docs: document custom/OpenAI-compatible LLM providers + fix stale versions

Add a clear path for users without Anthropic API credits to power the AI
enhancement step:
- README: replace the narrow GLM-only block with a three-way provider guide
  (LOCAL agent mode for ChatGPT Plus/Claude Pro subscriptions, any
  OpenAI-compatible endpoint via OPENAI_BASE_URL, Claude-compatible endpoints)
- ENVIRONMENT_VARIABLES: add OPENAI_BASE_URL, MOONSHOT_API_KEY,
  SKILL_SEEKER_AGENT_CMD, SKILL_SEEKER_MODEL, per-provider model table, and a
  new 'LLM Provider Selection' section with OpenRouter/Groq/Cerebras/Mistral/
  NVIDIA NIM endpoints

Fix pre-existing doc bugs:
- SKILL_SEEKERS_ENHANCE_TIMEOUT -> SKILL_SEEKER_ENHANCE_TIMEOUT (wrong name
  was a no-op); default 600s -> 2700s; document unlimited/0 -> 24h
- ANTHROPIC_MODEL default claude-3-5-sonnet-20241022 -> claude-sonnet-4-20250514
- Bump stale version strings to 3.7.0 (README badge, env-vars doc + user-agent,
  CLAUDE.md)

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

Author: yusufkaraaslan

CLAUDE.md

@@ -6,7 +6,7 @@ This file provides guidance to Claude Code (claude.ai/code) when working with co
 
 **Skill Seekers** converts documentation from 18 source types into production-ready formats for 21+ AI platforms (LLM platforms, RAG frameworks, vector databases, AI coding assistants). Published on PyPI as `skill-seekers`.
 
-**Version:** 3.5.0 | **Python:** 3.10+ | **Website:** https://skillseekersweb.com/
+**Version:** 3.7.0 | **Python:** 3.10+ | **Website:** https://skillseekersweb.com/
 
 **Architecture:** See `docs/UML_ARCHITECTURE.md` for UML diagrams and module overview. StarUML project at `docs/UML/skill_seekers.mdj`.
 

README.md

@@ -6,7 +6,7 @@
 
 English | [简体中文](README.zh-CN.md) | [日本語](README.ja.md) | [한국어](README.ko.md) | [Español](README.es.md) | [Français](README.fr.md) | [Deutsch](README.de.md) | [Português](README.pt-BR.md) | [Türkçe](README.tr.md) | [العربية](README.ar.md) | [हिन्दी](README.hi.md) | [Русский](README.ru.md)
 
-[![Version](https://img.shields.io/badge/version-3.6.0-blue.svg)](https://github.com/yusufkaraaslan/Skill_Seekers/releases)
+[![Version](https://img.shields.io/badge/version-3.7.0-blue.svg)](https://github.com/yusufkaraaslan/Skill_Seekers/releases)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 [![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)
 [![MCP Integration](https://img.shields.io/badge/MCP-40-Tools-blue.svg)](https://modelcontextprotocol.io)
@@ -341,24 +341,51 @@ skill-seekers package output/react/ --target markdown
 ```
 
 <details>
-<summary>🔧 <strong>Environment Variables for Claude-Compatible APIs (e.g., GLM-4.7)</strong></summary>
+<summary>🔧 <strong>Use your own AI provider (OpenAI-compatible endpoints + subscriptions, no Anthropic credits needed)</strong></summary>
 
-Skill Seekers supports any Claude-compatible API endpoint:
+The optional AI **enhancement** step (used by `create`, `scan`, and `enhance`) does **not** require an Anthropic key. You have three ways to power it:
+
+**1. Use a subscription you already pay for — no API credits at all (LOCAL agent mode)**
+
+Skill Seekers can shell out to a coding-agent CLI you're already logged into, so enhancement runs on your existing plan instead of metered API tokens:
 
