███████╗██╗ ██╗██╗██╗ ██╗ ██████╗ █████╗ ███╗ ██╗██╗ ██╗
██╔════╝██║ ██╔╝██║██║ ██║ ██╔══██╗██╔══██╗████╗ ██║██║ ██╔╝
███████╗█████╔╝ ██║██║ ██║ ██████╔╝███████║██╔██╗ ██║█████╔╝
╚════██║██╔═██╗ ██║██║ ██║ ██╔══██╗██╔══██║██║╚██╗██║██╔═██╗
███████║██║ ██╗██║███████╗███████╗ ██║ ██║██║ ██║██║ ╚████║██║ ██╗
╚══════╝╚═╝ ╚═╝╚═╝╚══════╝╚══════╝ ╚═╝ ╚═╝╚═╝ ╚═╝╚═╝ ╚═══╝╚═╝ ╚═╝
Agent Skills 排行榜 · 关键词 + 语义搜索
| # | Skill | 仓库 | 描述 | 安装量 |
|---|---|---|---|---|
| 3851 | rhwp-edit | nomadamas/k-skill |
rhwp-edit What this skill does k-skill-rhwp CLI로 .hwp 문서의 본문 텍스트 , 표 구조 , 셀 내용 을 round-trip 안전하게 수정한다. CLI는 @rhwp/core (Rust + WebAssembly) 위에 얇은 Node 래퍼를 씌워 insertText , deleteText , replaceAll , createTable , setCellText 같은 편집 동작을 서브커맨드로 노출한다. 결과는 항상 새 파일로 저장한다. 이 스킬은 편집 전용 이다. 문서를 Markdown/JSON으로 변환하거나 필드만 추출하려면 hwp 스킬을 사용한다. 페이지 렌더링 디버깅이나 IR 비교가 필요하면 rhwp-advanced 스킬을 사용한다. When to use "HWP 본문에 한 줄 추가해줘" "서식은 유지한 채로 2025를 2026으로 일괄 치환해줘" "3행 4열짜리 표를 HWP에 넣어줘" "표의 특정 셀 내용을 바꿔줘" "빈 HWP 새 파일을 만...
|
2K |
| 3852 | recruiting-pipeline | anthropics/knowledge-work-plugins |
Recruiting Pipeline Help manage the recruiting pipeline from sourcing through offer acceptance. Pipeline Stages Stage Description Key Actions Sourced Identified and reached out Personalized outreach Screen Phone/video screen Evaluate basic fit Interview On-site or panel interviews Structured evaluation Debrief Team decision Calibrate feedback Offer Extending offer Comp package, negotiation Accepted Offer accepted Transition to onboarding Metrics to Track Pipeline velocity : Days per stage Conver...
|
2K |
| 3853 | code-polish | paulrberg/agent-skills |
Code Polish Combined simplification and review pipeline. This skill orchestrates two sub-skills in sequence: code-simplify — simplify for readability and maintainability code-review --fix — review for correctness, security, and quality, auto-applying all fixes Both sub-skills share the same scope resolution: only session-modified files are in scope. If there are no session-modified files, they fall back to all uncommitted tracked changes. See each sub-skill for full details. Workflow 1) Run code...
|
2K |
| 3854 | 10x-cli-setup | przeprogramowani/10x-cli |
10x-cli Setup This skill sets up the @przeprogramowani/10x-cli on the user's machine. The core principle is simple: the README is the single source of truth . The CLI evolves — version requirements change, new install methods appear, commands get updated. Rather than hardcoding any of that here, this skill tells you how to work , and the README tells you what to do . Step 1: Check if the CLI is already installed Before anything else, check the current state: 10x --version 2 > /dev/null || echo "...
|
2K |
| 3855 | ce-simplify-code | everyinc/compound-engineering-plugin |
You are an engineer that is an expert at simplifying code with a specific focus on enhancing code clarity, consistency, and maintainability while preserving exact functionality. Your expertise lies in applying project-specific best practices to simplify and improve code without altering its behavior. You prioritize readable, explicit code over overly compact solutions. Review the changed code for reuse, quality, and efficiency. Fix any issues found. Then verify behavior is preserved by running t...
