Browse The Skill Store

Peer Review Stress Test

by PubsProToolkit

$12

An adversarial self-review gate that hunts your agent's weakest claim, overclaims, and missing limitations before a human sees the output.

Evidence Guard

by PubsProToolkit

$14

Audit any AI-generated output for unsupported claims, then verify every factual and technical assertion against its real source before it ships.

LLM Eval Framework Builder

by Arnstein Larsen

$17

You changed the prompt, tried four inputs, it looked better, you shipped — and three days later support tickets say outputs are worse for an entire class of inputs you didn't test

Battle-tested prompting patterns to eliminate LLM output drift. Sandwich structure, few-shot examples, history limits, retry, and token caps — 6 composable layers for production-grade agent reliability.

Prompt Injection & Agent Security Gate

by PubsProToolkit

$14

An adversarial security gate that audits untrusted content — web pages, tool outputs, documents, emails — for embedded instructions, exfiltration, and authority spoofing, then returns a SAFE/REVIEW/BLOCK verdict.

Subagent Workflow Patterns To Boost Output Quality

by zoninmane

$9

Deploy 6 battle-tested multi-agent orchestration patterns to eliminate agent laziness and boost output quality.

AI Agent QA & Failure Testing Specialist

by Shandra

$15

Tests AI agents, prompts, and agent skills against edge cases, unsafe behavior, output failures, permission risks, escalation gaps, memory leaks, and marketplace-quality weaknesses.

Agent Harness Architect

by PubsProToolkit

$14

Model quality is table stakes — the harness is where agents win or fail. This designs yours: it writes a structured, testable system prompt (role, tools, boundaries, method, output contract, failure handling) and maps every concern to the right layer — prompt, tool, guardrail, or evaluation — so the pieces reinforce each other instead of fighting.

Battle-tested prompting patterns to eliminate LLM output drift. Sandwich structure, few-shot examples, history limits, retry, and token caps — 6 composable layers for production-grade agent reliability.

Battle-tested prompting patterns to eliminate LLM output drift. Sandwich structure, few-shot examples, history limits, retry, and token caps — 6 composable layers for production-grade agent reliability.

ai code review strategist

by Timoranjes

$10

Teaches AI coding agents to perform structured, high-signal code reviews specifically for AI-generated code — catching the failure modes unique to LLM output (confident hallucinations, silent error sw