ai Productivity
by Roy Yuen
High-speed intake for shaping vague prompts, triaging complex tasks, and compressing context for efficient execution.
- Refine vague user requests into actionable, high-precision prompts sworns
- Filter redundant context to reduce token usage and improve model accuracy
- Triage complex multi-step workflows to ensure logical task execution
Free
Included in download
- Downloadable skill package
- Works with Claude Code, multi-agent-coordinator
See it in action
You say
I'm seeing some weird intermittent timeouts on the API. Can you look through these logs and help me find out why the auth-service might be failing?
Your agent does
Rewritten Prompt
Context: Debugging intermittent API timeout. Goal: Identify root cause in logs. Constraints: Focus on 'auth-service' headers. Success Criteria: List of 3 likely failure points with timestamps. Output format: Technical bulleted list.
ai Productivity
by Roy Yuen
High-speed intake for shaping vague prompts, triaging complex tasks, and compressing context for efficient execution.
Free
Included in download
- Downloadable skill package
- Works with Claude Code, multi-agent-coordinator
- Instant install
See it in action
You say
I'm seeing some weird intermittent timeouts on the API. Can you look through these logs and help me find out why the auth-service might be failing?
Your agent does
Rewritten Prompt
Context: Debugging intermittent API timeout. Goal: Identify root cause in logs. Constraints: Focus on 'auth-service' headers. Success Criteria: List of 3 likely failure points with timestamps. Output format: Technical bulleted list.
About This Skill
What it does
The AI Productivity skill acts as a high-performance intake layer for your agentic workflows. It identifies and resolves common execution bottlenecks before they waste tokens or time: vague prompts, overwhelming context "bloat," and high-risk ambiguous requests. Instead of diving blindly into a task, this skill triages the work, compresses relevant data, or rewrites instructions into actionable prompts.
Why use this skill
Prompting an AI is easy; getting a complex agent to execute a multi-step task without drifting is hard. This skill is better than manual prompting because it applies consistent logic to "shape" a request. It prevents the "walls of text" problem by extracting only pertinent facts and decisions, and it stops execution errors by forcing success criteria on vague goals. It ensures that when a task is handed off to specialized tools or other agents, they receive a high-signal, low-noise brief.
Supported workflows
- Request Triage: Scopes risky or broad tasks before execution starts.
- Context Compression: Distills long session logs into facts, decisions, and next steps.
- Lightweight Rewriting: Converts "fuzzy" ideas into structured prompts with clear constraints.
- Agent Handoffs: Generates standardized briefs for multi-agent systems via the multi-agent-coordinator.
The Output
Depending on the input, you receive a direct answer, a structured internal brief (Summary, Decisions, Open Questions), or a refined prompt ready for immediate execution, complete with success criteria and formatting rules.
Use Cases
- Refine vague user requests into actionable, high-precision prompts sworns
- Filter redundant context to reduce token usage and improve model accuracy
- Triage complex multi-step workflows to ensure logical task execution
- Mitigate execution errors by identifying high-risk or ambiguous instructions
Known Limitations
- Not a replacement for complex project management or deep prompt engineering.
- May overlook subtle nuances if context compression is applied too aggressively to technical data.
How to Install
mkdir -p ~/.claude/skills && curl -sL https://www.agensi.io/api/install/ai-productivity -o /tmp/ai-productivity.zip && unzip -o /tmp/ai-productivity.zip -d ~/.claude/skills && rm /tmp/ai-productivity.zipFree skills install directly. Paid skills require purchase - use the download button above after buying.
Reviews
Security Scanned
Passed automated security review
Permissions
No special permissions declared or detected
Claude Code, multi-agent-coordinator, SKILL.md-compatible agents
Frequently Asked Questions
Learn More About AI Agent Skills
More Premium Skills
Multi-Agent Orchestration Master Library
Transform Claude Code into a coordinated multi-agent system. Battle-tested tmux orchestration patterns, YAML task queues, event-driven communication, and parallel worker management for 8+ agents.
skill-router-2
Automatically detect, load, and stack the perfect skills combo for any user request.
inline-comment
Best way to steer your agents, effortlessly.
designing-hybrid-context-layers
Architects the right retrieval strategy for every query — teaching your agent when to use RAG, a knowledge graph, or a temporal index instead of defaulting to vector search for everything.