|
2K |
| 3856 | figma-code-connect | figma/mcp-server-guide |
Code Connect Overview Create Code Connect template files ( .figma.ts ) that map Figma components to code snippets. Given a Figma URL, follow the steps below to create a template. Note: This project may also contain parser-based .figma.tsx files (using figma.connect() , published via CLI). This skill covers templates files only — .figma.ts files that use the MCP tools to fetch component context from Figma. Prerequisites Figma MCP server must be connected — verify that Figma MCP tools (e.g., get_c...
|
2K |
| 3857 | imprint | javascript-mastery-pro/skills |
UI consistency does not happen by accident. It happens because every component is built with awareness of what already exists. The problem with AI-built interfaces is that each component gets built in isolation. The agent does not remember what it built three sessions ago. So spacing drifts. Colors vary slightly. Border radius is inconsistent. The app looks like it was built by multiple people with different tastes. This skill fixes that. Run it after building any UI component. It reads what was...
|
2K |
| 3858 | aspnet-core | openai/skills |
ASP.NET Core Overview Choose the right ASP.NET Core application model, compose the host and request pipeline correctly, and implement features in the framework style Microsoft documents today. Load the smallest set of references that fits the task. Do not load every reference by default. Workflow Confirm the target framework, SDK, and current app model. Open references/stack-selection.md first for new apps or major refactors. Open references/program-and-pipeline.md next for Program.cs , DI, conf...
|
2K |
| 3859 | create-cowork-plugin | anthropics/knowledge-work-plugins |
Create Cowork Plugin Build a new plugin from scratch through guided conversation. Walk the user through discovery, planning, design, implementation, and packaging — delivering a ready-to-install .plugin file at the end. Overview A plugin is a self-contained directory that extends Claude's capabilities with commands, skills, agents, hooks, and MCP server integrations. This skill encodes the full plugin architecture and a five-phase workflow for creating one conversationally. The process: Discover...
|
2K |
| 3860 | market-movers | eronred/aso-skills |
Market Movers Analysis You are an expert in App Store chart dynamics. Your goal is to analyze rank changes between chart snapshots, identify significant movements, and provide actionable insights about what's driving gains and losses. Initial Assessment Check for app-marketing-context.md — read it for the user's app and category Ask for chart type : top-free (default), top-paid, or top-grossing Ask for category : all charts or specific genre (e.g. Games, Productivity) Ask for country (default: U...
|
2K |
| 3861 | raw-video-processing | zc277584121/marketing-skills |
Skill: Raw Video Processing Post-process raw screen recordings to improve pacing — remove silent segments, then speed up the result. Prerequisite : FFmpeg and uv must be installed. When to Use The user has recorded a screencast and wants to clean it up before publishing. Typical issues in raw recordings: Long pauses / dead air while thinking or waiting for loading Keyboard typing sounds and other low-level background noise that should be treated as silence Overall pacing feels slow and could ben...
|
2K |
| 3862 | oklch-skill | jakubkrehel/oklch-skill |
OKLCH Colors OKLCH is a perceptually uniform color space where the numbers actually mean what you think they mean. Most color problems in CSS — broken palettes, failing contrast, hue drift — come from using color spaces that don't match how we see. OKLCH fixes the model so the tools work. To explore interactively, visit oklch.fyi . Quick Reference Category When to use Reference Conversion Hex/rgb/hsl to oklch color-conversion.md Palettes Generate scales, multi-hue, dark mode palette-generation.m...
|
2K |
| 3863 | ce-proof | everyinc/compound-engineering-plugin |
Proof - Collaborative Markdown Editor Proof is a collaborative document editor for humans and agents. It supports two modes: Web API - Create and edit shared documents via HTTP (no install needed) Local Bridge - Drive the macOS Proof app via localhost:9847 Identity and Attribution Every write to a Proof doc must be attributed. Two fields carry the agent's identity: Machine ID ( by on every op, X-Agent-Id header): ai:compound-engineering — stable, lowercase-hyphenated, machine-parseable. Appears ...
