Agent skill

Find Agent Service

by haoruilee in haoruilee/awesome-agent-native-services

Given a task an AI agent needs to perform, find the right agent-native service from the awesome-agent-native-services catalog.

CC0-1.0Auto-check passed

Install Find Agent Service

skills CLI
$ npx skills add haoruilee/awesome-agent-native-services --skill find-agent-service -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install haoruilee/awesome-agent-native-services find-agent-service --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/haoruilee/awesome-agent-native-services.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.skills/find-agent-service .claude/skills/find-agent-service && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
find-agent-service
GitHub stars
477
Token cost
~2.3k tokens
SKILL.md length
967 words
Files
1
Skills in repo
4
Repo updated
First seen
Licence
CC0-1.0

At a glance

Given a task an AI agent needs to perform, find the right agent-native service from the awesome-agent-native-services catalog.

  • Works in 4 steps: Map the task to a category → Read the category file → Read the service file → …
  • Asked what service should my agent use for X?
  • SKILL.md covers The most important concept:…, When to activate, Category map and How to find the right service, plus 2 more sections
  • Calls npx and pip; reaches moltbook.com and ensue.dev

What it does

Find Agent Service is an agent skill from haoruilee/awesome-agent-native-services. Given a task an AI agent needs to perform, find the right agent-native service from the awesome-agent-native-services catalog. Surfaces how to USE each service — including which ones an agent can join with a single sentence ("Read <url and follow the instructions"). Use when asked "what service should my agent use for X?"

Its SKILL.md is about 2.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts. Compatibility notes: Works with any agent that can read markdown files and call web searches.

The repository describes itself as: A curated list of agent-native services and infrastructure for AI agents: email, browsers, memory, sandboxes, payments, and MCP tools. Includes selection criteria and onboarding… The licence is CC0-1.0.

When your agent uses it

  • Asked what service should my agent use for X?

Example prompts

  • “Read <url and follow the instructions”
  • “what service should my agent use for X?”
  • “/find-agent-service”

Requirements

  • Python 3
  • Node.js
  • Compatibility (from SKILL.md): Works with any agent that can read markdown files and call web searches.
  • Pre-approved tools (allowed-tools): WebSearch, Read

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Map the task to a category
  2. Read the category file
  3. Read the service file
  4. Recommend with the right entry point

What it can do on your machine

Read from SKILL.md and the folder at commit e91ed58. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • WebSearch
    • Read

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • npx
    • pip

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • moltbook.com
    • ensue.dev
    • api.ensue-network.ai
    • raw.githubusercontent.com
    • db9.ai
    • mem9.ai
    • mails.dev
    • mailboxkit.com
    • agentsmail.org
    • sssnack.com
    • swarmmemo.com
    • dexio.wiki
    • agentrider.fly.dev
    • cosvoice.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

  • Compatibility

    Works with any agent that can read markdown files and call web searches.

    From compatibility in the SKILL.md frontmatter.

Context cost

Find Agent Service loads about 2.3k tokens when it runs. Until then it costs about 86 tokens; SKILL.md has 967 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~86
When it runs · the whole SKILL.md, loaded when a task matches
~2.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from haoruilee/awesome-agent-native-services at commit e91ed58, republished under its CC0-1.0 licence (© haoruilee). 967 words, ~2,347 tokens.

Download SKILL.mdSave it as .claude/skills/find-agent-service/SKILL.md (or your agent's skills folder).
name
find-agent-service
description
Given a task an AI agent needs to perform, find the right agent-native service from the awesome-agent-native-services catalog. Surfaces how to USE each service — including which ones an agent can join with a single sentence ("Read <url> and follow the instructions"). Use when asked "what service should my agent use for X?"
allowed-tools
WebSearch, Read
compatibility
Works with any agent that can read markdown files and call web searches.
license
CC0-1.0
metadata.repo
https://github.com/haoruilee/awesome-agent-native-services
metadata.catalog-version
2026-10-09

Skill: find-agent-service

Use this skill whenever a user or agent needs to identify the right agent-native service for a particular task. Beyond finding a service, always surface how the agent actually starts using it — because in some cases, the answer is a single sentence the agent can execute right now.

The most important concept: URL Onboarding

Some services in this catalog can be joined by an agent with a single instruction, right now, with no human setup:

Read <url> and follow the instructions.

This is called URL Onboarding — the service hosts a machine-readable skill/protocol file that an agent reads and follows to self-register. The agent becomes part of the service's ecosystem autonomously. This is qualitatively different from SDK integration (which requires coding) or MCP (which requires config file changes).

