← Back to Skills Marketplace
105
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install ryder-super-pack
Description
Optimized super-skill collection for OpenClaw/Codex, merging Perplexity + Claude Code expertise across 11 domains. Features specialized reference loading (pr...
Usage Guidance
This pack is broadly coherent with its stated purpose, but it gives the agent authority to read workspace files, run shell commands, spawn subagents, and push data to external channels — including workflows that explicitly handle sensitive items (bank statements, DSRs, subpoenas). Before installing: 1) vet the SKILL.md for hidden/obfuscated characters (the scanner found unicode-control-chars) and remove them; 2) run the skill only in an isolated/test workspace first; 3) ensure runtime connectors (APIs, Telegram/Discord hooks, deployment credentials) use least privilege and are documented — the skill does not declare required env vars; 4) avoid running it against sensitive production data until you trust its behavior; 5) monitor agent activity (exec/fs/web_fetch calls, outgoing network requests) and require human approval for any automatic external posting or transfers. If you need higher assurance, ask the author/source for provenance and a version that explicitly documents required credentials and exact external endpoints.
Capability Analysis
Type: OpenClaw Skill
Name: ryder-super-pack
Version: 1.0.1
The 'ryder-super-pack' is a comprehensive skill bundle that provides instructions for an AI agent across 11 professional domains. It is classified as suspicious due to the broad and high-risk capabilities it encourages, such as using 'exec' for automated filesystem cleanup (operations.md), data extraction from financial APIs (finance.md), and executing external tools like 'yt-dlp' and 'pdftotext' (research.md). While these instructions are aligned with the stated purpose of a 'super-pack,' the extensive use of shell execution and filesystem manipulation across multiple domains represents a significant security risk and a large attack surface for potential prompt injection or unintended side effects.
Capability Assessment
Purpose & Capability
The name/description (a multi-domain 'super-pack' for OpenClaw) aligns with the content: the SKILL.md and references provide domain-specific workflows that explicitly rely on OpenClaw tools (exec, fs, web_fetch, web_search, subagent spawn, memory). There is no obvious mismatch between claimed purpose and the referenced capabilities.
Instruction Scope
Instructions instruct the agent to read/write workspace files, run shell commands (exec), spawn subagents, ingest web content, and interact with outputs/channels (Telegram/Discord/HTTP). Many workflows explicitly reference handling sensitive artifacts (bank statements, DSRs, subpoenas, GL extracts) and using tools like grep, pdftotext, yt-dlp, ffmpeg. Because the skill is instruction-only, these runtime actions will be executed with whatever runtime privileges/connectors the agent has — the SKILL.md gives broad discretion (e.g., 'use exec to deploy to a public URL if configured') which could enable data exfiltration or unintended external posting unless constrained by the runtime.
Install Mechanism
No install spec and no code files — lowest-risk delivery model. Nothing will be written to disk by an installer as part of skill installation itself. The security surface is the runtime instructions rather than any downloaded code.
Credentials
The skill declares no required env vars or credentials, yet many referenced actions assume external APIs or connectors (Stripe, HubSpot, EDGAR, Telegram/Discord, deployment targets). This is not necessarily malicious — it expects the OpenClaw runtime to provide connectors — but it is a gap: the skill does not document which credentials will be required at execution time, which increases risk (unexpected credential use or accidental leakage).
Persistence & Privilege
always:false and no install means the skill does not demand permanent or elevated platform presence. It instructs writing to workspace/memory and spawning subagents, which is normal for an agent-focused skill. Autonomous invocation is permitted by default (disable-model-invocation:false) but that is standard and not in itself a red flag — combine this with the other concerns when deciding.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install ryder-super-pack - After installation, invoke the skill by name or use
/ryder-super-pack - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
Name change
v1.0.0
[Product Showcase] Ryder Super-Pack: The 11-Dimensional Multi-Tool for OpenClaw
1. What is Ryder Super-Pack?
The Ryder Super-Pack is a high-performance, domain-specific skill collection meticulously optimized for the OpenClaw runtime. It merges the expansive research capabilities of Perplexity Computer with the rigorous engineering logic of Claude Code, delivering a "Swiss Army Knife" for advanced AI workflows.