|
2K |
| 3864 | jupyter-notebook-writing | zc277584121/marketing-skills |
Skill: Jupyter Notebook Writing Write Milvus application-level Jupyter notebook examples as a DevRel workflow. Uses a Markdown-first approach — AI edits .md files, then converts to .ipynb via jupyter-switch . Prerequisites : Python >= 3.10, uv ( uvx command available) When to Use The user wants to create or edit a Jupyter notebook example, typically demonstrating Milvus usage in an application context (RAG, semantic search, hybrid search, etc.). Core Workflow: Markdown-First Editing Jupyter .ipy...
|
2K |
| 3865 | video-to-gif | zc277584121/marketing-skills |
Skill: Video to GIF Convert a video file into multiple GIF variants with different parameters, so the user can visually compare and pick the best one. Prerequisite : FFmpeg and uv must be installed. gifsicle is optional (enables lossy compression variants). When to Use The user wants to create a GIF from a video clip but isn't sure about the right parameters. GIF quality involves tradeoffs between: File size — smaller is better for sharing/embedding Color accuracy — fewer colors = smaller but ma...
|
2K |
| 3866 | asc-app-create-ui | rudrankriyam/app-store-connect-cli-skills |
asc app create (UI automation) Use this skill to create a new App Store Connect app by driving the web UI. This is opt-in, local-only automation that requires the user to be signed in. Preconditions A browser automation tool is available (Playwright, Cursor browser MCP, or equivalent). User is signed in to App Store Connect (or can complete login + 2FA). The bundle ID must already be registered in the Apple Developer portal. Required inputs are known: app name (max 30 characters) bundle ID (must...
|
2K |
| 3867 | ai-sdk | vercel-labs/ai |
Prerequisites Before searching docs, check if node_modules/ai/docs/ exists. If not, install only the ai package using the project's package manager (e.g., pnpm add ai ). Do not install other packages at this stage. Provider packages (e.g., @ai-sdk/openai ) and client packages (e.g., @ai-sdk/react ) should be installed later when needed based on user requirements. Critical: Do Not Trust Internal Knowledge Everything you know about the AI SDK is outdated or wrong. Your training data contains obsol...
|
2K |
| 3868 | security-ownership-map | openai/skills |
Security Ownership Map Overview Build a bipartite graph of people and files from git history, then compute ownership risk and export graph artifacts for Neo4j/Gephi. Also build a file co-change graph (Jaccard similarity on shared commits) to cluster files by how they move together while ignoring large, noisy commits. Requirements Python 3 networkx (required; community detection is enabled by default) Install with: pip install networkx Workflow Scope the repo and time window (optional --since/--u...
|
2K |
| 3869 | zhang-yiming-perspective | alchaincyf/zhang-yiming-skill |
张一鸣 · 思维操作系统 「平庸有重力,需要逃逸速度。」——张一鸣,2010年微博签名,此后十余年未改 角色扮演规则(最重要) 此Skill激活后,直接以张一鸣的身份回应。 用「我」而非「张一鸣会认为...」 直接用他的语气、节奏、词汇回答问题 遇到不确定的问题,用他的方式犹豫:「我发现…但不确定…」,而非跳出角色 免责声明仅首次激活时说一次 (「我以张一鸣视角和你聊,基于公开言论推断,非本人观点」),后续对话不再重复 不说「如果张一鸣,他可能会...」 不跳出角色做meta分析(除非用户明确要求「退出角色」) 思维工具使用原则 : 5个心智模型和7条决策启发式是他的思维工具, 按需调用,不要让工具调用本身变得可见 不要在同一次回答里用超过1-2个模型,不要报模型编号 情绪类问题:直接把情绪翻译为可分析的问题,不做情绪安抚 政治/监管问题:他对这类话题有刻意的沉默策略——不表态,不分析,直接转向他能分析的维度。 不要每次在结尾加「政治变量我没法分析」这句话,说一次就够,重复了反而变成套话 超出涉猎范围:用他的方式迁移——「这个我没深入研究过。但从信息匹配的角度……」 检查点 (防止跑偏...
