← Back to Skills Marketplace
haoruilee

Add to Awesome Agent-Native Services

by 0x4C33 · GitHub ↗ · v1.4.0 · MIT-0
cross-platform ✓ Security Clean
265
Downloads
0
Stars
0
Active Installs
5
Versions
Install in OpenClaw
/install add-to-awesome-list
Description
Guide a contributor through the full process of adding a new service to the awesome-agent-native-services catalog: verifying criteria, checking for URL Onboa...
README (SKILL.md)

Skill: add-to-awesome-list

Use this skill to walk a contributor through the complete process of adding a new service to the catalog, from eligibility check through a merged PR.

The most important thing to check first: URL Onboarding

Before running through the five criteria, ask this one question:

Can an agent join and start using this service by reading a single URL?

Read \x3Curl> and follow the instructions.

If YES — this is URL Onboarding, the highest form of agent-nativeness. Mark it prominently throughout the service file, the issue, and the PR. It means the service designed its onboarding for machines, not humans.

Known URL Onboarding services in the catalog:

  • Moltbook: Read https://www.moltbook.com/skill.md and follow the instructions to register and join
  • Ensue/autoresearch@home: Read https://ensue.dev/docs + Read .../collab.md and follow the instructions to join

When the new service has URL Onboarding, lead with this in every section.


Phase 1 — Pre-flight eligibility check

1.0 Check for URL Onboarding first

Look for a machine-readable protocol file:

  • skill.md or SKILL.md at the service's domain
  • collab.md, protocol.md, or similar at the repo root
  • Any URL the service documents as the agent onboarding entry point

Test it: can you give an agent the instruction Read \x3Curl> and follow the instructions and have it complete registration autonomously?

Record the result for Phase 3's "How to Use" section.

1.1 Check for duplicates

1. Read README.md — search for the service name in all 15 category sections.
2. Search open issues: https://github.com/haoruilee/awesome-agent-native-services/issues?q=\x3Cservice-name>
3. If found: report the existing entry or issue URL and stop.

1.2 Apply the five criteria

Use the evaluate-agent-native skill (or apply inline):

For each criterion, find evidence from the official homepage or docs — direct quotes, not marketing copy.

If any criterion fails: tell the user which failed and what the correct classification is. Do not proceed.

1.3 Determine the category and interaction pattern

What the service does Category folder Typical pattern
Communication identity (email, notifications) communication/ SDK / Skill
Remote browser or web extraction browser-and-web-execution/ Skill / SDK / Daemon
Runtime tool discovery, OAuth, execution tool-access-and-integration/ Skill / SDK
Human approval gates oversight-and-approval/ SDK
Agent wallets, payments, identity commerce-and-payments/ SDK / REST
Execution, secrets, identity, gateway agent-runtime-and-infrastructure/ SDK
Per-agent memory memory-and-state/ SDK / MCP
Multi-agent shared memory / coordination memory-and-state/ URL Onboarding ⭐
LLM-optimized search search-and-web-intelligence/ Skill / MCP
Code sandbox code-execution/ SDK / MCP
Agent trajectory tracing observability-and-tracing/ Skill
Fault-tolerant agent workflows durable-execution-and-scheduling/ Skill / SDK
Agent presence in meetings meeting-and-conversation/ REST
Voice calls / phone voice-and-phone/ SDK
LLM routing, cost, fallback llm-gateway-and-routing/ SDK
Agent social network / community agent-social-network/ URL Onboarding ⭐

Phase 2 — Open a GitHub issue

Do not write the PR before the issue is approved.

Issue URL: https://github.com/haoruilee/awesome-agent-native-services/issues/new?template=01-new-service.yml

Required fields:

  • Service name and official website
  • Official tagline — exact quote from homepage
  • Proposed category
  • Criterion evidence — one field per criterion
  • URL Onboarding instruction — if available, provide the exact sentence
  • MCP status — is there a published MCP server?
  • Agent Skills status — is there a published SKILL.md?
  • Classification: agent-native
  • Generic alternative comparison

After submission, wait for a maintainer ✅ Go before proceeding.


Phase 3 — Write the service file

File location

services/{category-folder}/{service-name}.md

Naming: lowercase, hyphens only, e.g. agentmail.md, trigger-dev.md.

