“open source”的搜索结果

Create and maintain knowledge collections in Open Knowledge Format v0.2, a Markdown format agents can read. Covers document types, source citations, verification records, indexes, and change logs, plus guidance for interpreting conformance warnings.

中文简介正在准备中。当前显示英语简介。

• Structuring knowledge as an OKF collection
• Recording sources and verification history
• Reviewing OKF plugin warnings

Turn OpenAPI specifications, GraphQL endpoints, MCP servers, or custom JavaScript functions into bash commands and a JavaScript API. The skill guides implementation so agents can call these tools from the isolated execution environment provided by just-bash.

中文简介正在准备中。当前显示英语简介。

• Generating bash commands from an OpenAPI specification
• Connecting GraphQL to a just-bash agent
• Calling MCP tools from bash or JavaScript

检查TypeScript和JavaScript的公开API，补充参数、返回值和异常说明，完善JSDoc注释，并为HTTP端点生成OpenAPI 3.0定义。

• 统一公开函数和类的说明
• 补充遗漏的JSDoc注释
• 创建HTTP API规范定义

Build and improve Python command interfaces for GUI applications with OpenClaw. The skill guides source analysis, command design, testing, and packaging, including interactive sessions and structured JSON output for agents.

中文简介正在准备中。当前显示英语简介。

• Build a command interface for a GUI application
• Add missing commands to an existing interface
• Test workflows against the actual application

Generate API documentation from source code, including OpenAPI/Swagger specifications. Describe endpoints, the addresses used to access API operations, with parameters, responses, errors, authentication guidance, and examples in cURL, JavaScript, and Python.

中文简介正在准备中。当前显示英语简介。

• Creating API documentation from source code
• Preparing OpenAPI/Swagger specifications
• Documenting parameters, responses, and errors

Create or update API documentation from source code. Produce OpenAPI or Swagger specifications, endpoint descriptions, parameter tables, response examples, authentication guides, error references, and usage examples that explain how to call the API.

中文简介正在准备中。当前显示英语简介。

• Create API documentation from source code
• Generate an OpenAPI or Swagger specification
• Document parameters, responses, and errors

Synthesize OpenViking knowledge bases or document collections into topic-based Markdown pages that explain trends, changes, comparisons, and implications. Keep conclusions traceable to source evidence, distinguish facts from inferences, and preserve disagreements and uncertainty.

中文简介正在准备中。当前显示英语简介。

• Comparing changes across financial reports
• Finding shared trends across knowledge bases
• Organizing sourced conclusions by topic

Create or update skills using OpenSEO's repository conventions. Keep one canonical source, distinguish internal and public workflows, maintain Claude Code links, and register public skills in documentation, the in-app agent, and plugin bundles.

中文简介正在准备中。当前显示英语简介。

• Add a new skill to the OpenSEO repository
• Turn a development workflow into an internal skill
• Repair drift between skill directories

Add, extend, or review OpenAI Ads conversion tracking for purchases, signups, and other confirmed outcomes. The skill covers browser Pixel events, server-side Conversions API events, duplicate-event prevention, secret handling, and local verification with a setup report.

中文简介正在准备中。当前显示英语简介。

• Add tracking for completed purchases and signups
• Send conversion events from a server
• Prevent duplicate counting across Pixel and CAPI

Search current web information and recent scientific literature with Perplexity through OpenRouter and LiteLLM. Get answers with source citations, choose models for different research needs, and save results as JSON for further use.

中文简介正在准备中。当前显示英语简介。

• Find recent scientific papers
• Verify claims with cited sources
• Compare current technologies and approaches

Create or update product-update / release-notes content for a given OpenMetadata/Collate patch version across getcollate, openmetadata-site, and docs-om. Sources getcollate's changelog from openmetadata-collate + OpenMetadata + ai-platform; openmetadata-site's from OpenMetadata only; docs-om reuses openmetadata-site's already-written content, reformatted into its Mintlify snippet structure. Filters to customer-facing changes only, runs each target's own doc-review checklist, verifies every link live, and requires explicit approval before any commit.

中文简介正在准备中。当前显示原文说明。

Investigate incorrect, missing, or unexpectedly changed OpenViking memories by tracing memory files back to archived change records and, when needed, source messages. Return an evidence trail, identify gaps, and suggest next steps without modifying data.