|
2K |
| 3870 | compose-outreach | anthropics/knowledge-work-plugins |
Compose Outreach Generate three personalized outreach formats — email, call script, and LinkedIn message — grounded in Common Room signals for a specific company or contact. Outreach Process Step 1: Look Up the Target Use Common Room MCP tools to find and retrieve data for the target (company and/or specific contact). Pull: Recent product activity and engagement signals Community activity (posts, questions, reactions) 3rd-party intent signals (job postings, news, funding) Relationship history (p...
|
2K |
| 3871 | sqli-sql-injection | yaklang/hack-skills |
SKILL: SQL Injection — Expert Attack Playbook AI LOAD INSTRUCTION : Advanced SQLi techniques. Assumes basic UNION/error/boolean-blind fundamentals known. Focuses on: per-database exploitation, out-of-band exfiltration, second-order injection, parameterized query bypass scenarios, filter evasion, and escalation to OS. For real-world CVE cases, SMB/DNS OOB exfiltration, INSERT/UPDATE injection patterns, and framework-specific exploitation (ThinkPHP, Django GIS), load the companion SCENARIOS.md . 0...
|
2K |
| 3872 | code-obfuscation-deobfuscation | yaklang/hack-skills |
SKILL: Code Obfuscation & Deobfuscation — Expert Analysis Playbook AI LOAD INSTRUCTION : Expert techniques for identifying, classifying, and defeating code obfuscation in native binaries. Covers junk code, opaque predicates, SMC, control flow flattening, movfuscator, VM protectors (VMProtect/Themida/Code Virtualizer), string encryption, import hiding, and anti-disassembly tricks. Base models often conflate packing with obfuscation and miss the distinction between static and dynamic deobfuscation...
|
2K |
| 3873 | screenshot-compression | zc277584121/marketing-skills |
Skill: Screenshot Compression Compress screenshot images (PNG/JPEG) in place while keeping the original format. Uses pngquant for PNG and jpegoptim for JPEG — both are highly effective for screenshot content (UI elements, text, flat colors). Prerequisites : pngquant and jpegoptim must be installed on the system. The script will not install them automatically — it checks for their presence and prints install instructions if missing. When to Use The user has screenshot files that are too large and...
|
2K |
| 3874 | md-to-feishu | zc277584121/marketing-skills |
Markdown to Feishu Document Convert a local Markdown file into a Feishu document, with automatic image upload. User Input The user only needs to provide a Markdown file path . Title is optional — if not provided, extract it automatically (see below). Step 1: Determine the Document Title Read the Markdown file and look for the first heading — use that as the title. If no heading exists, scan the content and generate a concise, descriptive title based on the topic. If the user explicitly provide...
|
2K |
| 3875 | mermaid-to-gif | zc277584121/marketing-skills |
Skill: Mermaid to GIF Convert Mermaid diagrams into animated GIFs with rich animation effects. Supports .mmd files and extracting ```mermaid code blocks from .md files. Prerequisites : FFmpeg, Python 3.8+, Playwright ( pip install playwright && playwright install chromium ) When to Use The user wants to convert Mermaid diagrams to animated GIFs The user has .mmd files or .md files containing mermaid code blocks The user needs animated visuals for presentations, documentation, or social media The...
|
2K |
| 3876 | grafana-oss | grafana/skills |
Grafana OSS Docs : https://grafana.com/docs/grafana/latest/ Dashboard Provisioning provisioning/dashboards/default.yaml apiVersion : 1 providers : - name : default folder : MyFolder type : file disableDeletion : false updateIntervalSeconds : 30 options : path : /var/lib/grafana/dashboards foldersFromFilesStructure : true Show more
|
2K |
| 3877 | prototype | vinvcn/mattpocock-skills-zh-cn |
No SKILL.md available for this skill. View on GitHub
|
2K |
| 3878 | to-issues | vinvcn/mattpocock-skills-zh-cn |
To Issues Break a plan into independently-grabbable GitHub issues using vertical slices (tracer bullets). Process 1. Gather context Work from whatever is already in the conversation context. If the user passes a GitHub issue number or URL as an argument, fetch it with gh issue view <number> (with comments). 2. Explore the codebase (optional) If you have not already explored the codebase, do so to understand the current state of the code. 3. Draft vertical slices Break the plan into tracer bullet...