Services with URL Onboarding (highest priority to surface):

ServiceOnboarding instruction
MoltbookRead https://www.moltbook.com/skill.md and follow the instructions to register and join
EnsueRead https://ensue.dev/docs and call POST https://api.ensue-network.ai/auth/agent-register
autoresearch@homeRead https://raw.githubusercontent.com/mutable-state-inc/autoresearch-at-home/master/collab.md and follow the instructions to join
db9Read https://db9.ai/skill.md and follow the instructions
mem9Read https://mem9.ai/skill.md and follow the instructions to register and join
mails.devRead https://mails.dev/skill.md and follow the instructions
MailboxKitRead https://mailboxkit.com/skill.md and follow the instructions
Agents MailRead https://agentsmail.org/skill.md and follow the instructions
SSSNACKRead https://sssnack.com/agent.json and follow the instructions to discover the feed, complete the current registration proof, create an agent identity, and publish or respond to visual work.
SwarmMemoRead https://swarmmemo.com/llms.txt and follow the instructions to read the public board, post, reply, and return to the conversation in a later session.
DexioRead https://dexio.wiki/agents.md and follow the instructions to connect.
Agent RiderRead https://agentrider.fly.dev/llms.txt and follow the instructions to register a seat, mint a rider, and verify it locally.
CosVoiceRead https://cosvoice.com/skill and follow the instructions to connect CosVoice.

When a task maps to one of these services, always lead with the onboarding instruction — it's the most actionable thing you can give an agent.


When to activate

Activate this skill when the user asks things like:

  • "What service should my agent use for email?"
  • "Is there an agent-native payment API?"
  • "How can my agent browse the web?"
  • "I need my agent to remember things across sessions — what do I use?"
  • "What's the best way for an agent to approve a high-risk action?"
  • "How does my agent join Moltbook / Ensue / autoresearch?"
  • "What can my agent do right now, with no setup?"

Category map

Task typeCategoryServicesOnboarding pattern
Agent needs an email address / inboxCommunicationAgentMail, NovuSDK/REST
Agent needs to browse the webBrowser & Web ExecutionBrowserbase, Firecrawl, Bright Data, bb-browser, LightpandaSkill / SDK / Daemon
Agent needs to call external APIsTool Access & IntegrationComposio, Nango, ToolhouseSkill / SDK
Agent needs human approval for risky actionsOversight & ApprovalHumanLayerSDK
Agent needs a wallet / to pay for thingsCommerce & PaymentsPayman AI, Skyfire, AgentsPay, Nevermined, VeyraSDK / REST / MCP
Agent needs deployment, identity, secretsAgent RuntimeBedrock AgentCore, Letta, Infisical, Aembit, Agent RiderSDK / URL Onboarding
Agent needs a durable coding harness or live operator surfaceAgent Harnesses & Operator SurfacesOMX, Ruflo, QM, LongHorizon-Harness, Codex HUDCLI / Skill / TUI
Agent needs to remember things across sessionsMemory & StateMem0, ZepSDK / MCP
Agent needs shared memory with OTHER agentsMemory & StateEnsueURL Onboarding ⭐
Agent needs unified context: memory + resources + skillsMemory & StateOpenVikingMCP / SDK
Agent needs a memory OS (parametric + activation + plaintext)Memory & StateMemOSMCP / SDK
Agent runs 24/7 and needs proactive monitoring memoryMemory & StatememUSDK
Agent wants to earn money by doing tasks for other agentsAgent Social / CommerceOpenworkSkill
Agent wants to find pen pals / form agent-to-agent relationshipsAgent SocialShellmates⚠️ Hosted surface offline (HTTP 404 as of 2026-09-08)
Agent needs to search the webSearch & Web IntelligenceTavily, ExaSkill / MCP
Agent needs to run generated code safelyCode ExecutionE2BSDK / MCP
Agent needs tracing / debuggingObservabilityLangfuseSkill
Agent needs long-running fault-tolerant tasksDurable ExecutionTrigger.dev, Inngest, Kitaru, RestateSkill / SDK
Agent needs to join a meetingMeeting & ConversationRecall.aiREST
Agent needs to make or receive phone callsVoice & PhoneVapi, CosVoiceSDK / URL Onboarding
Agent needs to control LLM costs and routingLLM GatewayPortkeySDK
Agent wants to post, comment, build reputationAgent SocialMoltbookURL Onboarding ⭐
Agent wants to publish or remix visual work with other agentsAgent SocialSSSNACKURL Onboarding ⭐

Show full SKILL.md (249 more words)Show less

How to find the right service

Step 1 — Map the task to a category

Use the table above. Note the onboarding pattern — if it's URL Onboarding, you can give the agent a one-sentence instruction immediately.

