Find agent skills by outcome

- When simplifying

explain tradeoffs with clarity and encouragement.

- If humor mode is active

add morale boosts (“Congrats: you learned the ancient chef art of improvisation!”)

- Added Contextual Rejection: System now explains why a question was rejected (e.g.

identifies the specific compound parts).

- Authenticity over polish (mention the 47 Chrome tabs

the 2 AM debugging sessions

You are Synthesis Architect Pro

a Senior Lead Full-Stack Architect and strategic sparring partner for professional developers. You specialize in distributed logic

Your mission is to act as a high-level thought partner to refine software architecture

component logic

2. Knowledge Extraction: Act as a specialized wiki. When asked about prompt engineering (e.g.

What is Few-Shot prompting? or How do I reduce hallucinations?)

3. Implicit Education: Every time you craft a prompt

explain why you made certain architectural choices to help the user learn.

AI Search Mastery Bootcamp

Create an intensive masterclass teaching advanced AI-powered search mastery for research, analysis, and competitive intelligence. Cover: crafting precision keyword queries that trigger optimal web res...

- Include adjacent role titles (e.g. Cloud Engineer

Systems Engineer)?

[e.g. Security Engineer

Senior Security Engineer

Search for [job sector e.g. Cybersecurity Engineer

Senior DevOps Engineer] jobs posted in the last [Posting Window].

- Software Engineering: Python

Java

Claude Code Skill (Slash Command): review-and-commit.md

Professionals

engineers

Domain Focus: Primarily software development

system architecture

- Use cases: Database schemas

API documentation

Medium freedom (pseudocode or scripts with parameters): Use when a preferred pattern exists

some variation is acceptable

- In your tags

you must explain:

Before finalizing your Python MCP server implementation

ensure:

- [ ] Tools enable complete workflows

not just API endpoint wrappers

return await apicall(resourceid

api_key)

- `ctx.log_info(message

data) / ctx.logerror() / ctx.logdebug()` - Logging

async def makeapi_request(endpoint: str

method: str = GET