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...
20,000
总 Skills
16.0M
总安装量
2,338
贡献者
# Skill 仓库 描述 安装量
19501 cw-official-docs haowjy/creative-writing-skills
Official Documentation Create canonical, sourced wiki pages for your story's characters, locations, events, and lore. Purpose Build authoritative documentation (wiki-style pages) that serves as "single source of truth" for your fictional world. These are polished, cited, encyclopedic reference pages suitable for readers - NOT working notes or brainstorming. Can be created before or during writing for worldbuilding, lore, and reference material that won't all appear in the story itself. Documenta...
 36
19502 updating-tauri-dependencies dchuk/claude-code-tauri-skills
This skill provides guidance for updating Tauri dependencies across both the JavaScript and Rust ecosystems. Version Synchronization (Critical) The JavaScript `@tauri-apps/api` package and Rust `tauri` crate must maintain matching minor versions. Adding new features requires upgrading both sides to ensure compatibility. For Tauri plugins, maintain exact version parity (e.g., both `2.2.1`) for the npm package and cargo crate. Updating JavaScript Dependencies Using npm Update Tauri CLI an...
 36
19503 arxiv-search willoscar/research-units-pipeline-skills
arXiv Search Search the complete arXiv database of preprints across physics, mathematics, computer science, and quantitative biology using natural language queries powered by Valyu's semantic search API. Why This Skill is Powerful No API Parameter Parsing: Just pass natural language queries directly - no need to construct complex search parameters Semantic Search: Understands the meaning of your query, not just keyword matching Full-Text Access: Returns complete article content, not just abstr...
 36
19504 mobile-debugging jamditis/claude-skills-journalism
Mobile debugging methodology Patterns for accessing JavaScript console and debugging web pages on mobile devices without traditional desktop DevTools. Quick-start: Inject console on any page Eruda bookmarklet (recommended) Add this as a bookmark on your mobile browser, then tap it on any page: javascript : ( function ( ) { var script = document . createElement ( 'script' ) ; script . src = 'https://cdn.jsdelivr.net/npm/eruda' ; document . body . append ( script ) ; script . onload = function ( )...
 36
19505 nestjs-guards-interceptors thebushidocollective/han
NestJS Guards and Interceptors Master NestJS guards and interceptors for implementing authentication, authorization, logging, and request/response transformation. Guards Fundamentals Understanding CanActivate and ExecutionContext. import { Injectable, CanActivate, ExecutionContext } from '@nestjs/common'; import { Observable } from 'rxjs'; @Injectable() export class BasicGuard implements CanActivate { canActivate( context: ExecutionContext, ): boolean | Promise<boolean> | Observable...
 36
19506 skill-evaluator gotalab/skillport
Skill Evaluator (WIP) Evaluates skills against Anthropic's official best practices for agent skill authoring. Produces structured evaluation reports with scores and actionable recommendations. Quick Start Read the skill's SKILL.md and understand its purpose Run automated validation: scripts/validate_skill.py <skill-path> Perform manual evaluation against criteria below Generate evaluation report with scores and recommendations Evaluation Workflow Step 1: Automated Validation Run the validatio...
 36
19507 groq-inference scientiacapital/skills
<quick_start> Basic chat with GROQ: from groq import Groq client = Groq ( api_key = os . environ . get ( "GROQ_API_KEY" ) ) response = client . chat . completions . create ( model = "llama-3.3-70b-versatile" , Best all-around messages = [ { "role" : "user" , "content" : prompt } ] , ) Model selection: Use Case Model General chat llama-3.3-70b-versatile Vision/OCR meta-llama/llama-4-scout-17b-16e-instruct STT whisper-large-v3 (GROQ-hosted, NOT OpenAI) TTS playai-tts </quick_start> <success_crite...
 36
19508 dev-orchestrator rysweet/amplihack
Dev Orchestrator Skill Purpose This is the default orchestrator for all non-trivial development and investigation tasks in amplihack. It replaces the ultrathink-orchestrator skill. When a user asks you to build, implement, fix, investigate, or create anything non-trivial, this skill ensures: Task is classified — Q&A / Operations / Investigation / Development Goal is formulated — clear success criteria identified Workstreams detected — parallel tasks split automatically Recipe runner used — code-...
