ledda

Search and debug LLM traces from Ledda's observability platform. Find errors, compare traces, analyze costs and tokens.

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "ledda" with this command: npx skills add leddaai/ledda-skills/leddaai-ledda-skills-ledda

Ledda Skill

Connect to Ledda's LLM observability platform to search traces, inspect errors, compare runs, and analyze costs — from any AI coding agent.

User-Invocable Skills

/ledda onboarding

Set up Ledda credentials for this project.

When the user runs /ledda onboarding:

  1. Look for a credentials block in the user's message. The block contains ini-formatted sections like:
[account-42]
api_key = ldda_ak_...
account_name = Production
base_url = https://app.ledda.ai
  1. Write the credentials to .ledda/.credentials in the project root. If the file already exists, ask the user if they want to overwrite or merge.

  2. Add .ledda/ to the project's .gitignore if not already present.

  3. Confirm which accounts were configured by listing account names.

/ledda

Search and debug LLM traces using Ledda's API.

When the user runs /ledda (with or without a follow-up question):

  1. Read .ledda/.credentials to discover available accounts and their API keys.

    • If .ledda/.credentials doesn't exist, tell the user to run onboarding from the Ledda UI first (Settings > AI Agent Integration).
  2. Check the documentation version:

    • Call GET <base_url>/docs/version (no auth needed) to get the current content hash.
    • Check if .ledda/<hash>/ directory exists locally.
    • If not, fetch the latest docs:
      • GET <base_url>/docs/md/reference → save to .ledda/<hash>/reference.md
      • GET <base_url>/docs/md/guide → save to .ledda/<hash>/guide.md
  3. Read the cached documentation files (.ledda/<hash>/guide.md and .ledda/<hash>/reference.md) to understand available API endpoints.

  4. Help the user with their request using the Ledda API:

    • Use the appropriate account's API key as a Bearer token: Authorization: Bearer <api_key>
    • If the user doesn't specify an account and there's only one, use it
    • If there are multiple accounts, ask which one to use (or let them specify by name)
    • Follow the guide for common workflows (searching, filtering, comparing traces)

Authentication

All Ledda API calls (except /docs/*) require a Bearer token:

Authorization: Bearer ldda_ak_your_key_here

Each API key is scoped to a single account. Use the key matching the account the user wants to query.

Credentials File Format

The .ledda/.credentials file uses ini format. See references/credentials-format.md for details.

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

General

ll-feishu-audio

飞书语音交互技能。支持语音消息自动识别、AI 处理、语音回复全流程。需要配置 FEISHU_APP_ID 和 FEISHU_APP_SECRET 环境变量。使用 faster-whisper 进行语音识别,Edge TTS 进行语音合成,自动转换 OPUS 格式并通过飞书发送。适用于飞书平台的语音对话场景。

Archived SourceRecently Updated
General

test_skill

import json import tkinter as tk from tkinter import messagebox, simpledialog

Archived SourceRecently Updated
General

51mee-resume-profile

简历画像。触发场景:用户要求生成候选人画像;用户想了解候选人的多维度标签和能力评估。

Archived SourceRecently Updated
General

51mee-resume-parse

简历解析。触发场景:用户上传简历文件要求解析、提取结构化信息。

Archived SourceRecently Updated