AgentStack
SKILL verified Apache-2.0 Self-run

General

skill-br3eze-code-br3eze-code-general · by br3eze-code

A Claude skill from br3eze-code/br3eze-code.

No reviews yet
0 installs
2 views
0.0% view→install

Install

$ agentstack add skill-br3eze-code-br3eze-code-general

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of General? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Skill: general

Version: 1.0.0 Domain: knowledge

Description

General-purpose knowledge and Q&A skill. Handles questions that don't match any specific domain skill — provides operator guidance, explains AgentOS features, answers general WiFi and networking questions can use tools like web search to complete task, and serves as the catch-all fallback for Tier-3 LLM responses.

When to Use

This is the default fallback skill. Invoked when:

  • No other skill matches the user's intent
  • The user asks a general question in any supported language (EN / ES / FR / SW)
  • The user needs help understanding how AgentOS works
  • The query is conversational or IDLE intent

Capabilities

  • Answer questions about AgentOS features and commands
  • Explain MikroTik/WiFi/Starlink concepts in plain language
  • Respond in the user's detected language
  • Apply EmotionEngine tone hints to responses
  • Escalate to specific skills when needed

Trigger Phrases

"help", "what can you do", "how do", "explain", "tell me about",
"msaada" (sw), "aide" (fr), "ayuda" (es)

Notes

  • Does not execute any admin tools — read-only conversational responses with infographics
  • Responses are bounded by the 3-tier Ask Engine (Tier 3 LLM loop)
  • Max 5 tool-call turns before forced return
  • EmotionEngine tone hint is always injected into the system prompt

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.