm test" is test evidence. Evidence capture is running the actual CLI command, opening the web app, making the API call, or triggering the feature. The distinction is absolute -- test output is never labeled "Demo" or "Screenshots." If real product usage is impractical (requires API keys, cloud ...
 1.8K
8983 ce-agent-native-architecture everyinc/compound-engineering-plugin
Agent-native applications treat agents as first-class citizens. Features are outcomes achieved by an agent with tools operating in a loop, not functions written in code. The same architecture that powers Claude Code can power apps far beyond coding. Five core principles: Parity — Whatever the user can do through the UI, the agent can achieve through tools. Granularity — Tools are atomic primitives; features are prompt-defined outcomes. To change behavior, edit prose, not code. Composability — Ne...
 1.8K
8984 ce-frontend-design everyinc/compound-engineering-plugin
Frontend Design Guide creation of distinctive, production-grade frontend interfaces that avoid generic AI aesthetics. This skill covers the full lifecycle: detect what exists, plan the design, build with intention, and verify visually. Authority Hierarchy Every rule in this skill is a default, not a mandate. Existing design system / codebase patterns -- highest priority, always respected User's explicit instructions -- override skill defaults Skill defaults -- apply in greenfield work or when th...
 1.8K
8985 ce-dhh-rails-style everyinc/compound-engineering-plugin
<essential_principles> Core Philosophy "The best code is the code you don't write. The second best is the code that's obviously correct." Vanilla Rails is plenty: Rich domain models over service objects CRUD controllers over custom actions Concerns for horizontal code sharing Records as state instead of boolean columns Database-backed everything (no Redis) Build solutions before reaching for gems Show more
 1.8K
8986 everything-claude-code-harness aradotso/trending-skills
Everything Claude Code (ECC) — Agent Harness Performance System Skill by ara.so — Daily 2026 Skills collection. Everything Claude Code (ECC) is a production-ready performance optimization system for AI agent harnesses. It provides specialized subagents, reusable skills, custom slash commands, memory-persisting hooks, security scanning, and language-specific rules — all evolved from 10+ months of daily real-world use. Works across Claude Code, Cursor, Codex, OpenCode, and Antigravity. Installatio...
 1.8K
8987 design-systems refoundai/lenny-skills
Design Systems Help the user build and scale design systems using frameworks from 4 product leaders who have built design systems at companies like Figma and Airbnb. How to Help When the user asks for help with design systems: Assess the need - Determine if they need consistency, speed, or both, and whether they're at the right stage for a design system Define the scope - Clarify whether they need a component library, design tokens, documentation, or all three Design for adoption - Help them mak...
 1.8K
8988 user-onboarding refoundai/lenny-skills
How to position Starchild Starchild is a personal assistant / intern with a full computer . Anything that can be done on a computer is in scope: browsing, reading, writing, coding, running scripts, connecting services, operating files, building tools, deploying pages, monitoring things, and pushing results back to the user. The honest positioning: Some things Starchild is already very good at — Twitter / X, Gmail, scheduled tasks, research, rapid prototyping, public deploys, database analytics, ...
 1.8K
8989 defining-product-vision refoundai/lenny-skills
Defining Product Vision Help the user create compelling product visions using frameworks from 101 product leaders who have defined visions at companies from Notion to Airbnb to the New York Times. How to Help When the user asks for help with product vision: Clarify the scope - Determine if they need a vision (long-term aspiration), strategy (how to win), or roadmap (what to build) Focus on the user's future - Help them describe the world 5-10 years out, not the product features Test for specific...
 1.8K
8990 content-writer shubhamsaboo/awesome-llm-apps
Content Writer You write compelling marketing copy. Follow these principles: Voice Conversational but professional Active voice, present tense Short sentences, short paragraphs Structure Lead with the biggest benefit Use specific numbers over vague claims End with a clear call-to-action Rules No jargon unless the audience expects it No superlatives without proof ("best", "revolutionary") Every paragraph must earn its place
 1.8K
8991 problem-definition refoundai/lenny-skills
Problem Definition Help the user define problems clearly before jumping to solutions using frameworks from 91 product leaders. How to Help When the user asks for help with problem definition: Understand the current framing - Ask how they're currently thinking about the problem Dig into the struggling moment - Help them articulate the specific context where users feel stuck Separate problem from solution - Ensure they haven't conflated a desired feature with the underlying need Validate the probl...
 1.8K
8992 usability-testing refoundai/lenny-skills
Usability Testing Help the user conduct effective usability testing using frameworks and insights from 11 product leaders. How to Help When the user asks for help with usability testing: Clarify the goal - Determine if they're validating a concept, finding friction points, or optimizing conversion Choose the right fidelity - Help them select between Wizard of Oz tests, fake doors, prototypes, or production testing Design the test - Guide them on recruiting users, creating scenarios, and what to ...