 36
19509 generic-fullstack-design-system travisjneuman/.claude
No SKILL.md available for this skill. View on GitHub
 36
19510 decision-matrix lyndonkl/claude
Decision Matrix What Is It? A decision matrix is a structured tool for comparing multiple alternatives against weighted criteria to make transparent, defensible choices. It forces explicit trade-off analysis by scoring each option on each criterion, making subjective factors visible and comparable. Quick example: Option Cost (30%) Speed (25%) Quality (45%) Weighted Score Option A 8 (2.4) 6 (1.5) 9 (4.05) 7.95 ← Winner Option B 6 (1.8) 9 (2.25) 7 (3.15) 7.20 Option C 9 (2.7) 4 (1.0) 6 (2.7) 6....
 36
19511 git-advanced-workflows julianobarbosa/claude-code-skills
Git Advanced Workflows Master advanced Git techniques to maintain clean history, collaborate effectively, and recover from any situation with confidence. Do not use this skill when The task is unrelated to git advanced workflows You need a different domain or tool outside this scope Instructions Clarify goals, constraints, and required inputs. Apply relevant best practices and validate outcomes. Provide actionable steps and verification. If detailed examples are required, open resources/implemen...
 36
19512 writing-plans bbeierle12/skill-mcp-claude
Writing Plans Overview Write comprehensive implementation plans assuming the engineer has zero context for our codebase and questionable taste. Document everything they need to know: which files to touch for each task, code, testing, docs they might need to check, how to test it. Give them the whole plan as bite-sized tasks. DRY. YAGNI. TDD. Frequent commits. Assume they are a skilled developer, but know almost nothing about our toolset or problem domain. Assume they don't know good test design ...
 36
19513 n8n-workflow-patterns ovachiever/droid-tings
n8n Workflow Patterns Proven architectural patterns for building n8n workflows. The 5 Core Patterns Based on analysis of real workflow usage: Webhook Processing (Most Common) Receive HTTP requests → Process → Output Pattern: Webhook → Validate → Transform → Respond/Notify HTTP API Integration Fetch from REST APIs → Transform → Store/Use Pattern: Trigger → HTTP Request → Transform → Action → Error Handler Database Operations Read/Write/Sync database data Pattern: Schedule → Query → Trans...
 36
19514 electrobun-window-management rajavijayach/electrobun-skills
Electrobun Window Management Advanced patterns for managing windows and views in Electrobun applications. Multi-Window Applications Basic Window Manager import { BrowserWindow } from "electrobun/bun" ; class WindowManager { private windows = new Map < string , BrowserWindow > ( ) ; createWindow ( id : string , options : any ) { const win = new BrowserWindow ( options ) ; this . windows . set ( id , win ) ; win . on ( "close" , ( ) => { this . windows . delete ( id ) ; } ) ; return win ; } getWin...
 35
19515 summarise-paper codeboyphilo/phi-skills
When to use Reading and summarising an academic paper. Workflow Determine whether the input is a PDF file or an arXiv URL. If the input is a PDF file: Use pdftoppm to convert the PDF into PNG images. Save them under .cache/{paper name}/ as [1,2,3,...].png . Read the converted images. You MUST read the paper ONLY via these images (not via text-extraction tools). Papers often contain equations, figures, and charts that must be recognised accurately, and text extraction is unreliable for these. If ...
 35
19516 nano-banana-use cnemri/google-genai-skills
Nano Banana Use Use this skill to generate, edit, and compose images using Gemini's Nano Banana models ( gemini-2.5-flash-image and gemini-3-pro-image-preview ). This skill uses portable Python scripts managed by uv . Prerequisites Ensure you have one of the following authentication methods configured in your environment: API Key : GOOGLE_API_KEY or GEMINI_API_KEY Vertex AI : GOOGLE_CLOUD_PROJECT GOOGLE_CLOUD_LOCATION GOOGLE_GENAI_USE_VERTEXAI=1 Usage Generate an Image Step 1: Confirm Parameters...
 35
19517 security-review yeachan-heo/oh-my-codex
Security Review Skill This skill ensures all code follows security best practices and identifies potential vulnerabilities. When to Activate Implementing authentication or authorization Handling user input or file uploads Creating new API endpoints Working with secrets or credentials Implementing payment features Storing or transmitting sensitive data Integrating third-party APIs Security Checklist 1. Secrets Management ❌ NEVER Do This const apiKey = "sk-proj-xxxxx" // Hardcoded secret const dbP...
