القائمة
Creates skills, agents, or both together. A unified factory for building Claude Code extensions with proper configuration, best practices, and coordinated workflows.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Show usage information for any workflow-toolkit skill. Use when the user asks how to use a specific skill, what a skill does, or needs guidance on workflow-toolkit features. Also triggers on "help", "how do I", "what does X do", or "usage" in the context of workflow-toolkit skills.
Initialize and verify the workflow-toolkit environment. Checks SQLite availability, creates the journal database, verifies directory structure, checks gh CLI auth, and reports readiness. Run this after installing the plugin or when troubleshooting.
Pre-flight checklist for open source contributions. Validates code changes against project rules, PR size limits, commit format, linting, and type-checking. Does NOT push or create PRs — only reports issues.
Creates a new Claude Code custom subagent configuration. Guides you through designing agent scope, tools, permissions, hooks, and system prompts.
Creates a new Claude Code custom skill (slash command). Guides you through designing, writing, and placing the SKILL.md file with proper frontmatter, arguments, and best practices.
Open the journal SQLite database in a GUI viewer (DB Browser for SQLite, or similar).
| name | skill-and-agent-factory |
| description | Creates skills, agents, or both together. A unified factory for building Claude Code extensions with proper configuration, best practices, and coordinated workflows. |
| argument-hint | <skill|agent|both> <name> <description of what to build> |
| disable-model-invocation | true |
You are a factory for creating Claude Code extensions based on the user's request: $ARGUMENTS
This factory can create:
/skill-name)Parse $ARGUMENTS to determine the creation mode:
| First token | Action |
|---|---|
skill | Create a skill only |
agent | Create an agent only |
both | Create a coordinated skill + agent pair |
| (anything else) | Infer from context |
.claude/skills/ to avoid conflicts.claude/agents/| Choose Skill when... | Choose Agent when... | Choose Both when... |
|---|---|---|
| Runs in main conversation context | Needs isolation | User-facing command that delegates to isolated agent |
| No special tool restrictions | Specific tools needed | Quick inline mode + thorough isolated mode |
| Reusable prompt or reference material | Verbose output would pollute context | Orchestration skill + execution agent |
Pattern A: Skill delegates to agent — Skill uses context: fork + agent: <name>
Pattern B: Independent but complementary — Skill for quick inline, agent for deep analysis
Pattern C: Skill preloads into agent — Agent uses skills field for domain knowledge
.claude/skills/<name>/SKILL.mdUse the /workflow-toolkit:create-skill workflow.
.claude/agents/<name>.mdUse the /workflow-toolkit:create-agent workflow.
Provide a summary with file paths, invocation instructions, example usage, and architecture notes for how extensions relate to each other.