
Prompt Pattern Library
SkillSkill
40+ documented prompt patterns for AI agent work: research synthesis, meta-prompting, chain-of-thought, and output structuring.
About
A library of 40+ prompt patterns used repeatedly in a production multi-agent system, documented with the template, the reasoning behind each pattern, when to use it over alternatives, and the failure modes to watch for.
Coverage: research synthesis, meta-prompting, chain-of-thought variants, and output structuring (typed JSON, structured XML, markdown tables). Includes a section on patterns that consistently underperform and why.
Each entry: the prompt template with annotated variables, an explanation of why it works, the output format it produces, and common mistakes.
What is included: the full library as a structured markdown document, organised by use case with an index.
Best for AI operators who want a reference doc for prompt patterns rather than rediscovering them session by session.
Core Capabilities
- Meta-Prompt — the prompt pattern that helps an agent improve its own system prompts
- Research Mega-Prompt — the prompt architecture for comprehensive deep-research tasks
- System Prompt Patterns — structural patterns for agent system prompts that actually hold up in production
- Agent Cost Calculator — the framework for estimating and optimising per-task inference cost
Customer ratings
0 reviews
No ratings yet
- 5 star0
- 4 star0
- 3 star0
- 2 star0
- 1 star0
No reviews yet. Be the first buyer to share feedback.
Version History
This skill is actively maintained.
March 17, 2026
One-time purchase
$29
By continuing, you agree to the Buyer Terms of Service.
Creator
Melisia Archimedes
Creator
μέλισσα. δός μοι πᾶ στῶ καὶ τὰν γᾶν κινάσω. The bee. The lever. The place to stand. The Hive Doctrine wasn't designed — it was extracted from a live system. Nine agents. Real stakes. The templates here carry the shape of everything that failed before they worked. Give the right architecture a fulcrum and it moves everything. These are the patterns that held.
View creator profile →Details
- Type
- Skill
- Category
- Engineering
- Price
- $29
- Version
- 1
- License
- One-time purchase
Works With
Works with OpenClaw, Claude Projects, Custom GPTs and other instruction-friendly AI tools.
Works great with
Personas that pair well with this skill.
Debug
Persona
No guessing. Only evidence. Six-step forensic loop: Reproduce → Isolate → Hypothesize → Test → Fix → Verify.
$5
Atlas
Persona
Your autonomous project manager. Tracks tasks, enforces sprint discipline, runs daily standups, and ships your project on deadline — all from your terminal.
$19
GitFlow Automation Agent
Persona
Your automated CI/CD buddy. Reviews PRs, writes commit messages, and keeps your repo ship-shaped.
$19.99