中文简介正在准备中。当前显示英语简介。

• Investigate incorrect memory content
• Check unexpected memory paths or owners
• Trace missing or deleted memories

Generate images from text, edit an existing picture, or combine up to three source images using Gemini 3 Pro Image through OpenRouter. Choose 1K, 2K, or 4K output and save the results as image files.

中文简介正在准备中。当前显示英语简介。

• Generating a landscape image from a written description
• Replacing the sky in an existing photo
• Combining subjects from multiple images into one portrait

Write and manage infrastructure as code with Terraform and OpenTofu. Design reusable modules, review planned changes before applying them, bring existing resources under management, and organize shared state so teams can track infrastructure across environments.

中文简介正在准备中。当前显示英语简介。

• Designing reusable infrastructure modules
• Bringing existing resources under Terraform management
• Separating development, staging, and production state

Create reusable starting configurations that combine an agent’s role, startup context, and source history. The skill guides registry entries, checks whether their sources are current, and manages their progression from initial capture to recommendation or retirement.

中文简介正在准备中。当前显示英语简介。

• Create reusable startup context for an agent role
• Refresh an agent workspace from an existing starter
• Check a starter’s source history and freshness

Process spreadsheets with Python after checking source files, required sheets and columns, and external data access. The workflow includes backup source checks and clear failure reports when the required data cannot be reached.

中文简介正在准备中。当前显示英语简介。

• Check required files and columns before processing Excel
• Verify external data access before updating a spreadsheet
• Check backup data when the primary source is unavailable

Validate spreadsheet sources before running Python scripts to transform data, update multiple sheets, or apply formatting. Check required data first, try backup sources when needed, and report errors clearly if processing cannot proceed.

中文简介正在准备中。当前显示英语简介。

• Checking required columns before processing Excel files
• Transforming data and saving a new workbook
• Updating formatting across multiple sheets

Audit an Excel workbook before editing, then verify the saved file with Python and openpyxl. Each requested requirement receives an explicit status, so completion depends on checks of the actual file.

中文简介正在准备中。当前显示英语简介。

• Verify exact sheet names and row counts
• Check sample size and category coverage
• Confirm required source sheets remain after editing

Set up OSS-Fuzz for an open-source project and test it locally. Prepare configuration and build files, run fuzz tests that probe code with varied inputs, reproduce reported crashes, and inspect which code the tests reach.

中文简介正在准备中。当前显示英语简介。

• Preparing an open-source project for OSS-Fuzz enrollment
• Testing an OSS-Fuzz build locally before submission
• Reproducing crashes from OSS-Fuzz reports

Research a topic through BrowserAct web searches and organize findings into a report with source references. Filters for search engine, date range, content type, and result count help focus supplemental research and gather information from multiple sources.

中文简介正在准备中。当前显示英语简介。

• Finding supplemental sources when direct web access fails
• Researching recent industry or market news
• Comparing facts and statistics across sources

Guides Apache OpenDAL release managers through preparation, release candidates, verification, voting, and publication. It tracks the current stage, checks external systems, and distinguishes core, candidate, and package versions when deciding the next release action.

中文简介正在准备中。当前显示英语简介。

• Preparing a weekly candidate or manual release candidate
• Checking release CI and staged source artifacts
• Preparing a vote and verifying its outcome

Generate OpenAPI 3.0.3 specifications, a standard format for describing APIs, from route definitions in supported web frameworks. Extract paths, HTTP methods, parameters, and available model information into JSON or YAML for Swagger UI or Redoc.

中文简介正在准备中。当前显示英语简介。

• Generating an API specification from source code
• Listing existing API endpoints
• Preparing specifications for Swagger UI or Redoc

Turn existing research notes into an authoritative knowledge article after a team has made its decision. Records the outcome, rationale, trade-offs, and rejected alternatives while preserving source notes and links showing which documents the article replaces.

中文简介正在准备中。当前显示英语简介。

• Documenting a decision after research
• Combining several research notes into one reference
• Updating an authoritative article with replacement links

Prepares Claude Code or OpenAI Codex for in-depth research with hyperresearch, then hands the request to a structured workflow for research reports, literature reviews, and analysis using multiple sources with verified citations.

中文简介正在准备中。当前显示英语简介。

• Preparing a research report with verified citations
• Reviewing literature on a specific topic
• Comparing evidence from multiple sources