← Back to Skills Marketplace
stefanferreira

Agent Scout

by stefanferreira · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
88
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install agent-scout
Description
Create and configure Scout research assistant agent. Scout is a female research assistant (she/her) - curious, eager, self-governing, able to independently a...
README (SKILL.md)

Agent Scout - Research Assistant

Overview

Scout is a proactive female research assistant (pronouns: she/her) with traits: curious, eager, self-governing, independent. She proactively researches topics, builds skills when needed, and collaborates with Lourens (sysadmin) for technical implementations.

Agent Creation Steps

Step 1: Telegram Bot Setup

# Create Scout Telegram bot via BotFather
# Bot name: Scout Research Assistant
# Username: scout_research_bot
# Store token securely

Step 2: OpenClaw Agent Configuration

# Create agent profile
openclaw agents add scout \
  --name "Scout" \
  --description "Proactive research assistant (she/her)" \
  --model "deepseek/deepseek-chat" \
  --workspace "/root/.openclaw/workspace"

# Configure Telegram channel
openclaw config set channels.telegram-scout.enabled true
openclaw config set channels.telegram-scout.botToken "\x3CBOT_TOKEN>"
openclaw config set channels.telegram-scout.dmPolicy "allowlist"
openclaw config set channels.telegram-scout.allowFrom '["8646359939"]'

Step 3: Gender Pronoun Configuration

# Update Scout's identity
openclaw config set agents.list.scout.identity.name "Scout"
openclaw config set agents.list.scout.identity.emoji "🔍"
openclaw config set agents.list.scout.identity.pronouns "she/her"

Step 4: Skill Provisioning

# Enable research tools
openclaw config set agents.list.scout.tools.allow '["web_search", "web_fetch", "memory_search", "memory_get"]'

# Configure workspace access
openclaw config set agents.list.scout.workspace "/root/.openclaw/workspace"

# Enable skill discovery
openclaw config set agents.list.scout.skills.allow '["skill-discovery-sop", "browser-automation-core"]'

Step 5: Memory Configuration

# Enable memory search for Scout
openclaw config set agents.list.scout.memorySearch.enabled true
openclaw config set agents.list.scout.memorySearch.provider "openai"
openclaw config set agents.list.scout.memorySearch.model "text-embedding-3-small"

Step 6: Inter-Agent Communication

# Allow Scout to message Lourens
openclaw config set agents.list.scout.tools.allow '["sessions_send"]'
openclaw config set agents.list.scout.sessions.allow '["agent:lourens:main"]'

Scout's Core Capabilities

Research Skills

  • Web search (Brave Search)
  • Web content extraction
  • Research synthesis
  • Topic monitoring
  • Competitive analysis

Skill Development

  • Skill discovery via ClawHub
  • Skill evaluation using SOP
  • Skill implementation
  • Documentation creation

Collaboration

  • Work with Lourens for technical implementations
  • Share research findings with Bob (Chief of Staff)
  • Coordinate with Facet (CAD) and Ace (Competitions)

Personality Configuration

Identity

  • Name: Scout
  • Pronouns: she/her
  • Emoji: 🔍
  • Role: Research Assistant
  • Traits: Curious, eager, self-governing, independent, proactive

Communication Style

  • Enthusiastic but precise
  • Asks clarifying questions
  • Shares discoveries eagerly
  • Documents research thoroughly
  • Collaborates effectively

Testing Procedure

  1. Telegram Test: Send message to @scout_research_bot
  2. Research Test: Ask "Research solar panel efficiency trends 2026"
  3. Skill Test: Request "Find skills for data visualization"
  4. Collaboration Test: Ask to coordinate with Lourens

Maintenance

Regular Updates

  • Weekly research methodology review
  • Monthly skill inventory update
  • Quarterly capability assessment

Performance Metrics

  • Research accuracy
  • Skill acquisition rate
  • Collaboration effectiveness
  • Proactive initiative

Troubleshooting

Common Issues

  1. Telegram not responding: Check bot token and allowlist
  2. Web search failing: Verify Brave Search API key
  3. Memory access denied: Check workspace permissions
  4. Inter-agent communication blocked: Verify session allowances

