trustabl/agent-reliability-analyzer/action-creator
Claude Code and agent skill by trustabl/agent-reliability-analyzer
- community
Checking that the SKILL.md file is still in the repository.
Creates user-specific one-click action templates that execute email operations when clicked in the chat interface. Use when user wants reusable actions for their specific workflows (send payment reminder to ACME Corp, forward bugs to engineering, archive old newsletters from specific sources).
Install
npx vskill@latest install trustabl/agent-reliability-analyzer/action-creatorSKILL.md
The same SKILL.md was published earlier as anthropics/claude-agent-sdk-demos/action-creator.
Action Creator
Creates TypeScript action template files that define reusable, user-specific operations users can execute with one click in the chat interface.
When to Use This Skill
Use this skill when the user wants to:
- Create reusable actions for their specific workflows ("I often need to send payment reminders to ACME Corp")
- Set up one-click operations for their vendors/customers ("Forward bugs to engineering team")
- Automate repetitive email tasks with their specific context ("Archive newsletters from TechCrunch/Morning Brew")
- Build personalized email management tools for their business processes
Key difference from listeners: Actions are user-triggered (clicked in chat), while listeners are event-triggered (automatic).
How Actions Work
Actions are TypeScript files in agent/custom_scripts/actions/ that:
- Export a
configobject defining the template metadata and parameter schema - Export a
handlerfunction that executes the operation with given parameters - Use
ActionContextmethods to perform operations (email API, send emails, call AI, etc.)
The agent creates action instances during conversation by providing specific parameters to these templates, which appear as clickable buttons in the chat.
Creating an Action Template
1. Understand User-Specific Workflow
Parse the user's request to identify:
- User context: Who are their specific vendors/customers/teams?
- Operation: What specific action do they need? (send to ACME Corp, forward to engineering team, etc.)
- Parameters: What varies per execution? (invoice number, priority level, days old)
- Frequency: How often will they use this?
2. Write the Action Template File
Create a file in agent/custom_scripts/actions/ with this structure:
3. File Naming Convention
Use kebab-case that reflects the user-specific operation:
send-payment-reminder-to-acme.ts(notsend-email.ts)forward-bugs-to-engineering.ts(notforward-email.ts)archive-newsletters-from-techcrunch.ts(notarchive-emails.ts)summarize-weekly-updates-from-ceo.ts(notsummarize-emails.ts)
Important: Templates should be specific to the user's actual workflows, vendors, teams, and processes.
4. Available Context Methods
The ActionContext provides these capabilities:
Action Result
Always return an ActionResult object:
Examples and Templates
Reference the template files for common patterns:
- [send-payment-reminder.ts](templates/send-payment-reminder.ts): Send invoice reminders to specific vendor
- [forward-bug-report.ts](templates/forward-bug-report.ts): Forward bugs to engineering with AI analysis
- [archive-old-newsletters.ts](templates/archive-old-newsletters.ts): Archive newsletters from specific sources
Best Practices
- User-Specific Templates: Create templates tailored to user's actual vendors, customers, teams, and processes
- Descriptive Naming: Use specific names that reflect the operation (not generic like "send-email")
- Rich Parameter Schemas: Define clear parameter types with descriptions
- AI-Powered: Use
context.callAgent()for intelligent processing - Error Handling: Always wrap operations in try-catch and return meaningful errors
- Clear Messages: Return human-readable success/failure messages
- Idempotency: Design handlers to be safely re-runnable when possible
- Logging: Use
context.log()for debugging and audit trail
Parameter Schema Guidelines
Define parameters using JSON Schema:
Creating the File
When the user requests an action template:
- Clarify user-specific context:
- Who are their vendors/customers/teams?
- What are their specific workflows?
- What parameters vary per execution?
- Write the TypeScript file in
agent/custom_scripts/actions/
- Use Write tool to create the file with:
- Proper imports from "../types"
- User-specific config (not generic)
- Parameter schema with all required fields
- Handler with error handling
- Clear success/failure messages
- Test parameters: Ensure all required parameters are defined
- Confirm with user that the action matches their workflow
Common Patterns
1. Send Email to Specific Recipient
User-specific → Compose email with template → Send → Return result
2. Bulk Email Operation
Search emails → Filter → Apply operation to each → Return count
3. AI-Powered Email Processing
Get email → Call AI to analyze → Use AI result → Take action → Return summary
4. Email Forwarding with Enhancement
Get email → AI analysis → Compose enhanced forward → Send → Label original
Type Imports
Always import types from the correct location:
How Users Trigger Actions
After you create an action template:
- Agent discovers template: During conversation, agent reads available actions
- Agent creates instance: Agent provides specific parameters for user's situation
- User sees button: Action instance appears as clickable button in chat
- User clicks: Action executes with pre-filled parameters
- Result appears: Success/failure message shown in chat
Example flow:
Reference
This is the start of the file. Read the full SKILL.md on GitHub.
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingtestdata/corpus/email-agent/agent/.claude/skills/action-creator/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/trustabl/agent-reliability-analyzer/action-creator)