Featbit logo

Featbit

Community
JinFanZheng
featbit

FeatBit official documentation real-time Q&A assistant. Activate when user mentions "FeatBit", "feature flag", "feature toggle", or asks about FeatBit SDK integration, deployment, or configuration. Capabilities: Real-time fetching from docs.featbit.co and GitHub, supporting SDK integration, Docker/K8s deployment, feature flag configuration, A/B testing, and more.

Overview

PublisherJinFanZheng
Repositorykode-sdk-csharp
Skill namefeatbit
Stars
80
Forks
30
Bundled files
4
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 4 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by JinFanZheng on GitHub. Read the source before you install it.

Installation

Install the Featbit AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/JinFanZheng/kode-sdk-csharp.git /tmp/kode-sdk-csharp
mkdir -p .claude/skills
cp -r /tmp/kode-sdk-csharp/examples/Kode.Agent.WebApiAssistant/skills/featbit .claude/skills/featbit
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Featbit in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Featbit on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Featbit is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

FeatBit Documentation Q&A Assistant

Real-time fetching with precise routing, no index maintenance, always up-to-date information.

Documentation Architecture (Critical)

Doc TypeHostingFetch MethodReason
SDK IntegrationGitHub READMEwebReader on GitHubSDK docs not on official site
Deployment/Featuresdocs.featbit.cowebReader on docsStandard doc structure
All TypesReal-time, no cacheFeatBit under active development, docs update frequently

Decision Logic: If question contains "SDK", "integration", "client", "server" keywords → GitHub; otherwise → docs.featbit.co

Workflow

User Question
[MANDATORY Step 1] Load Routing Rules
Use fs_read to completely read the following files (do NOT set line limits):
  - references/page-map.md (29 documentation page mappings)
  - references/keywords.md (keyword matching priority rules)

[IMPORTANT] usage.md is for humans, Agent does NOT need to load it.
Identify question type and platform according to keywords.md rules
Locate relevant documentation pages from page-map.md (note SDK vs other docs hosting difference)
Use webReader to fetch page content (GitHub URLs for SDK, docs.featbit.co for others)
Answer question based on page content
Attach source links

Answer Guidelines

Must Include

  1. Direct Answer: Clear answer in the language of the question, do not repeat the question
  2. Code Examples: Provide directly runnable code for SDK integration questions
  3. Source Links: Attach official documentation links at the end of each answer
markdown
## Answer

To integrate .NET SDK, follow these steps...

### Code Example

\`\`\`csharp
using FeatBit.ServerSdk;
var client = FbClient.Create(...);
\`\`\`

---
**Source**: [.NET Server SDK](https://github.com/featbit/featbit-dotnet-sdk)

Special Cases

No answer in documentation:

Sorry, the official documentation does not contain information about "xxx".
Please check [Official Documentation](https://docs.featbit.co/) or ask in [GitHub Issues](https://github.com/featbit/featbit/issues).

Multiple relevant pages:

Based on your question, the following documentation may be relevant:
1. [Page 1 Title](URL1) - Brief description
2. [Page 2 Title](URL2) - Brief description

NEVER DO (Learned from Pitfalls)

  1. NEVER assume all docs are on docs.featbit.co

    • ❌ Wrong: Using webReader on GitHub may get incomplete content
    • ✅ Right: SDK questions → GitHub README, others → docs.featbit.co
    • 🚨 Consequence: Providing incorrect SDK integration steps
  2. NEVER use LaunchDarkly or other competitor docs to infer

    • ❌ Wrong: "Feature flags should be similar"
    • ✅ Right: Must fetch from FeatBit official docs, say "not found in docs" if missing
    • 🚨 Consequence: APIs are completely different, causes integration failure
  3. NEVER cache documentation content for more than 24 hours

    • ❌ Wrong: Caching SDK docs to save tokens
    • ✅ Right: Always fetch in real-time, especially SDK content
    • 🚨 Consequence: FeatBit SDK updates frequently, cache leads to outdated API advice
  4. NEVER confuse SDK Key and Environment Secret

    • ❌ Wrong: Both keys serve the same purpose, use either
    • ✅ Right: SDK Key for client connections, Environment Secret for server API
    • 🚨 Consequence: Most common beginner mistake, causes SDK initialization failure
  5. NEVER answer with generic "feature flag" concepts