 35
19518 multi-source-data-merger letta-ai/skills
Multi Source Data Merger Overview This skill guides the process of merging data from multiple sources with different formats into a unified dataset. It covers reading heterogeneous file formats, applying field name mappings, resolving conflicts using priority ordering, and generating comprehensive output files including conflict reports. Workflow Step 1: Analyze Requirements and Source Files Before writing any code, thoroughly understand the task: Identify all source files and their formats (JSO...
 35
19519 bird liewcf/agent-skills
Bird - X/Twitter CLI Guide for using the bird CLI tool to interact with X/Twitter content. Quick Start Install bird globally: npm install -g @steipete/bird or pnpm add -g @steipete/bird or bun add -g @steipete/bird one-shot (no install) bunx @steipete/bird whoami or brew install steipete/tap/bird Verify authentication: bird whoami Show logged-in account bird check Check available credentials Common Tasks Read Tweets and Threads Read a single tweet bird read < tweet-url-or-id > bird < twee...
 35
19520 xai-x-search adaptationio/skrillz
Real-time Twitter/X search using Grok's native X integration - a capability unique to xAI. Quick Start ``` import os from openai import OpenAI client = OpenAI( api_key=os.getenv("XAI_API_KEY"), base_url="https://api.x.ai/v1" ) Simple X search response = client.chat.completions.create( model="grok-4-1-fast", messages=[{ "role": "user", "content": "Search X for what people are saying about Tesla stock today" }] ) print(response.choices[0].message.content) ...
 35
19521 data-table-filters openstatushq/data-table-filters
Data Table Filters A shadcn registry for building filterable, sortable data tables with infinite scroll and virtualization. Start with the core block, then extend with optional blocks for command palette, cell renderers, sheet panels, store adapters, schema generation, Drizzle ORM helpers, and React Query integration. Registry Blocks Install any block via npx shadcn@latest add <url> . The CLI handles dependencies, path rewriting, and CSS variable injection. Block Install URL What it adds data-ta...
 35
19522 competitor-monitor guia-matthieu/clawfu-skills
Competitor Monitor Track competitor websites for changes and get alerts - stay informed about pricing, features, and content updates. When to Use This Skill Pricing intelligence - Track competitor price changes Feature tracking - Monitor new feature announcements Content watch - Track new blog posts or pages Change alerts - Get notified of website updates Competitive analysis - Regular competitor audits What Claude Does vs What You Decide Claude Does You Decide Structures analysis frameworks Str...
 35
19523 skill-architect tech-leads-club/agent-skills
Skill Architect: The Authoritative Meta-Skill The unified authority for creating expert-level Agent Skills. Combines systematic workflow from skill-creator with domain expertise encoding from skill-coach. Philosophy Great skills are progressive disclosure machines that encode real domain expertise (shibboleths), not just surface instructions. They activate precisely, teach efficiently, and make users productive immediately. When to Use This Skill ✅ Use for: Creating new skills from scratch...
 35
19524 moneydevkit openagentsinc/openagents
Money Dev Kit Overview Integrate Lightning payment workflows using Money Dev Kit. Use this skill when tasks involve setting up @moneydevkit/agent-wallet for autonomous agents, wiring @moneydevkit/nextjs or @moneydevkit/replit checkout flows, bootstrapping credentials via @moneydevkit/create , validating MDK environment variables, or applying hybrid architecture constraints (hosted API plus self-custodial node). Environment Requires bash , curl , and Node.js 20+. Requires internet access to npm a...
 35
19525 nansen-fund-tracker nansen-ai/nansen-cli
Fund Watch Answers: "What are crypto funds and VCs holding right now?" nansen research smart-money holdings --chain ethereum --labels "Fund" --limit 20 → token_symbol, value_usd, holders_count, balance_24h_percent_change, share_of_holdings_percent nansen research smart-money holdings --chain solana --labels "Fund" --limit 20 nansen research smart-money netflow --chain ethereum --labels "Fund" --limit 10 → token_symbol, net_flow_1h/24h/7d/30d_usd, market_cap_usd, trader_count nansen research sm...