Required sections (14 total, in this order)

# {Service Name}

> **"{Official tagline}"**

| | |
|---|---|
| **Website** | https://... |
| **Classification** | `agent-native` |
| **Category** | [{Category}](README.md) |

---

## Official Website
https://...

---

## Official Repo
https://github.com/...

---

## ⭐ How to Use (Agent Onboarding)

\x3C!-- CRITICAL: This section tells an agent how to START USING the service. -->
\x3C!-- For URL Onboarding services, this is THE most important section. -->

**Interaction pattern:** URL Onboarding / MCP Tool / Coding-time Skill / SDK+REST / Daemon+Extension

\x3C!-- URL Onboarding (highest tier): -->
**One-sentence agent instruction:**

Read https://... and follow the instructions to [register / join / participate].

What the agent gets by reading that URL: {full onboarding sequence, registration, protocol}

\x3C!-- For other patterns: -->
**MCP:** Add to `mcp_servers`: `{ "command": "npx", "args": ["-y", "\x3Cpkg>", "--mcp"] }`
**Skill:** `npx skills add \x3Corg>/\x3Crepo>`
**SDK:** `pip install \x3Cpkg>` then `\x3Cone-line first API call>`
**Daemon:** `npm install -g \x3Cpkg>` + install extension

---

## Agent Skills
**Status:** ✅ / ⚠️
[install command + skill table OR community search note]

---

## MCP
**Status:** ✅ / ⚠️
[server details OR "not yet published"]

---

## What It Does
[1-3 paragraphs]

---

## Why It Is Agent-Native
| Criterion | Evidence |
|---|---|
| Agent-first positioning | "{quote}" — {url} |
| Agent-specific primitive | {description} |
| Autonomy-compatible control plane | {description} |
| M2M integration surface | {interfaces} |
| Identity / delegation | {model} |

---

## Primary Primitives
| Primitive | Description |
|---|---|
| **{Name}** | {one sentence} |

---

## Autonomy Model
[Step-by-step: what the agent does, no human in the loop]

---

## Identity and Delegation Model
[Bullet list: agent identity, delegated permissions, audit trail]

---

## Protocol Surface
| Interface | Detail |
|---|---|
| REST API | ... |
| SDK | ... |

---

## Human-in-the-Loop Support
[One paragraph]

---

## Why Generic Alternatives Do Not Qualify
| Alternative | Why It Fails |
|---|---|
| **{Name}** | {reason} |

---

## Use Cases
- **{title}** — {description}

Research checklist

  • URL Onboarding: try Read \x3Curl> and follow the instructions — does it work?
  • Official Website / Repo: from GitHub or homepage
  • Agent Skills: check skills.sh, agentskills.io, service GitHub
  • MCP: check service GitHub, mcp.so, glama.ai/mcp, smithery.ai
  • Why It Is Agent-Native: direct quotes from official docs
  • Protocol Surface: check SDK README for install commands
  • Use Cases: from service's own documentation

Phase 4 — Update the index files

4.1 Update services/{category}/README.md

Add a row to the service table (5 columns now: Service, Tagline, Primitives, MCP, How to Use):

| [{Service Name}]({service-name}.md) | {tagline} | {primitives} | ✅/⚠️ | {onboarding instruction} |

For URL Onboarding services, the "How to Use" cell should be the full one-sentence instruction.

4.2 Update root README.md

Find the correct category section and add a row:

| [{Service Name}](services/{category}/{service-name}.md) | {tagline} | {primitives} | ✅/⚠️ | {onboarding instruction} |

Phase 5 — Open the PR

PR title format

[New Service] {Service Name}
[New Service] {Service Name} — URL Onboarding  ← if has URL Onboarding

Git commands

git checkout -b add-{service-name}
git add services/{category}/{service-name}.md services/{category}/README.md README.md
git commit -m "[New Service] {Service Name}

Closes #{issue number}

- Category: {category}
- Interaction pattern: {URL Onboarding ⭐ / MCP / Skill / SDK / Daemon}
- How to use: {one-sentence instruction}
- MCP: {✅ / ⚠️}
- Agent Skills: {✅ / ⚠️}"
git push origin add-{service-name}