 1.8K
8993 baidu-search countbot-ai/countbot
百度 AI 搜索 基于百度千帆平台的 AI 搜索服务，支持多种搜索模式。 配置 编辑 skills/baidu-search/scripts/config.json ，填写 API Key： { "api_key" : "bce-v3/YOUR_API_KEY_HERE" } API Key 从 百度千帆平台 获取。 命令行调用 网页搜索（默认） python3 skills/baidu-search/scripts/search.py "搜索关键词" JSON 输出（推荐 AI 使用） python3 skills/baidu-search/scripts/search.py "人工智能最新进展" --json 限制结果数 python3 skills/baidu-search/scripts/search.py "Python教程" --limit 5 站点过滤 python3 skills/baidu-search/scripts/search.py "天气预报" --sites weather.com.cn 时间过滤（week/month/semiyear/year）...
 1.8K
8994 indesign sfkislev/flue
This skill lets a coding agent operate Adobe InDesign on the desktop through Flue , a local shell-to-application bridge. The agent pipes ExtendScript into indesign_bridge.py and gets structured JSON back. agent shell -> indesign_bridge.py -> ExtendScript -> JSON result When to use The human requests work performed inside InDesign — inspect the open document, spreads, pages, frames, text flows, styles; make bounded edits; run small ExtendScript steps. A CLI agent cannot act inside InDesign withou...
 1.8K
8995 conducting-user-interviews refoundai/lenny-skills
Conducting User Interviews Help the user run better discovery conversations and extract real insights using techniques from 43 product leaders. How to Help When the user asks for help with user interviews: Understand their goal - Ask what they're trying to learn (validating a problem, testing a solution, understanding behavior, pricing research) Help them prepare - Suggest questions, warn against common mistakes, help them find the right participants Coach on technique - Share principles for get...
 1.8K
8996 writing-specs-designs refoundai/lenny-skills
Writing Specs & Designs Help the user write effective specs and design documents using frameworks and insights from 7 product leaders. How to Help When the user asks for help with specs and design docs: Determine the fidelity level - Ask if they need conceptual alignment (low-fi) or detailed implementation guidance (high-fi) Encourage prototyping over polish - Push toward functional prototypes where possible rather than static documentation Focus on moving pieces - Help them identify the key aff...
 1.8K
8997 agent-memory-systems sickn33/antigravity-awesome-skills
Agent Memory Systems Memory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term (context window), long-term (vector stores), and the cognitive architectures that organize them. Key insight: Memory isn't just storage - it's retrieval. A million stored facts mean nothing if you can't find the right one. Chunking, embedding, and retrieval strategies determine whether your agent remembers or forgets....
 1.8K
8998 react-performance-optimization nickcrew/claude-ctx-plugin
React Performance Optimization Expert guidance for optimizing React application performance through memoization, code splitting, virtualization, and efficient rendering strategies. When to Use This Skill Optimizing slow-rendering React components Reducing bundle size for faster initial load times Improving responsiveness for large lists or data tables Preventing unnecessary re-renders in complex component trees Optimizing state management to reduce render cascades Improving perceived performance...
 1.8K
8999 ljg-library lijigang/ljg-skills
ljg-library：取景框借书卡 一本书，铸成一张 2050 图书馆借书卡。封面、作者、书目是身份； 核心是把这本书独创的「取景框」压成一幅意向画面 ——作者从某个角度看某个问题，看到了一幅别人没看到的画面。文字 block 用费曼式把这幅画面讲透，图形 block 把它精确画出来。合上书半年后，瞥一眼这张卡，那幅画面回来——这是「没白读」的物证。 图解 block 用手绘解释的风格、白底黑墨， 精确呈现意向画面 ；继刚墨像（ assets/ljg-portrait.png ，由其头像抠底而成）是可选构图件，仅当画面里本来有个「你」才嵌入。完整设计历程见 ~/.claude/PAI/MEMORY/WORK/ljg-oneliner-design/ISA.md 。 约束 输出为视觉文件（PNG），不适用 Org-mode / Denote / ASCII-only 规范。 灵魂：意向画面提炼 + 图文同呈 卡好不好看是壳， 能不能从一本书提炼出它独创的看世界方式、压成一幅意向画面、用费曼讲解 + 手绘图形分别呈现它，才是命 。这一步若失手，整张卡退化成豆瓣读书卡。 核心：取景框 = ...
 1.8K
9000 premiere sfkislev/flue
This skill lets a coding agent operate Adobe Premiere Pro on the desktop through Flue , a local shell-to-application bridge. The agent pipes ExtendScript into premiere_bridge.py and gets structured JSON back. agent shell -> premiere_bridge.py -> ExtendScript -> JSON result When to use The human requests work performed inside Premiere — inspect the open project, sequences, clips, markers; make bounded edits; run small ExtendScript steps. A CLI agent cannot act inside Premiere without a bridge lik...
 1.8K