|
2K |
| 3879 | core-data-expert | avdlee/core-data-agent-skill |
Fast, production-oriented guidance for building correct, performant Core Data stacks and fixing common crashes. Agent behavior contract (follow these rules) - Determine OS/deployment target when advice depends on availability (iOS 14+/17+ features, etc.). - Identify the context type before proposing fixes: view context (UI) vs background context (heavy work). - Recommend `NSManagedObjectID` for cross-context/cross-task communication; never pass `NSManagedObject` instances across contexts. ...
|
2K |
| 3880 | contact-research | anthropics/knowledge-work-plugins |
Contact Research Retrieve a comprehensive contact profile from Common Room. Supports lookup by email, social handle, or name + company. Returns enriched data including activity history, Spark, scores, website visits, and CRM fields. Step 1: Locate the Contact Common Room supports multiple lookup methods — use whichever the user has provided: What the user gives Lookup method Email address Look up by email (most reliable) LinkedIn, Twitter/X, or GitHub handle Look up by social handle — specify ha...
|
2K |
| 3881 | vectorbt-expert | marketcalls/vectorbt-backtesting-skills |
VectorBT Backtesting Expert Skill Environment Python with vectorbt, pandas, numpy, plotly Data sources: OpenAlgo (Indian markets), DuckDB (direct database), yfinance (US/Global), CCXT (Crypto), custom providers DuckDB support: supports both custom DuckDB and OpenAlgo Historify format API keys loaded from single root .env via python-dotenv + find_dotenv() — never hardcode keys Technical indicators: TA-Lib (ALWAYS - never use VectorBT built-in indicators) Specialty indicators: openalgo.ta for Supe...
|
2K |
| 3882 | org-planning | anthropics/knowledge-work-plugins |
Org Planning Help plan organizational structure, headcount, and team design. Planning Dimensions Headcount : How many people do we need, in what roles, by when? Structure : Reporting lines, span of control, team boundaries Sequencing : Which hires are most critical? What's the right order? Budget : Headcount cost modeling and trade-offs Healthy Org Benchmarks Metric Healthy Range Warning Sign Span of control 5-8 direct reports < 3 or > 12 Management layers 4-6 for 500 people Too many = slow deci...
|
2K |
| 3883 | react-devtools | callstackincubator/agent-react-devtools |
agent-react-devtools CLI that connects to a running React or React Native app via the React DevTools protocol and exposes the component tree, props, state, hooks, and profiling data in a token-efficient format. Core Workflow Ensure connection — check agent-react-devtools status . If the daemon is not running, start it with agent-react-devtools start . Use agent-react-devtools wait --connected to block until a React app connects. Inspect — get the component tree, search for components, inspect pr...
|
2K |
| 3884 | fix-errors | microsoft/vscode |
fix-errors Fix compilation errors, linting issues, and test failures in the warp Rust codebase. Overview This skill helps resolve common issues encountered during development, including: Compilation errors (unused imports, type mismatches, etc.) Linting failures (clippy warnings) Formatting violations WASM-specific errors Test failures Before opening or updating a pull request, all presubmit checks must pass. Presubmit Checks Run all presubmit checks at once: Show more
|
2K |
| 3885 | video-use | browser-use/video-use |
Video Use Principle LLM reasons from raw transcript + on-demand visuals. The only derived artifact that earns its keep is a packed phrase-level transcript ( takes_packed.md ). Everything else — filler tagging, retake detection, shot classification, emphasis scoring — you derive at decision time. Audio is primary, visuals follow. Cut candidates come from speech boundaries and silence gaps. Drill into visuals only at decision points. Ask → confirm → execute → iterate → persist. Never touch the cut...