    • ❌ Wrong: Explaining what is feature flag, why use it
    • ✅ Right: Jump directly to "how to create in FeatBit UI" operational steps
    • 🚨 Consequence: User wants operational steps, not concept explanation
  6. NEVER ignore platform differences

    • ❌ Wrong: .NET SDK and JavaScript SDK initialize the same way
    • ✅ Right: Each platform SDK has specific initialization parameters and config
    • 🚨 Consequence: Cross-platform application leads to non-executable code

Tools

Recommended Tool: query.py

Location: scripts/query.py

Use Case: Quick documentation page location (no full answer needed)

python
from scripts.query import FeatBitDocFinder

# Find relevant pages
pages = FeatBitDocFinder.find_pages("How to integrate .NET SDK")

# Output:
# [
#   {
#     "url": "https://github.com/featbit/featbit-dotnet-sdk",
#     "category": "sdk",
#     "reason": "Matched category: sdk, platform: dotnet"
#   }
# ]

Command Line Usage:

bash
# Query pages
python scripts/query.py "How to configure targeting rules"

# List all pages
python scripts/query.py --list-pages

# JSON output
python scripts/query.py "Where to find SDK key?" --json

Note: This tool is only for page location. Full Q&A still requires fetching page content.

Quick Reference

Question Type Quick Reference

Question TypeKeywordsHostingExample
SDK Integrationsdk, integration, initialize, client, serverGitHub"How to integrate React SDK?"
Deployment Operationsdeployment, docker, kubernetes, helmdocs.featbit.co"Docker deployment steps"
Feature Managementfeature flag, toggle, targeting, rollout, ab testdocs.featbit.co"How to configure targeting rules?"
Configuration Managementsdk key, secret, environment, webhookdocs.featbit.co"Where to find SDK key?"

Decision Framework

Before Fetching Documentation, Ask Yourself:

  1. Precise Location: Does the question contain platform/category keywords?

    • Yes → Use keywords.md rules for precise matching
    • No → Return overview page https://docs.featbit.co/
  2. Documentation Location: Is this an SDK question or other question?

    • SDK → Go to GitHub README
    • Other → Go to docs.featbit.co
    • Basis: Classification in page-map.md
  3. Timeliness: Does this type of information change frequently?

    • SDK API → Must fetch in real-time
    • Core concepts → Can cache 24h (but real-time still recommended)
  4. Completeness: Does the user need operational steps or concept explanation?

    • Operations → Fetch directly and provide steps
    • Concepts → Explain first, then provide doc link

Handling Fetch Failures

SymptomPossible CauseSolution
404 ErrorURL expiredCheck if page-map.md needs update
Empty ContentGitHub README in non-standard locationTry fetching repository root directory
Incomplete ContentwebReader parsing issueTry fetching directly from raw.githubusercontent.com

Extension & Maintenance

Adding New Documentation Pages

Edit PAGES dictionary in scripts/query.py:

python
PAGES = {
    "sdk": {
        "new-platform": "https://github.com/featbit/featbit-new-platform-sdk",
    },
    "deployment": {
        "new-platform": "https://docs.featbit.co/installation/new-platform",
    },
}

Adding New Keywords

Edit KEYWORDS dictionary in scripts/query.py:

python
KEYWORDS = {
    "new-platform": ["new-platform", "np", "new platform"],
}

Important: When modifying, also update:

  • references/page-map.md - Documentation mapping
  • references/keywords.md - Keyword rules

Reference Materials

  • references/page-map.md - Complete mapping of 29 documentation pages (Agent MUST load)
  • references/keywords.md - Keyword matching rules and priorities (Agent MUST load)
  • references/usage.md - Human usage guide (Agent does NOT need to load)

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Featbit AI skill do?

FeatBit official documentation real-time Q&A assistant. Activate when user mentions "FeatBit", "feature flag", "feature toggle", or asks about FeatBit SDK integration, deployment, or configuration. Capabilities: Real-time fetching from docs.featbit.co and GitHub, supporting SDK integration, Docker/K8s deployment, feature flag configuration, A/B testing, and more.

Why use Featbit on TypingMind?

Because you install it once and use it with any model. Featbit is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Featbit in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/JinFanZheng/kode-sdk-csharp/tree/main/examples/Kode.Agent.WebApiAssistant/skills/featbit. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Featbit?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Featbit?

As many as you like. As long as a model supports skills, you can use Featbit with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Featbit AI skill free?

Yes. It is published on GitHub by JinFanZheng under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