 35
19526 test-reporting-triage-skill patricio0312rev/skills
Test Reporting & Triage Skill Automatically triage test failures and suggest next actions. Failure Categorization // types/test-failure.ts export type FailureCategory = | "timeout" | "assertion" | "network" | "database" | "authentication" | "permission" | "configuration" | "flaky" | "infrastructure" | "unknown"; export interface TestFailure { testName: string; category: FailureCategory; errorMessage: string; stackTrace: string; suggestedOwner: string; suggested...
 35
19527 m365-agents-py sickn33/antigravity-awesome-skills
Microsoft 365 Agents SDK (Python) Build enterprise agents for Microsoft 365, Teams, and Copilot Studio using the Microsoft Agents SDK with aiohttp hosting, AgentApplication routing, streaming responses, and MSAL-based authentication. Before implementation Use the microsoft-docs MCP to verify the latest API signatures for AgentApplication, start_agent_process, and authentication options. Confirm package versions on PyPI for the microsoft-agents-* packages you plan to use. Important Notice - Impor...
 35
19528 pdf teachingai/full-stack-skills
PDF Processing Guide Overview This guide covers essential PDF processing operations using Python libraries and command-line tools. For advanced features, JavaScript libraries, and detailed examples, see REFERENCE.md. If you need to fill out a PDF form, read FORMS.md and follow its instructions. Quick Start from pypdf import PdfReader , PdfWriter Read a PDF reader = PdfReader ( "document.pdf" ) print ( f"Pages: { len ( reader . pages ) } " ) Extract text text = "" for page in reader . pages : t...
 35
19529 finance anton-roos/finance
No SKILL.md available for this skill. View on GitHub
 35
19530 stripe-integration yusuketsunoda/ppt-trans
Stripe Integration Master Stripe payment processing integration for robust, PCI-compliant payment flows including checkout, subscriptions, webhooks, and refunds. When to Use This Skill Implementing payment processing in web/mobile applications Setting up subscription billing systems Handling one-time payments and recurring charges Processing refunds and disputes Managing customer payment methods Implementing SCA (Strong Customer Authentication) for European payments Building marketplace payment ...
 35
19531 mteb-retrieve letta-ai/skills
This skill provides guidance for text embedding retrieval tasks that involve encoding documents and queries using embedding models, computing similarity scores, and retrieving or ranking documents based on semantic similarity. Workflow Step 1: Inspect and Parse Data Before writing any code, carefully inspect the raw data format: - Read the data file and examine actual line contents - Identify formatting artifacts such as: Line number prefixes (e.g., `1→`, `2→`, `1.`, `1:`) - Whitespace ...
 35
19532 conflict-resolution troykelly/claude-skills
Conflict Resolution Overview Handle merge conflicts systematically to maintain code integrity. Core principle: Conflicts require careful resolution, not just picking one side. Announce at start: "I'm using conflict-resolution to handle these merge conflicts." When Conflicts Occur Conflicts happen when: Situation Example Rebasing on updated main git rebase origin/main Merging main into branch git merge origin/main Cherry-picking commits git cherry-pick [sha] Pulling with local changes git p...
 35
19533 update-packages blogic-cz/agent-tools
Update Packages Step 0: Update Skills + Create Branch (MANDATORY) Before touching any packages, update skills and create a dedicated branch. Update all skills from skills-lock.json (reads sources + skill names from lock) bun run .agents/skills/update-packages/references/skills-update-local.ts Dry run to see what would be executed bun run .agents/skills/update-packages/references/skills-update-local.ts --dry-run Create a fresh branch git checkout -b chore/update-packages- $( date +%y%m%d-%H%M ...
 35
19534 beads-task-tracker tdimino/claude-code-minoan
Beads Task Tracker Overview Beads is a git-versioned, dependency-aware issue tracker designed specifically for AI coding agents. It solves the "amnesia problem" where agents lose context between sessions by providing a persistent, queryable task database that agents can use to orient themselves, find ready work, and track dependencies across long-horizon projects. Use Beads when: Working on projects with multiple interconnected tasks Tasks span multiple agent sessions (>10 minutes) Need to track...
 35
19535 path-tracing letta-ai/skills
Path Tracing and Ray Tracing Implementation This skill provides guidance for implementing path tracers and ray tracers, particularly for image reconstruction tasks where a target image must be matched within a similarity threshold. When to Use This Skill Implementing ray tracers or path tracers in C/C++ Reconstructing images by reverse-engineering scene parameters Building rendering systems with geometric primitives (spheres, planes) Tasks requiring image similarity matching (L2 norm, cosine sim...