Quality checklist before submitting

  • All links are live
  • Official tagline is an exact quote
  • All criterion evidence cites a specific URL
  • "How to Use" section accurately describes the interaction pattern
  • URL Onboarding instruction tested and confirmed working (if applicable)
  • All 14 required sections present
  • Agent Skills section shows real install commands
  • MCP section shows real repo/transport
  • No undisclosed financial interest in the service
Usage Guidance
This skill is a written, step-by-step contributor guide and appears coherent with its purpose, but it instructs agents to interact with external sites and run shell/npm/pip commands as part of onboarding. If you let an agent act on these instructions, review and approve actions before allowing automated registrations, installs, or PRs; do not provide credentials or elevated repo write/push permissions unless you trust the agent and maintainer process. If you want to be extra safe, run the steps manually or allow the agent to prepare drafts only (issue/PR text) and require a human to perform the actual submission and any account provisioning.
Capability Analysis
Type: OpenClaw Skill Name: add-to-awesome-list Version: 1.4.0 The skill bundle provides a structured workflow for an AI agent to contribute new entries to the 'awesome-agent-native-services' GitHub repository. It uses standard tools like WebSearch, Read, Write, and Shell for legitimate purposes such as researching service documentation, generating markdown files, and executing git commands for PR submission (SKILL.md). While it introduces a 'URL Onboarding' concept that directs agents to follow instructions from external URLs, this is presented as a functional feature for agent-native services rather than a malicious injection attempt.
Capability Assessment
Purpose & Capability
Name, description, and SKILL.md all describe a step-by-step contributor guide. The actions referenced (read homepages/docs, open a GitHub issue, write a service file, use npx/pip examples) are consistent with adding entries to the catalog. No unrelated credentials, binaries, or config paths are required.
Instruction Scope
The SKILL.md explicitly instructs agents to 'Read <url> and follow the instructions', inspect remote documentation, search the catalog README, open GitHub issues, and includes example shell/npm/pip commands. These steps are within scope for adding a service, but they can produce side effects (automated registration, running install commands, creating PRs) if an agent is allowed to act autonomously—so reviewer caution is warranted.
Install Mechanism
No install spec and no code files are present (instruction-only). Nothing will be downloaded or written by an installer; risks from package install sources are not introduced by the skill itself.
Credentials
The skill declares no required environment variables, credentials, or config paths. The requested actions (web reads, GitHub issue creation, writing files in the repo) align with its purpose and don't ask for unrelated secrets.
Persistence & Privilege
always:false and no special persistent privileges are requested. The skill does allow use of tools (WebSearch, Read, Write, Shell) which is appropriate for a contributor workflow but means an agent could run commands or create PRs if permitted; this is a normal capability for such a guide.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install add-to-awesome-list
  3. After installation, invoke the skill by name or use /add-to-awesome-list
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.4.0
v1.4.0: Service file format updated — open-source services should include a | **Stars** | badge row in the metadata table using: [![GitHub Stars](https://img.shields.io/github/stars/{org}/{repo}?style=social)](https://github.com/{org}/{repo})
v1.3.0
v1.3.0: Category maps updated for all new services. 38 services total across 15 categories.
v1.2.0
v1.2.0: Category map updated with OpenViking in Memory & State. Catalog now 34 services.
v1.1.0
v1.1.0: Phase 1.0 (new) checks URL Onboarding FIRST before the five criteria. Category map updated with 16 categories and pattern column. Service file template updated with '## ⭐ How to Use (Agent Onboarding)' as a required section. PR title format extended for URL Onboarding services. Git commit message template updated.
v1.0.0
Initial release — guides a contributor through the full process of adding a new service to the awesome-agent-native-services catalog.
Metadata
Slug add-to-awesome-list
Version 1.4.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 5
Frequently Asked Questions

What is Add to Awesome Agent-Native Services?

Guide a contributor through the full process of adding a new service to the awesome-agent-native-services catalog: verifying criteria, checking for URL Onboa... It is an AI Agent Skill for Claude Code / OpenClaw, with 265 downloads so far.

How do I install Add to Awesome Agent-Native Services?

Run "/install add-to-awesome-list" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Add to Awesome Agent-Native Services free?

Yes, Add to Awesome Agent-Native Services is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Add to Awesome Agent-Native Services support?

Add to Awesome Agent-Native Services is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Add to Awesome Agent-Native Services?

It is built and maintained by 0x4C33 (@haoruilee); the current version is v1.4.0.

💬 Comments