 ```bash
-# Option 1: Official Anthropic API (default)
-export ANTHROPIC_API_KEY=sk-ant-...
+skill-seekers create <source> --agent codex     # OpenAI Codex CLI → your ChatGPT Plus
+skill-seekers create <source> --agent claude    # Claude Code      → your Claude Pro/Max
+```
 
-# Option 2: GLM-4.7 Claude-compatible API
-export ANTHROPIC_API_KEY=your-glm-47-api-key
-export ANTHROPIC_BASE_URL=https://glm-4-7-endpoint.com/v1
+Supported agents: `claude`, `codex`, `copilot`, `opencode`, `kimi`, and `custom`
+(pair `--agent custom` with `--agent-cmd "<your-cli> ..."` to drive any other tool).
 
-# All AI enhancement features will use the configured endpoint
-skill-seekers enhance output/react/
-skill-seekers scan . --enhance
+**2. Any OpenAI-compatible provider (OpenRouter, Groq, Cerebras, Mistral, NVIDIA NIM, …)**
+
+All of these expose an OpenAI-compatible `/v1` endpoint. Point Skill Seekers at one with three env vars — it detects `OPENAI_API_KEY`, and the OpenAI SDK honors `OPENAI_BASE_URL` automatically:
+
+```bash
+export OPENAI_API_KEY="<your provider key>"
+export OPENAI_BASE_URL="https://openrouter.ai/api/v1"   # provider endpoint (see table)
+export OPENAI_MODEL="<a model that provider offers>"     # required — default gpt-4o won't exist elsewhere
+skill-seekers create <source>
+```
+
+| Provider     | `OPENAI_BASE_URL`                          |
+|--------------|--------------------------------------------|
+| OpenRouter   | `https://openrouter.ai/api/v1`             |
+| Groq         | `https://api.groq.com/openai/v1`           |
+| Cerebras     | `https://api.cerebras.ai/v1`               |
+| Mistral      | `https://api.mistral.ai/v1`                |
+| NVIDIA NIM   | `https://integrate.api.nvidia.com/v1`      |
+
+> Provider detection picks the **first** API-key env var it finds (`ANTHROPIC_API_KEY` → `MOONSHOT_API_KEY` → `GOOGLE_API_KEY` → `OPENAI_API_KEY`). If you want the OpenAI-compatible route, make sure the higher-priority keys are unset.
+
+**3. Claude-compatible endpoints (e.g. GLM, proxies)**
+
+```bash
+export ANTHROPIC_API_KEY="your-key"
+export ANTHROPIC_BASE_URL="https://your-claude-compatible-endpoint/v1"
 ```
 
-**Note**: Setting `ANTHROPIC_BASE_URL` allows you to use any Claude-compatible API endpoint, such as GLM-4.7 (智谱 AI) or other compatible services.
+Google Gemini (`GOOGLE_API_KEY`) and Kimi/Moonshot (`MOONSHOT_API_KEY`) are also supported natively. See **[Environment Variables Reference](docs/reference/ENVIRONMENT_VARIABLES.md#llm-provider-selection)** for the full list, including per-provider model overrides.
 
 </details>
 
@@ -1101,7 +1128,7 @@ python -m skill_seekers.mcp.server_fastmcp --transport http --port 8765
 
