“scratch”的搜索结果

为功能、模块或整个项目从零补写缺失文档。按照 Diataxis 的用途分类，组织学习教程、操作指南、参考信息和原理说明，为不同阅读需求准备相应内容。

• 为尚无文档的功能补写说明
• 编写教程和操作指南
• 准备模块参考信息与原理说明

Turn a repeatable workflow into a skill, or improve an existing one through test prompts and feedback. Compare results with and without the skill, review performance measurements, and refine its description so it triggers appropriately.

中文简介正在准备中。当前显示英语简介。

• Turn a recurring workflow into a reusable skill
• Improve an existing skill using feedback
• Compare outputs with and without a skill

Set up Ruflo in a new repository using an interactive wizard or the standard preset. Create project instructions and configuration files, including MCP server registration so the agent can access the ruflo tools.

中文简介正在准备中。当前显示英语简介。

• Introduce Ruflo into a new repository
• Set up a project with an interactive wizard
• Initialize configuration using the standard preset

Rebuild the index of ADRs, records of architectural decisions, after files or relationship lines are deleted. It clears stored records and relationships, indexes the files still present, and checks that the final record count matches.

中文简介正在准备中。当前显示英语简介。

• Rebuild the index after deleting an ADR file
• Remove stale relationships after editing an ADR
• Reconcile the ADR index on a schedule

Create a substantial technical manual for one exact system version. Organize authoritative sources, record offline inputs and outputs, explain behavior with figures, and audit the text and supporting evidence for consistency.

中文简介正在准备中。当前显示英语简介。

• Documenting a protocol or file format at a fixed version
• Building reproducible offline request and response records
• Adding a section with figures and traceable sources

Build an interactive page that explains a process as a machine viewed from an angle. A tested simulation keeps movement, numbers, and explanations consistent, while controls let readers step through operations and explore failures.

中文简介正在准备中。当前显示英语简介。

• Explain a cache or queue through an interactive machine
• Show what fails when one process step breaks
• Create a standalone visual explanation page

Create animated lesson diagrams, sliders that update figures, and interactive panels that explain how systems work. It also builds moving dot patterns for page headers, with rules for readability, themes, and reduced motion.

中文简介正在准备中。当前显示英语简介。

• Animate a process in a lesson
• Explore a formula with a slider
• Show a system's behavior through one control

Review database migration files before merging changes. It gathers evidence about what the changes do, rollback limits, database locks, and risks from large data volumes, then reports blockers when evidence needed for a decision is missing.

中文简介正在准备中。当前显示英语简介。

• Review database changes before merging
• Check rollback limits
• Assess database locks and data-volume risks

Review deployment evidence and recovery conditions when assessing a release. The skill directs the agent to consult the accompanying restore reference and include a timestamp in its decision, providing a narrowly defined release review procedure.

中文简介正在准备中。当前显示英语简介。

• Reviewing deployment evidence
• Checking recovery conditions for a release
• Preparing a release decision with a timestamp

Run a local check of test evidence and retain source paths in the result. The workflow stops when required evidence is missing, keeping the findings tied to their sources.

中文简介正在准备中。当前显示英语简介。

• Checking local test evidence
• Keeping source paths in check results
• Stopping a check when evidence is missing

Evaluate an Agent Skill bundle before release by checking structure, activation conditions, output quality, scripts, safety, file integrity, and host compatibility. Receive a detailed JSON report that distinguishes local evidence checks from production readiness backed by external attestation.

中文简介正在准备中。当前显示英语简介。

• Reviewing a skill bundle before distribution
• Evaluating activation accuracy and output improvements
• Checking scripts, safety, and distributed files

Build a catalog from multiple skill directories using an explicit priority order. Review duplicate names, selection decisions, and omitted entries before loading the instruction text of the chosen skill.

中文简介正在准备中。当前显示英语简介。

• Cataloging project and user skill directories together
• Checking duplicate skill names before activation
• Reviewing catalog limits and omitted entries

Review proposed file operations, commands, network access, secret handling, or destructive actions against explicit sandbox rules that define permitted activity. Receive a JSON verdict and the exact rule behind it without performing the proposed action.