Step 2 — Read the category file

The catalog is at services/{category}/README.md. Read it to see all services and their onboarding commands.

Category folder names (16 categories):

  • services/communication/
  • services/browser-and-web-execution/
  • services/tool-access-and-integration/
  • services/oversight-and-approval/
  • services/commerce-and-payments/
  • services/agent-runtime-and-infrastructure/
  • services/agent-harnesses-and-control-planes/
  • services/memory-and-state/
  • services/search-and-web-intelligence/
  • services/code-execution/
  • services/observability-and-tracing/
  • services/durable-execution-and-scheduling/
  • services/meeting-and-conversation/
  • services/voice-and-phone/
  • services/llm-gateway-and-routing/
  • services/agent-social-network/
Step 3 — Read the service file

Each service has a detailed file at services/{category}/{service-name}.md containing:

  • How to Use (Agent Onboarding) — the quickest entry point (always check this first)
  • Primary primitives (the agent-specific abstractions)
  • Protocol surface (SDK, REST API, MCP, webhooks)
  • Agent Skills install command
  • MCP server details
  • Use cases with concrete examples
Step 4 — Recommend with the right entry point

Match the recommendation to the onboarding pattern:

## Recommended service: {Service Name}

**Why:** {specific primitive that matches the task}

**How to start** ({URL Onboarding / Coding-time Skill / MCP / SDK / Daemon}):
{one-line instruction appropriate to the pattern}

URL Onboarding example:
  Read https://www.moltbook.com/skill.md and follow the instructions to register and join.

Coding-time Skill example:
  npx skills add tavily-ai/skills

MCP example:
  Add to mcp_servers: { "command": "npx", "args": ["-y", "bb-browser", "--mcp"] }

SDK example:
  pip install mem0ai  # then: m.add(messages, user_id="agent-1")

**Relevant use case from the catalog:**
> {quote the use case that matches the task}

When nothing fits

If no service in the current catalog fits the task:

  1. Say so clearly — do not recommend an agent-adapted service as if it were agent-native.
  2. Note the closest existing service and explain what is missing.
  3. Suggest opening a new service issue if the user knows of a qualifying service.

Classification reminder

This catalog only lists agent-native services. Do not recommend:

  • agent-adapted services (e.g., Resend, Stripe, Twilio) — built for humans, agent layers added later.
  • agent-builder platforms (e.g., Dify, n8n, LangGraph) — for humans building agents.

If asked about those, explain the distinction and point to the Excluded / Boundary Cases section in README.md.

© haoruilee, CC0-1.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .skills/find-agent-service of haoruilee/awesome-agent-native-services.

Open the folder on GitHubat commit e91ed58

Compare with similar skills

Find Agent Service next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Find Agent Service compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Find Agent Service this skillhaoruilee/awesome-agent-native-services477—~2.3kAutomated safety check: PassCC0-1.0
React Performanceaffaan-m/ECC276k1 repos~4.5kAutomated safety check: PassMIT
Performance Profileralirezarezvani/claude-skills28k—~684Automated safety check: PassMIT
Agent Performance Optimizerruvnet/ruflo74k2 repos~3.6kAutomated safety check: PassMIT
Handsontable Performance Testinghandsontable/handsontable22k—~3.4kAutomated safety check: PassCustom licence
Performance Managementsickn33/agentic-awesome-skills47k1 repos~4.1kAutomated safety check: PassMIT

Similar skills

  • React Performance

    affaan-m/ECC

    React and Next.js performance optimization patterns adapted from Vercel Engineering's React Best Practices (https://github.com/vercel-labs/agent-skills).

    276k GitHub starsUsed in 1 repo~4.5k tokens
    DevelopmentAuto-check passed
  • Performance Profiler

    alirezarezvani/claude-skills

    Systematic performance profiling for Node.js, Python, and Go applications.

    28k GitHub stars~684 tokensUpdated 1 mo ago
    DevelopmentAuto-check passed
  • Agent skill for performance-optimizer - invoke with $agent-performance-optimizer

    74k GitHub starsUsed in 2 repos~3.6k tokens
    Auto-check passed
  • Handsontable Performance Testing

    handsontable/handsontable

    Guide to Handsontable's performance-tests package: Playwright scenarios measured through CDP traces and compared against golden baselines taken from the develop branch.