 35
19536 kubernetes-operations nodnarbnitram/claude-code-extensions
Kubernetes Operations Expert knowledge for Kubernetes cluster management, deployment, and troubleshooting with mastery of kubectl and cloud-native patterns. Core Expertise Kubernetes Operations Workload Management : Deployments, StatefulSets, DaemonSets, Jobs, and CronJobs Networking : Services, Ingress, NetworkPolicies, and DNS configuration Configuration & Storage : ConfigMaps, Secrets, PersistentVolumes, and PersistentVolumeClaims Troubleshooting : Debugging pods, analyzing logs, and inspecti...
 35
19537 brand-positioning-theory mike-coulbourn/claude-vibes
Brand Positioning Theory Framework Quick reference for positioning a brand using methodologies from Al Ries, Jack Trout, and Marty Neumeier. "Marketing is not a battle of products, it's a battle of perceptions." — Al Ries & Jack Trout "When everybody zigs, zag." — Marty Neumeier Ries & Trout's 5 Core Principles Positioning happens in the mind: You don't position products; you position perceptions. The only reality that counts is what's already in the prospect's mind. The mind is limited: I...
 35
19538 attack-surface-analyzer jeremylongshore/claude-code-plugins-plus-skills
Attack Surface Analyzer Purpose This skill provides automated assistance for attack surface analyzer tasks within the Security Advanced domain. When to Use This skill activates automatically when you: Mention "attack surface analyzer" in your request Ask about attack surface analyzer patterns or best practices Need help with advanced security skills covering penetration testing, compliance frameworks, threat modeling, and enterprise security. Capabilities Provides step-by-step guidance for attac...
 35
19539 letta conversations api letta-ai/skills
Letta Conversations API The Conversations API allows multiple isolated message threads on a single agent. Each conversation maintains its own message history while sharing the agent's memory blocks and tools. When to Use This Skill Building multi-user chat applications (each user gets their own conversation) Implementing session management with separate contexts A/B testing agent responses across isolated conversations Any scenario where you need multiple independent chat threads with one agent ...
 35
19540 xiaohongshu-creation-workflow cyhzzz/finance_aigc_skills
小红书图文笔记创作工作流 任务目标 本Skill提供从需求到成品的完整小红书图文笔记创作工作流，专为 财经证券领域官方/员工账号 设计。 核心目标 ：智能模式判断、两阶段创作（内容创作+风格适配）、爆款评估、专业输出、视觉化呈现、用户全程控制。 核心工作流 用户输入 → Phase 0(模式判断) → Phase 1(初稿创作) → Phase 1.5(审校优化) → Phase 2(IP风格迁移+平台适配) → Phase 2.5(爆款评分≥80分自动继续) → Phase 3(HTML预览) → 最终输出 关键变化 ： Phase 1 ：纯粹的选题探讨、优质初稿创作（不考虑IP风格和平台格式） Phase 1.5 ：审校优化（非可选，正式的质量检查步骤） Phase 2 ：IP风格迁移 + 平台格式适配（自动选择账号风格） Phase 2.5 ：评分≥80分自动进入Phase 3 Phase 3 ：默认生成HTML预览，可选手动调用baoyu生成PNG图集 ⚡ 自动执行原则 本工作流采用 智能自动执行 策略，大幅减少人工确认步骤： 自动执行的步骤 ： ✅ Phase 1 所有步骤（...
 35
19541 pr-resolver zenobi-us/dotfiles
Automate the process of addressing pull request review feedback by processing ALL comments, making code fixes, resolving EVERY conversation thread, and fixing ALL failing CI checks. This skill does NOT skip any comments. Every unresolved thread must be addressed and resolved. Prerequisites ``` Verify gh CLI is installed and authenticated gh auth status If not authenticated, run: gh auth login ``` Token requires `repo` scope for full repository access. Workflow Overview - Fetch PR con...
 35
19542 epic-react-patterns epicweb-dev/epic-stack
Epic Stack: React Patterns and Guidelines When to use this skill Use this skill when you need to: Write efficient React components in Epic Stack applications Optimize performance and bundle size Follow React Router patterns and conventions Avoid common React anti-patterns Implement proper code splitting Optimize re-renders and data fetching Use React hooks correctly Philosophy Following Epic Web principles: Make it work, make it right, make it fast - In that order. First make it functional, ...