 ```bash
 # List all presets
-# skill-seekers list-configs  # Not available in v3.6.0
+# skill-seekers list-configs  # Not available in v3.7.0
 ```
 
 | Category | Presets |

docs/reference/ENVIRONMENT_VARIABLES.md

@@ -1,6 +1,6 @@
 # Environment Variables Reference - Skill Seekers
 
-> **Version:** 3.6.0  
+> **Version:** 3.7.0  
 > **Last Updated:** 2026-02-16  
 > **Complete environment variable reference**
 
@@ -11,6 +11,7 @@
 - [Overview](#overview)
 - [API Keys](#api-keys)
 - [Platform Configuration](#platform-configuration)
+- [LLM Provider Selection](#llm-provider-selection)
 - [Paths and Directories](#paths-and-directories)
 - [Scraping Behavior](#scraping-behavior)
 - [Enhancement Settings](#enhancement-settings)
@@ -75,11 +76,12 @@ export GOOGLE_API_KEY=AIzaSyxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
 
 ### OPENAI_API_KEY
 
-**Purpose:** OpenAI API access for upload and embeddings.
+**Purpose:** OpenAI (and OpenAI-compatible) API access for enhancement, upload, and embeddings.
 
 **Format:** `sk-...`
 
 **Used by:**
+- `skill-seekers create` / `scan` / `enhance` (AI enhancement, API mode)
 - `skill-seekers upload` (OpenAI target)
 - Embedding generation for vector DBs
 
@@ -88,6 +90,26 @@ export GOOGLE_API_KEY=AIzaSyxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
 export OPENAI_API_KEY=sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
 ```
 
+> Combine with `OPENAI_BASE_URL` + `OPENAI_MODEL` to route enhancement through any
+> OpenAI-compatible provider (OpenRouter, Groq, Cerebras, Mistral, NVIDIA NIM).
+> See [LLM Provider Selection](#llm-provider-selection).
+
+---
+
+### MOONSHOT_API_KEY
+
+**Purpose:** Moonshot AI (Kimi) API access for enhancement (API mode).
+
+**Format:** `sk-...`
+
+**Used by:**
+- `skill-seekers create` / `scan` / `enhance` (enhancement, Kimi/Moonshot)
+
+**Example:**
+```bash
+export MOONSHOT_API_KEY=sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
+```
+
 ---
 
 ### GITHUB_TOKEN
@@ -134,6 +156,61 @@ export ANTHROPIC_BASE_URL=https://custom-api.example.com
 
 ---
 
+### OPENAI_BASE_URL
+
+**Purpose:** Custom OpenAI-compatible API endpoint for enhancement.
+
+**Default:** `https://api.openai.com/v1`
+
+**Use case:** Any OpenAI-compatible provider — OpenRouter, Groq, Cerebras, Mistral,
+NVIDIA NIM, local servers (Ollama, vLLM, LM Studio), proxies.
+
+**Example:**
+```bash
+export OPENAI_BASE_URL=https://openrouter.ai/api/v1
+```
+
+> Read automatically by the OpenAI SDK. Pair with `OPENAI_API_KEY` and `OPENAI_MODEL`.
+
+---
+
+## LLM Provider Selection
+
+The AI **enhancement** step (`create`, `scan`, `enhance`) supports multiple providers
+through one abstraction. The provider is chosen by the **first** API key found, in this
+order: `ANTHROPIC_API_KEY` → `ANTHROPIC_AUTH_TOKEN` → `MOONSHOT_API_KEY` →
+`GOOGLE_API_KEY` → `OPENAI_API_KEY`. If none is set, it falls back to **LOCAL agent
+mode** (`--agent`, no API key required — uses your Claude Pro / ChatGPT Plus subscription).
+
+### Any OpenAI-compatible provider (OpenRouter, Groq, Cerebras, Mistral, NVIDIA NIM)
+
+```bash
+export OPENAI_API_KEY="<provider key>"
+export OPENAI_BASE_URL="https://api.groq.com/openai/v1"   # provider endpoint
+export OPENAI_MODEL="llama-3.3-70b-versatile"             # a model that provider offers
+skill-seekers create <source>
+```
+
+| Provider     | `OPENAI_BASE_URL`                     |
+|--------------|---------------------------------------|
+| OpenRouter   | `https://openrouter.ai/api/v1`        |
+| Groq         | `https://api.groq.com/openai/v1`      |
+| Cerebras     | `https://api.cerebras.ai/v1`          |
+| Mistral      | `https://api.mistral.ai/v1`           |
+| NVIDIA NIM   | `https://integrate.api.nvidia.com/v1` |
+
+> Set `OPENAI_MODEL` — the OpenAI default (`gpt-4o`) won't exist on other providers.
+> Ensure no higher-priority key (e.g. `ANTHROPIC_API_KEY`) is set, or it wins.
+
+### Subscriptions instead of API credits (LOCAL mode)
+
+```bash
+skill-seekers create <source> --agent codex    # ChatGPT Plus via Codex CLI
+skill-seekers create <source> --agent claude   # Claude Pro/Max via Claude Code
+```
+
+---
+
 ## Paths and Directories
 