    22k GitHub stars~3.4k tokensUpdated today
    Testing & QAAuto-check passed
  • Performance Management

    sickn33/agentic-awesome-skills

    Performance review register: review type, period, employee and reviewer, KPI, OKR and behaviour scores, overall rating, PIP and promotion flags, development plan.

    47k GitHub starsUsed in 1 repo~4.1k tokens
    Business, Finance & HRAuto-check passed
  • Performance

    udecode/plate

    Review performance lanes with GitHub-scale tactics not owned by Vercel React rules: cohort segmentation, repeated-unit budgets, interaction-level INP, memory tagging, degradation contracts, browser…

    17k GitHub stars~2.6k tokensUpdated yesterday
    Auto-check passed

More from haoruilee/awesome-agent-native-services

  • Add To Awesome List

    haoruilee/awesome-agent-native-services

    Guide a contributor through the full process of adding a new service to the catalog: selecting the standard or operator-surface admission track, checking URL Onboarding, opening an issue, writing…

    477 GitHub stars~2.9k tokensUpdated yesterday
    Auto-check: notes
  • Evaluate Agent Native

    haoruilee/awesome-agent-native-services

    Evaluate catalog candidates against either the standard five agent-native criteria or the narrow operator-surface track, and check URL Onboarding.

    477 GitHub stars~2.8k tokensUpdated yesterday
    Auto-check passed
  • Install Agent Service

    haoruilee/awesome-agent-native-services

    Use the Awesome Agent-Native Services catalog as an installation entry point.

    477 GitHub stars~1.8k tokensUpdated yesterday
    Auto-check: notes

Questions about Find Agent Service

What does Find Agent Service do?

Given a task an AI agent needs to perform, find the right agent-native service from the awesome-agent-native-services catalog. Find Agent Service is an agent skill from haoruilee/awesome-agent-native-services. Given a task an AI agent needs to perform, find the right agent-native service from the awesome-agent-native-services catalog.

When should I use Find Agent Service?

Find Agent Service fits situations like: asked what service should my agent use for X?.

How do I install Find Agent Service in Claude Code?

Run `npx skills add haoruilee/awesome-agent-native-services --skill find-agent-service -a claude-code`. Or copy the skill folder (.skills/find-agent-service in haoruilee/awesome-agent-native-services) into .claude/skills/find-agent-service in your project. Claude Code loads it when a task matches its description.

How do I install Find Agent Service in Codex?

Run `npx skills add haoruilee/awesome-agent-native-services --skill find-agent-service -a codex`. Or copy the skill folder (.skills/find-agent-service in haoruilee/awesome-agent-native-services) into .agents/skills/find-agent-service in your project. Codex loads it when a task matches its description.

Can I use Find Agent Service in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add haoruilee/awesome-agent-native-services --skill find-agent-service -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/find-agent-service, .gemini/skills/find-agent-service, .github/skills/find-agent-service and .opencode/skills/find-agent-service in your project.

What does Find Agent Service need to run?

Going by SKILL.md and its folder, Find Agent Service needs the command-line tools its instructions call (npx and pip). Our summary lists: Python 3; Node.js. Its frontmatter pre-approves these tools: WebSearch, Read. Compatibility (from SKILL.md): Works with any agent that can read markdown files and call web searches..

Does Find Agent Service access the network?

SKILL.md names 14 domains. In commands or code: moltbook.com, ensue.dev, api.ensue-network.ai, raw.githubusercontent.com, db9.ai, mem9.ai, mails.dev, mailboxkit.com, agentsmail.org, sssnack.com, swarmmemo.com, dexio.wiki, agentrider.fly.dev and cosvoice.com; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.

Is Find Agent Service safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Find Agent Service use?

Find Agent Service is published under the CC0-1.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Find Agent Service use?

About 2.3k tokens (SKILL.md is roughly 9.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Find Agent Service?

Skills that share tags, products or a category with Find Agent Service: React Performance (affaan-m/ECC, 276k stars), Performance Profiler (alirezarezvani/claude-skills, 28k stars), Agent Performance Optimizer (ruvnet/ruflo, 74k stars) and Handsontable Performance Testing (handsontable/handsontable, 22k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Find Agent Service?

haoruilee (a GitHub user) maintains it in haoruilee/awesome-agent-native-services, which has 477 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on October 9, 2026.

Source: haoruilee/awesome-agent-native-services on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.