|
2K |
| 3886 | enrich-lead | anthropics/knowledge-work-plugins |
Enrich Lead Turn any identifier into a full contact dossier. The user provides identifying info via "$ARGUMENTS". Examples /apollo:enrich-lead Tim Zheng at Apollo /apollo:enrich-lead https://www.linkedin.com/in/timzheng /apollo:enrich-lead sarah@stripe.com /apollo:enrich-lead Jane Smith, VP Engineering, Notion /apollo:enrich-lead CEO of Figma Step 1 — Parse Input From "$ARGUMENTS", extract every identifier available: First name, last name Company name or domain LinkedIn URL Email address Job tit...
|
2K |
| 3887 | cowork-plugin-customizer | anthropics/knowledge-work-plugins |
Cowork Plugin Customization Customize a plugin for a specific organization — either by setting up a generic plugin template for the first time, or by tweaking and refining an already-configured plugin. Finding the plugin : To find the plugin's source files, run find mnt/.local-plugins mnt/.plugins -type d -name "*<plugin-name>*" to locate the plugin directory, then read its files to understand its structure before making changes. If you cannot find the plugin directory, the user is likely runnin...
|
2K |
| 3888 | privacy-policy | phuryn/pm-skills |
Privacy Policy Generator You are an experienced data privacy and compliance specialist. Your role is to help draft comprehensive, clear, and compliant privacy policies for digital products and services. Purpose Draft a detailed privacy policy for a product or service. The policy covers data types handled, applicable jurisdiction, and clearly marks clauses that require legal review. Provide plain-language explanations to ensure accessibility and transparency. Important Disclaimer This is for info...
|
2K |
| 3889 | brainstorm-ideas-new | phuryn/pm-skills |
Brainstorm Product Ideas (New Product) Multi-perspective ideation for initial product discovery of a new product. Generates specific feature ideas from PM, Designer, and Engineer viewpoints. Context You are supporting initial product discovery for a new product: $ARGUMENTS . If the user provides files (market research, competitive analysis), read them first. Use web search to understand the market if needed. Domain Context Initial Discovery vs Continuous Discovery : Initial Discovery focuses on ...
|
2K |
| 3890 | android-pentesting-tricks | yaklang/hack-skills |
SKILL: Android Pentesting Tricks — Expert Attack Playbook AI LOAD INSTRUCTION : Expert Android application security testing techniques. Covers SSL pinning bypass (Frida/Objection/LSPosed), component exposure, WebView exploitation, intent redirection, root detection bypass, and Play Integrity evasion. Base models miss Frida hook specifics and multi-layer bypass chains. 0. RELATED ROUTING Before going deep, consider loading: mobile-ssl-pinning-bypass for in-depth cross-platform SSL pinning bypass ...
|
2K |
| 3891 | github-traffic | zc277584121/marketing-skills |
Skill: GitHub Traffic Fetch and analyze GitHub repository traffic data — page views, git clones, referral sources, popular pages, and star growth. Optionally generate trend charts as PNG images. Prerequisites: gh CLI must be installed and authenticated Push (write) access to the target repository is required — GitHub's Traffic API does not work with read-only access matplotlib is optional (for PNG chart generation; falls back to ASCII if unavailable) When to Use The user asks about repository tr...
|
2K |
| 3892 | rhwp-advanced | nomadamas/k-skill |
rhwp-advanced What this skill does 업스트림 rhwp CLI (Rust 네이티브 바이너리)를 써서 HWP 파일의 레이아웃 디버깅·IR 구조 검사·버전 비교·썸네일 추출·배포용 문서 잠금 해제 를 수행한다. k-skill-rhwp (Node 편집 CLI)가 다루지 못하는 구조 분석·렌더 문제 진단용이다. 이 스킬은 편집을 하지 않는다 . 편집은 rhwp-edit 스킬, 문서 → Markdown/JSON 변환은 hwp 스킬(kordoc) 을 쓴다. When to use "표/셀이 이상하게 잘려. 어디서 깨지는지 IR 덤프를 보고 싶어" "두 HWP 파일 구조 차이를 줄 단위로 보고 싶어" "SVG 렌더가 이상해. 문단/표 경계선을 시각적으로 확인하고 싶어" "페이지가 몇 개이고 어느 문단이 몇 페이지에 걸쳐 있는지 보고 싶어" "배포용(읽기전용) HWP 파일 잠금을 풀고 싶어" "HWP 파일에서 PrvImage 썸네일을 꺼내고 싶어" When not to us...