中文简介正在准备中。当前显示英语简介。

• Reviewing requested file operations before execution
• Checking commands or network access against sandbox rules
• Reviewing actions involving secrets or destructive changes

Publish an approved Orchard release while retaining source paths in the result. The skill requires work to stop when supporting evidence is missing, making evidence availability a condition for proceeding.

中文简介正在准备中。当前显示英语简介。

• Publish an approved Orchard release
• Retain source paths in publication results
• Stop release work when supporting evidence is missing

Review a release proposal by reading its deployment diff and quoting changed replica settings, which describe running instance counts. The review surfaces the specific configuration changes for inspection.

中文简介正在准备中。当前显示英语简介。

• Review a release proposal's deployment diff
• Inspect changes to replica settings
• Quote changed settings in a release review

Review a reusable Agent Skill package before implementation. Validate its identity fields, separate instructions from external capabilities and execution timing, and receive a validation report with a minimal set of building blocks and reasons for each choice.

中文简介正在准备中。当前显示英语简介。

• Reviewing a workflow before turning it into a reusable skill
• Checking SKILL.md identity fields
• Choosing instructions, scripts, or delegation

Design and test rules for activating skills through human requests, AI selection, applications, or other skills. Check eligibility before matching descriptions, then return a JSON decision showing the selected channel, score, and policy reason.

中文简介正在准备中。当前显示英语简介。

• Separate explicit requests from automatic skill selection
• Test allowed callers and skill composition limits
• Check cases where no skill should activate

Review Orchard deployment manifests, the files describing deployment settings, and keep source paths in the result. The workflow stops when evidence is missing, tying review findings to the available source material.

中文简介正在准备中。当前显示英语简介。

• Reviewing Orchard deployment manifests
• Keeping source paths in review results
• Stopping a review when evidence is missing

Set up a Python environment inside the project and install its packages. Follow existing environment tools when present, avoid changing the system Python, and provide commands that work from a fresh shell.

中文简介正在准备中。当前显示英语简介。

• Set up an environment for a new Python project
• Install packages into an existing project environment
• Resolve an externally-managed-environment installation error

Create, edit, and clean spreadsheet files, including Excel workbooks and CSV data. Add formulas, formatting, and charts, preserve existing workbook conventions, and recalculate formulas with error checks before delivering the spreadsheet.

中文简介正在准备中。当前显示英语简介。

• Clean messy CSV data into a spreadsheet
• Edit an Excel workbook while preserving its formatting
• Create a financial model with recalculating formulas

Create and improve agent skills by defining tasks, writing instructions, and testing realistic requests. Compare outputs, success rates, time, and token use, then refine the skill and its description so it triggers appropriately.

中文简介正在准备中。当前显示英语简介。

• Turn a recurring workflow into a reusable skill
• Improve an existing SKILL.md using test feedback
• Compare results with and without a skill

Create product comparison and alternative pages that help buyers evaluate options. Organize pricing, features, use cases, and migration details, and audit existing competitive claims for outdated information, missing evidence, or wording that overstates the facts.

中文简介正在准备中。当前显示英语简介。

• Creating a page comparing your product with a competitor
• Planning a list of alternative products
• Checking existing comparison claims for accuracy

Improve existing marketing copy while preserving its message and voice. The skill reviews clarity, evidence, specific details, and prompts to act, refreshes outdated content, and replaces formulaic AI phrasing with language grounded in available facts.

中文简介正在准备中。当前显示英语简介。

• Review landing page and product copy
• Make AI-written drafts sound more natural
• Refresh outdated page content

Plan and improve customer or fan communities with platform recommendations, launch plans, welcome journeys, recurring activities, and ambassador programs. The skill also reviews participation metrics to identify where members disengage and suggest practical priorities for community managers.

中文简介正在准备中。当前显示英语简介。

• Plan a community launch from scratch
• Improve welcome journeys for new members
• Design recurring events and discussion threads