Results for “code”

Switch PUA's narration to an encouragement-first style in Codex CLI through the equivalent of Claude Code's /pua:yes command. The skill preserves verification requirements and requires command or output evidence before reporting completion.

• Calling the equivalent of /pua:yes from Codex CLI
• Switching task narration to an encouraging style
• Keeping verification requirements while changing narration

Audit custom subagents, the specialized assistants used by Claude Code and Codex. Check whether definitions load, identify overlapping roles, review model choices and tool access, and receive scores with prioritized fixes and optional confirmed edits.

• Checking agents when joining a project
• Reviewing newly added or imported agents
• Investigating delegation to the wrong agent

Claude Code（.claude）と Codex（.codex / .agents / AGENTS.md）に分裂したエージェント設定を、 実ファイル1つ + symlink と双方向変換で単一化・同期するスキル。 実ファイルをどちら側に置くか（symlink の向き）は共通設定 source で選べる。 プロジェクト単位の導入ウィザード、既に分裂しているリポジトリを危険度の低い順に解決する手順、 片方しか無いリポジトリへもう片方を生成する scaffold、書き換え前のバックアップと復元、常駐の管理を含む。 「エージェント設定を同期して」「.codex と .claude がずれている」「Codex でも同じスキルを使いたい」 「AGENTS.md と CLAUDE.md を一本化したい」「MCP を Codex でも使えるようにして」 「サブエージェントを Codex 側にも作って」「設定の分裂を解消して」「元に戻して」 「agents-sync」「同期デーモン」などと言われたら使う。 Keywords: agents-sync, エージェント設定同期, .claude, .codex, .agents, AGENTS.md, symlink 統合, symlink の向き, 実ファイルを置く側, 双方向同期, scaffold, 分裂解消, MCP 同期, hooks 同期, サブエージェント同期, バックアップ, 復元, fswatch, launchd, 常駐デーモン

The English summary is being prepared. Showing the original description.

Set up Claude Code hooks that block Git commands such as push, hard reset, and forced deletion before execution. Choose project-wide or global settings, customize the blocked commands, and verify that the hook rejects a test command.

• Block Git pushes from Claude Code
• Prevent commands that discard changes or delete branches
• Apply Git restrictions to one project or all projects

Use OpenAI Codex CLI to review code changes, challenge an implementation by looking for ways it could fail, or discuss technical questions. Three modes provide an independent opinion, with follow-up questions supported in ongoing consultations.

• Get an independent review of code changes
• Challenge code to uncover possible failures
• Continue a technical consultation with follow-up questions

Benchmark how CodeGraph affects an agent investigating a real codebase. Choose a version, language, repository, and execution mode, then compare cost, tool calls, file reads, and answer correctness with and without CodeGraph.

• Evaluating a local development build
• Auditing a published CodeGraph version
• Comparing investigation cost and file reads

Display a preset introduction to Oh My OpenCode through an Easter egg command. The message outlines the plugin’s agent coordination, code navigation, structural search, built-in search integrations, and compatibility with Claude Code configuration.

• Reading a brief introduction to Oh My OpenCode
• Trying the hidden command
• Reviewing the plugin features listed in its introduction

Diagnose problems in Muse Code itself using the installed executable, settings, crash reports, and session evidence. The skill narrows down the likely failing component, summarizes evidence with sensitive information removed, and recommends a safe next action.

• Investigate Muse Code startup or authentication failures
• Diagnose a session that cannot be resumed
• Review earlier activity in a selected Muse Code session

Analyze a project's code and configuration to recommend useful Claude Code automations. Get tailored suggestions for event-triggered actions, specialist agents, reusable skills, plugins, and external tool connections, with reasons for each recommendation.

• Set up Claude Code for a new project
• Find useful formatting and testing automations
• Choose external tool connections for a project's stack

Audit GitHub Codespaces startup time and spending, then identify up to three evidence-based improvements to development containers, machine sizes, prebuilds, or idle timeouts, with validation results and expected impact.

• Investigating slow Codespaces startup
• Reviewing Codespaces spending
• Trimming unused development container components

Create step-by-step code walkthroughs tailored to readers such as new contributors, reviewers, or bug fixers. Produce CodeTour .tour files linked to verified files and line numbers, with explanations of behavior, design choices, and pitfalls.