 35
19543 ansible-validator akin-ozer/cc-devops-skills
Ansible Validator Overview Comprehensive toolkit for validating, linting, and testing Ansible playbooks, roles, and collections. This skill provides automated workflows for ensuring Ansible code quality, syntax validation, dry-run testing with check mode and molecule, and intelligent documentation lookup for custom modules and collections with version awareness. Default behavior: When validating any Ansible role with a molecule/ directory, attempt Molecule automatically using bash scripts/test_r...
 35
19544 code-review smallnest/langgraphgo
Code Review When to use this skill Reviewing pull requests Checking code quality Providing feedback on implementations Identifying potential bugs Suggesting improvements Security audits Performance analysis Instructions Step 1: Understand the context Read the PR description : What is the goal of this change? Which issues does it address? Are there any special considerations? Check the scope : How many files changed? What type of changes? (feature, bugfix, refactor) Are tests included? Step 2: Hi...
 35
19545 nginx-ingress-manager jeremylongshore/claude-code-plugins-plus-skills
Nginx Ingress Manager Purpose This skill provides automated assistance for nginx ingress manager tasks within the DevOps Advanced domain. When to Use This skill activates automatically when you: Mention "nginx ingress manager" in your request Ask about nginx ingress manager patterns or best practices Need help with advanced devops skills covering kubernetes, terraform, advanced ci/cd, monitoring, and infrastructure as code. Capabilities Provides step-by-step guidance for nginx ingress manager Fo...
 35
19546 pwa-development travisjneuman/.claude
PWA Development Skill Load with: base.md Purpose: Build Progressive Web Apps that work offline, install like native apps, and deliver fast, reliable experiences across all devices. Core PWA Requirements ┌─────────────────────────────────────────────────────────────────┐ │ THE THREE PILLARS OF PWA │ │ ───────────────────────────────────────────────────────────── │ │ │ │ 1. HTTPS ...
 35
19547 tuzi-video-gen tuziapi/tuzi-skills
Video Generation (AI SDK) Tuzi API video generation backend. Default model: veo3.1. Script Directory Agent Execution : SKILL_DIR = this SKILL.md file's directory Script path = ${SKILL_DIR}/scripts/main.ts Step 0: Load Preferences ⛔ BLOCKING CRITICAL : This step MUST complete BEFORE any video generation. Do NOT skip or defer. 0.1 Check API Key echo " ${TUZI_API_KEY :- not_set} " grep -s TUZI_API_KEY .tuzi-skills/.env " $HOME /.tuzi-skills/.env" Result Action Key found Continue to Step 0.2 Key NOT...
 35
19548 install-windows-3.11 letta-ai/skills
Install Windows 3.11 in QEMU Overview This skill provides procedural knowledge for installing and running Windows 3.11 in a QEMU virtual machine with VNC and web-based access. Windows 3.11 is a legacy 16-bit operating system that requires specific QEMU configuration for proper operation. Pre-Installation Checklist Before starting, verify the following: Check for expected file paths and naming conventions - Tests or acceptance criteria may expect specific paths (e.g., /tmp/qemu-monitor.sock vs /t...
 35
19549 markdownlint-integration thebushidocollective/han
Markdownlint Integration Master integrating markdownlint into development workflows including CLI usage, programmatic API (sync/async/promise), CI/CD pipelines, pre-commit hooks, and editor integration. Overview Markdownlint can be integrated into various parts of your development workflow to ensure consistent markdown quality. This includes command-line tools, programmatic usage in Node.js, continuous integration pipelines, Git hooks, and editor plugins. Command-Line Interface markdownlint-cli ...
 35
19550 track17 tristanmanchester/agent-skills
track17 (17TRACK parcel tracking) This skill lets Clawdbot keep a local list of your parcels, track their state via the 17TRACK Tracking API v2.2 , and summarise changes. It stores everything in a small SQLite DB under your workspace (by default: <workspace>/packages/track17/track17.sqlite3 ). <workspace> is auto-detected as the parent directory of the nearest skills/ directory that contains this skill. For example, if you install it at /clawd/skills/track17/ , data will be stored at /clawd/pack...
 35