From pletor
Diagnoses and resolves errors when using Pletor MCP operations. Activate when any operation returns an error, when you've retried something more than once, or when you're stuck.
How this skill is triggered — by the user, by Claude, or both
Slash command
/pletor:troubleshooterThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
You are diagnosing an error with a Pletor MCP operation. Follow the guidance below to resolve it quickly.
You are diagnosing an error with a Pletor MCP operation. Follow the guidance below to resolve it quickly.
Activate when:
| Symptom | Cause | Fix |
|---|---|---|
file_path not found / ENOENT | Web MCP clients can't access local files | Use content_base64 instead. Read the file, base64-encode it, and pass with mime_type and filename. |
| "Could not determine MIME type" | No Content-Type header or unknown file extension | Pass mime_type explicitly (e.g., image/jpeg, video/mp4). |
| Upload succeeds but asset not usable | Forgot to provide filename | Always pass filename when using content_base64. |
| Symptom | Fix |
|---|---|
| 401 from any operation | MCP token expired. Ask the user to re-authenticate with Pletor. |
| "fetch failed" or network error | Backend API not reachable. Ask the user to check if Pletor is running. |
This is the most common source of wasted retries. Never guess input formats.
Before passing inputs to run_workflow, always discover the schema:
get_workflow to read the DSL and identify input nodes (types ending with _input).text_input → plain stringimage_input / video_input / audio_input → { "asset_ids": ["<asset_id>"] }get_node_details with the node type to get the expected schema.Errors like "Field required", "Input should be a valid dictionary", or validation errors:
get_node_run_result for the failed node to read the actual error.get_node_details for that node type to see the correct schema.flow_input.get_node_run_result to read the actual error message.get_node_details for unfamiliar node types. Don't guess schemas.get_schema with the operation name to verify you're passing the right parameters.Guides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.
npx claudepluginhub pletor-ai/claude-code-pletor-plugin --plugin pletor