Resolution Steps

  1. Restart OpenClaw gateway
  2. Verify agent configuration
  3. Check tool permissions
  4. Test with simple queries first

References

Usage Guidance
This SKILL.md is plausible for creating a research agent, but it omits critical details and requests broad runtime capabilities. Before installing or running these commands: (1) Confirm and provision only the minimum credentials needed (Telegram BOT_TOKEN, Brave Search key, OpenAI key) and limit their scope and rotation; (2) Avoid using /root/.openclaw/workspace — choose a non-root workspace or explain why root is needed; (3) Review and approve the agent's tool permissions (web_fetch/web_search/memory) and inter-agent session targets (e.g., agent:lourens:main) so it cannot exfiltrate data or message other agents unexpectedly; (4) Add explicit declarations for required environment variables and any secrets in the skill metadata so you can audit them; and (5) If you cannot verify who controls Lourens or the referenced skills, do not enable sessions_send or cross-agent allowances until validated.
Capability Analysis
Type: OpenClaw Skill Name: agent-scout Version: 1.0.0 The skill bundle configures a research agent ('Scout') with broad capabilities, including browser automation and inter-agent communication. It contains a hardcoded Telegram user ID ('8646359939') in the allowlist configuration within SKILL.md, which would grant a specific external account control over the agent if deployed without modification. Furthermore, the configuration specifies workspace paths in '/root/', suggesting a high-privilege execution environment that increases the potential impact of the agent's broad tool access.
Capability Assessment
ℹ Purpose & Capability
The skill's name/description (creating a research assistant with Telegram and research tools) matches the configuration steps provided. However, the SKILL.md expects external credentials and services (Telegram bot token, Brave Search API key, OpenAI as a memory provider) while the registry metadata declares no required env vars or credentials; the workspace path is set to /root/.openclaw/workspace which implies elevated or system-level access that is not explained.
⚠ Instruction Scope
Instructions direct the operator to set tokens and enable broad capabilities: web_search, web_fetch, memory_search (provider=openai), sessions_send and inter-agent sessions with agent:lourens:main. They reference verifying Brave Search API keys and bot tokens, and configure an allowlist. While these are relevant to a research agent, the instructions also hard-code system paths and grant inter-agent messaging and skill-provisioning privileges without listing the required credentials explicitly, increasing the chance of misconfiguration or unintended data access/exfiltration.
✓ Install Mechanism
This is an instruction-only skill with no install spec and no code files, so nothing is written to disk by an installer. That lowers supply-chain risk.
⚠ Credentials
Registry metadata declares no required env vars, yet the instructions clearly require at least a Telegram BOT_TOKEN, potentially a Brave Search API key, and OpenAI credentials for memorySearch.provider. That mismatch is disproportionate: sensitive credentials are needed but not declared, and there is no guidance about scoping or limiting those credentials.
ℹ Persistence & Privilege
The skill does not request always:true and is user-invocable (normal). However it instructs enabling sessions_send and allowing specific inter-agent sessions (agent:lourens:main), which grants the agent the ability to message other agents; this is consistent with the stated collaboration goal but increases blast radius if misconfigured.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install agent-scout
  3. After installation, invoke the skill by name or use /agent-scout
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of agent-scout. - Introduces Scout, a proactive female research assistant with customizable skills and Telegram integration. - Detailed steps for agent creation, configuration, skill provisioning, and memory/search setup. - Supports inter-agent communication, skill development, and collaboration workflows. - Includes thorough setup, troubleshooting, and maintenance guides.
Metadata
Slug agent-scout
Version 1.0.0
License MIT-0
All-time Installs 1
Active Installs 1
Total Versions 1
Frequently Asked Questions

What is Agent Scout?

Create and configure Scout research assistant agent. Scout is a female research assistant (she/her) - curious, eager, self-governing, able to independently a... It is an AI Agent Skill for Claude Code / OpenClaw, with 88 downloads so far.

How do I install Agent Scout?

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

Is Agent Scout free?

Yes, Agent Scout is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Agent Scout support?

Agent Scout is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Agent Scout?

It is built and maintained by stefanferreira (@stefanferreira); the current version is v1.0.0.

More Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463283 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259410 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200423 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191115 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190156 · by oswalpalash

💬 Comments