 ### SKILL_SEEKERS_HOME
@@ -261,7 +338,7 @@ export SKILL_SEEKERS_TIMEOUT=60
 
 **Purpose:** Custom User-Agent header.
 
-**Default:** `Skill-Seekers/3.6.0`
+**Default:** `Skill-Seekers/3.7.0`
 
 **Example:**
 ```bash
@@ -291,36 +368,64 @@ export SKILL_SEEKER_AGENT=cursor
 
 ---
 
-### SKILL_SEEKERS_ENHANCE_TIMEOUT
+### SKILL_SEEKER_AGENT_CMD
 
-**Purpose:** Timeout for AI enhancement operations.
+**Purpose:** Custom CLI command template for `--agent custom` (LOCAL mode).
 
-**Default:** `600` (seconds = 10 minutes)
+**Used by:** `skill-seekers create` / `scan` / `enhance` when `SKILL_SEEKER_AGENT=custom`.
 
 **Example:**
 ```bash
-# For large skills
-export SKILL_SEEKERS_ENHANCE_TIMEOUT=1200
+export SKILL_SEEKER_AGENT=custom
+export SKILL_SEEKER_AGENT_CMD="my-llm-cli --prompt-file {prompt_file}"
+```
+
+---
+
+### SKILL_SEEKER_MODEL
+
+**Purpose:** Global model override for API-mode enhancement (wins over all
+per-provider model vars below).
+
+**Example:**
+```bash
+export SKILL_SEEKER_MODEL=llama-3.3-70b-versatile
 ```
 
-**Override:** Use `--timeout` flag.
+---
+
+### Per-provider model overrides
+
+Used only when `SKILL_SEEKER_MODEL` is unset. Each falls back to a per-provider default.
+
+| Variable          | Provider           | Default (if unset)          |
+|-------------------|--------------------|-----------------------------|
+| `ANTHROPIC_MODEL` | Anthropic          | `claude-sonnet-4-20250514`  |
+| `OPENAI_MODEL`    | OpenAI/-compatible | `gpt-4o`                    |
+| `GOOGLE_MODEL`    | Gemini             | `gemini-2.0-flash`          |
+| `MOONSHOT_MODEL`  | Moonshot/Kimi      | `moonshot-v1-auto`          |
+
+```bash
+export OPENAI_MODEL=llama-3.3-70b-versatile
+```
 
 ---
 
-### ANTHROPIC_MODEL
+### SKILL_SEEKER_ENHANCE_TIMEOUT
 
-**Purpose:** Claude model for API enhancement.
+**Purpose:** Timeout for AI enhancement operations (seconds).
 
-**Default:** `claude-3-5-sonnet-20241022`
+**Default:** `2700` (45 minutes)
 
-**Options:**
-- `claude-3-5-sonnet-20241022` (recommended)
-- `claude-3-opus-20240229` (highest quality, more expensive)
-- `claude-3-haiku-20240307` (fastest, cheapest)
+**Special values:** `unlimited`, `none`, or `0` map to a 24-hour ceiling.
 
 **Example:**
 ```bash
-export ANTHROPIC_MODEL=claude-3-opus-20240229
+# For large skills
+export SKILL_SEEKER_ENHANCE_TIMEOUT=3600
+
+# No practical limit
+export SKILL_SEEKER_ENHANCE_TIMEOUT=unlimited
 ```
 
 ---