“coding”的搜索结果

Keep coding tasks small by checking whether new code is needed, reusing existing helpers, and preferring standard libraries or built-in platform features. Apply the same approach to feature development, bug fixes, refactoring, and reviews.

中文简介正在准备中。当前显示英语简介。

• Adding a feature with minimal code
• Reviewing unnecessary dependencies
• Simplifying an overcomplicated implementation

Delegate coding, analysis, planning, and reviews from Codex to Claude Code through its command-line interface. Capture responses, resume sessions, or run independent tasks in parallel, then verify changed files and test results independently.

中文简介正在准备中。当前显示英语简介。

• Delegating implementation or refactoring from Codex
• Getting another model's review of code changes
• Continuing delegated work across multiple sessions

Delegate coding, analysis, refactoring, or reviews from Claude Code to Codex CLI. The skill explains unattended execution, permission settings, output capture, parallel tasks, and independent checks of changed files and test results.

中文简介正在准备中。当前显示英语简介。

• Delegate implementation while retaining planning responsibility
• Get a second opinion on code changes
• Split independent tasks across separate git worktrees

Turn an explicit request for a coding plan into an ordered checklist. Review project documentation and relevant files, define scope, and outline implementation, validation, and risks without changing any files.

中文简介正在准备中。当前显示英语简介。

• Planning a feature before implementation
• Defining the scope of a refactor
• Organizing testing and validation steps

Reviews recent Codex conversations to identify coding habits, strengths, and recurring challenges. Produces a prioritized growth report with practical next steps and relevant HackerNews reading, then delivers it to your Slack direct messages.

中文简介正在准备中。当前显示英语简介。

• Reviewing recent coding habits
• Identifying recurring technical challenges
• Choosing learning topics from actual work

Share the current coding session transcript with the Convex team, with explicit consent, for an AI review that identifies unclear setup instructions, tooling failures, and successful patterns to help improve the quickstart system.

中文简介正在准备中。当前显示英语简介。

• Reviewing where an agent got stuck during setup
• Reporting tooling failures in a coding session
• Sharing successful setup patterns with the Convex team

Set up OpenRig to run a team of coding agents, including Claude Code and Codex. Open the team interface, pass project goals to its operator, reconnect to agents, and follow assigned work through to its results.

中文简介正在准备中。当前显示英语简介。

• Installing OpenRig and starting a coding team
• Returning to an existing team's interface
• Passing project goals to the team operator

Audits GitHub Actions workflows that run AI coding agents. Traces how attacker-controlled content reaches prompts, checks permissions and sandbox settings, and reports evidence, severity, and fixes for prompt injection and related configuration risks.

中文简介正在准备中。当前显示英语简介。

• Reviewing workflows that run AI coding agents
• Tracing issue and PR content into agent prompts
• Checking sandbox settings and user allowlists

Supports authorized security exercises that test data transfer outside a network. Organizes channel choices, compression, encryption, splitting, and receipt verification, alongside the monitoring signals defenders can use to identify different transfer methods.

中文简介正在准备中。当前显示英语简介。

• Comparing data transfer channels for an authorized exercise
• Planning compression, encryption, and file splitting
• Verifying received files against SHA-256 records

Create hand-drawn SVG illustration cards featuring expressive creatures or living objects that represent coding and design ideas. A supplied brush library supports uneven ink outlines, loose watercolor fills, large eyes, and consistent details across a set.

中文简介正在准备中。当前显示英语简介。

• Creating a loading illustration with a snail mascot
• Adding a character illustration to an error page
• Illustrating a coding concept for a blog header

Create flat SVG illustrations of long-legged people in design and coding scenes. Large black shapes, bright colors, and consistent poses give onboarding screens, error pages, and marketing cards a shared visual style.

中文简介正在准备中。当前显示英语简介。

• Illustrations for onboarding screens
• Character art for error pages
• Cards showing design and coding work

Apply a short quality checklist to everyday code changes. Read existing code first, keep edits focused, check types and common security risks, verify execution, remove debugging leftovers, and summarize what changed and its impact.

中文简介正在准备中。当前显示英语简介。

• Checking quality during routine feature work
• Reviewing type safety in Python and TypeScript
• Checking input handling and common security risks

Access TeamAI workflows for sharing skills, rules, documents, and environment settings across AI coding tools. This entry skill loads version-matched guidance for team setup, synchronization, codebase knowledge, and sharing lessons from a session.