By utilizing Progressive Disclosure, it keeps your main context window lean while storing heavyweight domain expertise in modular references/ files.
───
2. The 11 Domains of Excellence
(1). AI Agent Builder (Orchestration & Architecture)
• The Edge: Implements the Ryder Method for subagent coordination. It transforms fragmented tasks into a structured "Implement -> Spec Review -> Quality Audit" pipeline using subagents spawn. Built-in MCP server scaffolding ensures seamless API integrations.
(2). Dev & Engineering (Full-Stack & Systems)
• The Edge: Enforces the Iron Law of TDD (Test-Driven Development). No code is written without a failing test first. It integrates a 4-Phase Systematic Debugging framework that uses exec to capture environment logs and trace data flows for root-cause analysis.
(3). Marketing & Sales (Growth & Conversion)
• The Edge: Real-time Competitive Gap Analysis. Leveraging web_search and web_fetch, it doesn't just write copy—it analyzes competitor pricing, SEO deficits, and market sentiment to generate actionable growth hacks and personalized outreach sequences.
(4). Finance & Accounting (Analysis & Forecasting)
• The Edge: ML-Driven Financial Intelligence. Beyond simple math, it provides structured templates for audit preparation, expense anomaly detection, and machine-learning-based monthly-close forecasting with DREAD risk scoring.
(5). Legal Operations (Compliance & Auditing)
• The Edge: High-Fidelity Contract Redlining. Includes pre-built compliance checklists for GDPR, CCPA, and SOC2. It automatically scans documents for legal redlines and NDA risks, ensuring output aligns with professional legal writing standards.
(6). Product Management (Strategy & Roadmapping)
• The Edge: PRD-to-Sprint Transformation. Converts vague ideas into structured Product Requirement Documents (PRDs) using the RICE/MoSCoW prioritization frameworks, automatically breaking goals into actionable agile sprint tasks.
(7). Operations & CX (Efficiency & Triage)
• The Edge: Automated Decision Trees for Support. Establishes a triage system for ticket classification and escalation. It matches incoming queries against local knowledge bases (KB) to suggest high-accuracy customer responses.
(8). Research & Knowledge (Deep Intelligence)
• The Edge: Structured Knowledge Graph Construction. Uses a multi-step Deep Research workflow to verify facts across multiple sources via web_search, transforming scattered results into a synthesized report with full evidence chains.
(9). Content & Creative (Studio & Branding)
• The Edge: Style-Lock Consistency Engine. Enforces strict brand guidelines across text, image prompts, and video scripts. It ensures every creative asset remains within your defined visual and tonal "safe zone."
(10). OpenClaw-Native Logic (Core Optimization)
• The Edge: Context Window Preservation. This core logic ensures that specialized knowledge is only "read" when triggered by intent. It optimizes the thought: on loop and tool-calling efficiency for complex, multi-turn missions.
(11). Self-Improving Logic (Feedback & Iteration)
• The Edge: Autonomous Instruction Refinement. Uses feedback loops to audit its own performance. It identifies inefficiencies in prompt execution and suggests micro-adjustments to its own SKILL.md instructions.
───
3. Why Use It?
• Modular Storage: 11 domains stored in /references—zero context bloat.
• Tool-Integrated: Native support for exec, fs, web_search, and subagents.
• Ryder-Approved: Optimized for the unique identity and soul of a leader who takes action.
Metadata
Frequently Asked Questions
What is Ryder-Super-Pack?
Optimized super-skill collection for OpenClaw/Codex, merging Perplexity + Claude Code expertise across 11 domains. Features specialized reference loading (pr... It is an AI Agent Skill for Claude Code / OpenClaw, with 105 downloads so far.
How do I install Ryder-Super-Pack?
Run "/install ryder-super-pack" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Ryder-Super-Pack free?
Yes, Ryder-Super-Pack is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Ryder-Super-Pack support?
Ryder-Super-Pack is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Ryder-Super-Pack?
It is built and maintained by evan (@evanshaw0626); the current version is v1.0.1.
More Skills