• Create a code walkthrough for new team members
• Guide reviewers through a PR and its risks
• Trace code involved in a bug or incident

Find code components that match Figma design components by comparing names, structure, and settings. Presents candidates for approval, then creates Code Connect mappings, explicit links between design components and their implementations.

• Link a Figma button to its code component
• Find unconnected components within a frame
• Compare similar implementation candidates

Keep Kilo-specific changes small in files shared with upstream OpenCode. The skill guides where to place custom logic and tests, how to mark changes, and how to check annotations while preserving behavior.

• Add Kilo-specific features to shared upstream code
• Move additive logic into Kilo-owned files
• Clean up outdated or overly broad change markers

Write Python for n8n Code nodes to transform, filter, aggregate, and validate workflow data. Get guidance on reading input items, returning the required JSON structure, using standard library modules, and avoiding common errors within n8n's Python execution modes.

• Transforming and filtering data in n8n with Python
• Calculating totals and basic statistics
• Extracting and validating text with regular expressions

Lets Codex CLI users choose and configure a PUA narration style through a dedicated command alias. It consults the style reference, preserves unrelated configuration fields, and requires command output as evidence of completed changes.

• Choosing a PUA narration style
• Setting a style from Codex CLI
• Updating a style while preserving unrelated settings

Use Codex to define strategic direction, organizational structure, and P9 management boundaries through the P10/CTO protocol. This alias provides a Codex entry point corresponding to the Claude Code command `/pua:p10`.

• Defining strategic direction
• Organizing team structure
• Clarifying P9 management boundaries

Use the P7 engineering workflow in Codex CLI through a command alias. It guides planning, implementation, and a three-question self-review, then requires command and output evidence before reporting completion.

• Calling the P7 workflow from Codex CLI
• Planning, implementing, and reviewing a coding task
• Reporting completion with command and output evidence

Automate Codereadr tasks using Rube MCP and Composio. The skill guides tool discovery, connection checks, and execution based on current input requirements, with instructions for keeping related steps within the same session.

• Looking up available Codereadr tools
• Checking the Codereadr connection before a task
• Executing operations using current input requirements

Automate Codeinterpreter operations through Rube MCP, a connection to external tools. The skill searches for available actions, retrieves their current input requirements, checks authentication status, and runs supported operations.

• Finding available Codeinterpreter actions
• Checking the connection before running tasks
• Automating supported Codeinterpreter operations

Set up, update, or check a fiction-writing toolkit in a project folder. It adapts skills, assistants, and configuration to the AI tool in use while preserving manuscripts and user settings, then reports what is ready and what needs attention.

• Setting up an AI-assisted fiction-writing project
• Checking a writing environment for missing components
• Updating writing tools while preserving manuscripts and settings

Configure coding agents, AI SDKs, and HTTP clients to send model requests through AntSeed’s local proxy. Find available providers and models, select a provider, set compatible API endpoints, and verify request usage and payment activity.

• Connect Claude Code or Codex to AntSeed
• Configure a local endpoint for AI SDKs
• Compare providers’ models, protocols, and prices

Audit Claude Code and Codex hooks, actions triggered by agent events. Check commands, trigger conditions, blocking behavior, and timeouts to identify why hooks fail to run, fail to block actions, or delay the agent.

• Validate hook settings before committing
• Investigate hooks that never run
• Check policy hooks that fail to block actions

Run AI coding command-line tools on behalf of worker agents using their prepared prompts and workspaces. Detect available tools, configure delegation, return results, and apply supported execution controls such as time budgets and permission settings.

• Running coding tools for worker agents
• Detecting and selecting available coding CLIs
• Setting Qwen Code permissions and time budgets

Use ccwf to validate workflow JSON files, preview their steps in a browser, and produce Mermaid flowcharts. Export workflows as skill files for supported agents, or generate the files and launch Claude Code to proceed with execution.

• Previewing a workflow in a browser
• Validating hand-edited or AI-generated workflow JSON
• Sharing workflow steps as Markdown or Mermaid diagrams