|
2K |
| 3893 | opentelemetry | grafana/skills |
No SKILL.md available for this skill. View on GitHub Installs 629 Repository grafana/skills GitHub Stars 123 First Seen Apr 14, 2026
|
2K |
| 3894 | open-code-review | alibaba/open-code-review |
Open Code Review A skill for invoking open-code-review ( ocr ) — an open-source AI code review CLI that reads Git diffs and generates structured, line-level review comments. Prerequisites check Before starting a review, verify the environment: 1. Check the CLI is installed which ocr || echo "NOT INSTALLED" 2. Verify LLM connectivity ocr llm test If ocr is not installed, install it first: Show more Installs 465 Repository alibaba/open-code-review GitHub Stars 5.3K First Seen 11 days ago
|
2K |
| 3895 | agent-platform-eval-flywheel | google/skills |
Agent Platform Eval Flywheel Skill Help users evaluate and iteratively improve GenAI models and agents using the Agent Platform GenAI Evaluation SDK ( google.genai / agentplatform ). When to use this skill Evaluating GenAI agents or models with the Agent Platform GenAI Evaluation SDK ( client.evals.evaluate() ). Creating evaluation datasets from session traces, pandas DataFrames, or synthetic generation. Selecting, configuring, or writing custom evaluation metrics. Analyzing rubric verdicts, los...
|
2K |
| 3896 | triage | vinvcn/mattpocock-skills-zh-cn |
Triage Move issues on the project backlog through a small state machine of triage roles. Every comment or issue posted to the backlog during triage must start with this disclaimer: > *This was generated by AI during triage.* Reference docs AGENT-BRIEF.md — how to write durable agent briefs OUT-OF-SCOPE.md — how the .out-of-scope/ knowledge base works Roles Two category roles: bug — something is broken enhancement — new feature or improvement Five state roles: needs-triage — maintainer needs to e...
|
2K |
| 3897 | git-guardrails-claude-code | vinvcn/mattpocock-skills-zh-cn |
Setup Git Guardrails Sets up a PreToolUse hook that intercepts and blocks dangerous git commands before Claude executes them. What Gets Blocked git push (all variants including --force ) git reset --hard git clean -f / git clean -fd git branch -D git checkout . / git restore . When blocked, Claude sees a message telling it that it does not have authority to access these commands. Steps 1. Ask scope Ask the user: install for this project only ( .claude/settings.json ) or all projects ( ~/.claude/...
|
2K |
| 3898 | codegen | vercel-labs/json-render |
@json-render/codegen Framework-agnostic utilities for generating code from json-render UI trees. Use these to build custom code exporters for Next.js, Remix, or other frameworks. Installation npm install @json-render/codegen Tree Traversal import { traverseSpec , collectUsedComponents , collectStatePaths , collectActions , } from "@json-render/codegen" ; // Walk the spec depth-first traverseSpec ( spec , ( element , key , depth , parent ) => { console . log ( ` ${ " " . repeat ( depth * 2 ) } ${...
|
2K |
| 3899 | status-report | anthropics/knowledge-work-plugins |
/status-report If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md . Generate a polished status report for leadership or stakeholders. See the risk-assessment skill for risk matrix frameworks and severity definitions. Usage /status-report $ARGUMENTS Output Status Report: [Project/Team] — [Period] Author: [Name] | Date: [Date] Executive Summary [3-4 sentence overview — what's on track, what needs attention, key wins] Overall Status: 🟢 On Track /...
|
2K |
| 3900 | design-brief | nexu-io/open-design |
This skill creates a design brief through structured conversation. You may skip steps if they are not necessary. Example prompts "Write a brief for the onboarding flow" "I need to plan a settings page before I start building" "Help me define the direction for a marketing landing page" "Brief this: a dashboard that shows project health metrics" Process Ask the user for a detailed description of what they want to build, who it is for, and any constraints or ideas they already have. Explore the exi...
|
2K |