中文简介正在准备中。当前显示英语简介。

• Start sharing AI settings across a team
• Sync team skills across AI coding tools
• Build or search knowledge about codebase architecture

Use Evo 2 to score DNA sequences, turn genomic regions into numerical representations for classification, and generate sequences from a supplied prefix. Compare reference and variant sequences or assess coding and regulatory regions across species.

中文简介正在准备中。当前显示英语简介。

• Comparing scores before and after a DNA variant
• Preparing numerical features for genomic region classification
• Generating DNA from a supplied prefix

Review a coding session to identify improvements to the agent’s working environment. Get prioritized suggestions for finding files, strengthening automated checks, clarifying guidance, reducing costly tool calls, and accessing missing information.

中文简介正在准备中。当前显示英语简介。

• Reviewing why a coding agent struggled
• Finding gaps in automated checks
• Simplifying agent instructions

Analyze interviews, focus groups, and open-ended survey responses using Braun and Clarke's six-phase framework. Label meaningful passages, develop and review themes, and produce an academic Word report with an annotated map showing theme relationships.

中文简介正在准备中。当前显示英语简介。

• Identifying themes across interview transcripts
• Analyzing open-ended survey responses
• Choosing an approach before coding qualitative data

Organize work so an expensive AI model handles planning, judgment, and final review while cheaper helper agents perform bounded research, coding, and testing. Define ownership and verification requirements, then inspect the evidence and integrate their results centrally.

中文简介正在准备中。当前显示英语简介。

• Delegate broad codebase research to cheaper agents
• Split coding tasks with clear file ownership
• Distribute test runs and log analysis

An experimental workflow for finding and resuming coding runs interrupted by a host restart or automation failure. It checks original instructions, worktree ownership, and external state, then reports which runs were resumed, skipped, or held.

中文简介正在准备中。当前显示英语简介。

• Resuming coding work after an agent host restart
• Finding unfinished work after automation stops
• Checking external state before retrying an uncertain action

Isolate parallel coding tasks with Git worktrees, separate working folders with their own branches. The skill guides environment setup, dependency installation, change review, merging, and cleanup so each task has a dedicated workspace.

中文简介正在准备中。当前显示英语简介。

• Prepare separate working folders for parallel coding tasks
• Set up dependencies and environment files in a new worktree
• Review and merge completed changes

Create and manage Boat cloud sandboxes, remote machines for development work, through API, CLI, or SSH. Configure repositories and secrets, prepare reusable templates, manage machine state, and verify coding agents inside the selected environment.

中文简介正在准备中。当前显示英语简介。

• Create a cloud workspace for a coding agent
• Configure repositories and secrets
• Reuse prepared environments through templates

Add EAGLE-3 or draft-model speculative decoding to a Jetson vLLM server when TPOT is the bottleneck.

中文简介正在准备中。当前显示原文说明。

Delegate coding tasks to Codex, Claude Code, or Pi agents via background process. Use when: (1) building/creating new features or apps, (2) reviewing PRs (spawn in temp dir), (3) refactoring large codebases, (4) iterative coding that needs file exploration. NOT for: simple one-liner fixes (just edit), reading code (use read tool), thread-bound ACP harness requests in chat (for example spawn/run Codex or Claude Code in a Discord thread; use sessions_spawn with runtime:"acp"), or any work in ~/clawd workspace (never spawn agents here). Claude Code: use --print --permission-mode bypassPermissions (no PTY). Codex/Pi/OpenCode: pty:true required.

中文简介正在准备中。当前显示原文说明。

Delegate a coding task to Aider (`aider`) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Aider - phrasings like "have Aider do X", "delegate this to aider", "run it through Aider", or "use Aider to implement/fix/refactor" - or wants to run a queue of coding tasks through Aider while staying the reviewer. This includes asking Aider to drive a local or self-hosted OpenAI-compatible endpoint ("have Aider use my local model", "run Aider against llama.cpp / Ollama / vLLM / LM Studio"), which Aider reaches via `--api-base`. DO NOT USE for local-model or coding requests that do not name Aider, for tasks small enough to do inline, or when the user wants the code written directly without delegating.

中文简介正在准备中。当前显示原文说明。

Delegate a coding task to the Pi coding agent CLI (`pi`) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to delegate implementation work to Pi - phrasings like "have Pi implement X", "delegate this to pi", "run it through Pi", or "use pi to implement/fix/refactor" - or wants to run a queue of coding tasks through Pi while staying the reviewer. DO NOT USE for tasks small enough to do inline, or when the user wants the code written directly without delegating.

中文简介正在准备中。当前显示原文说明。