Prompt Dataset Builder
by Edric Vale
$9.9
Build and curate high-quality prompt datasets for fine-tuning and eval — deduped and labeled.
11
1621.0(1)
Claude Skills for Testing & Debugging
Skills for unit tests, integration tests, end-to-end suites, and systematic debugging. Improve coverage, catch regressions, and find root causes fast.
1,518 live testing & debugging skills for Claude Code.
New in Testing & Debugging
api contract tester
by Samuel Rose
$5
Turn OpenAPI specs into exhaustive, framework-ready test suites covering happy paths, edge cases, and security gaps.
5
2
opencode coding
by Roy Yuen
$5
Enforce senior-level coding standards with a focus on verification, minimal diffs, and evidence-based bug fixing.
4
0
codex grade coding
by Roy Yuen
Free
Turn your AI agent into a senior engineer with strict task classification and verification-driven coding protocols.
4
3234.7(3)
env doctor
by Samuel Rose
Free
Diagnoses why your project will not start. Checks runtime versions, dependencies, environment variables, databases, ports, and build artifacts systematically.
5
2565.0(1)
truth first
by Roy Yuen
Free
Eliminate hallucinations with an evidence-first verification framework for system state, configs, and file contents.
3
1825.0(3)
lobster debugging
by 王晓菲
Free
A systematic 4-phase debugging framework to find root causes, eliminate flaky tests, and prevent regressions.
4
55
diagnosing rag failure modes
by loreto
$10
RAG fails quietly. It retrieves documents, returns confident-looking answers, and misses the question entirely — because the question required connecting facts across documents, reasoning about sequence, or tracing causation. This skill gives you a five-question diagnostic checklist that classifies any failing query as either RAG-safe or structurally RAG-incompatible, then maps it to the specific failure pattern and the architectural fix that resolves it.
5
55.0(1)
Multi Agent Coordinator
by Roy Yuen
$7
Coordinate specialized AI agent roles for complex planning, implementation, and verification workflows.
4
1
AI Coding Prompt Refiner for Better Developer Results
by Shandra
$19.99
Transforms vague coding requests into precise, scoped, testable, AI-ready prompts for Cursor, Claude Code, Codex CLI, Replit, and other coding agents.
6
12
robot to playwright converter
by Matthew King
Free
Most 'migrations' rewrite your tests from scratch. This one maps your existing keywords and locators automatically.
1
8
rag architect
by Roy Yuen
$5
Design, debug, and optimize production RAG systems with expert architecture, hybrid search, and grounding strategies.
2
0
bypass macos file dialog
$5
Bypass OS-native file upload dialogs in browser automation using JavaScript interception and DataTransfer injection.
1
0
coding plus
by Roy Yuen
$5
Upgrade your AI agent with a senior-level engineering SOP focused on inspection, minimal diffs, and hard verification.
2
0
Flaky Test Detective for AI Coding Agents
by Shandra
$9.99/mo
Diagnoses unreliable tests, identifies root causes, creates stabilization plans, and generates safe AI coding prompts for fixing flaky unit, integration, E2E, and CI tests.
6
2
prod bug hunter
by Shippers
Free
Systematic runtime bug detection and automated patching for Firebase, Next.js, and Vercel stacks.
4
204.0(1)
test gen
by Kevin Cline
$12
Automated test generation with edge case analysis and framework-native syntax for TS, Python, Go, and Rust.
2
0
instruction layer auditor
by Roy Yuen
Free
Audit and de-conflict complex agent instruction stacks to fix inconsistent behavior and logic bloat.
2
27
agent regression guard
by Rian O'Leary
$5
Automated risk classification and regression checking to stop AI agents from breaking your codebase.
2
0
Git History Archaeologist
by Edric Vale
$5
Excavate git history: blame forensics, reverted-change recovery, and commit narrative reconstruction.
13
895.0(1)
Windows Desktop Automation Architect for AI Coding Agents
by Shandra
$9.99
Designs robust Windows desktop automation workflows using pywinauto, UI Automation, hotkeys, image matching, OCR, retries, logging, screenshots, and safety controls.
2
0
finalize
by Alex Shi
$5
The ultimate pre-commit checklist agent for cleaning code, updating docs, and validating repository state.
2
0
ai trace runner
by Roy Yuen
$5
Transform ambiguous AI tasks into auditable execution traces with verified evidence and AI-smell detection.
2
0
regex builder
by Kevin Cline
$12
Convert plain English into tested regex patterns and explain existing ones across multiple language flavors.
2
0
Claude testing skills for writing and running tests
Claude testing skills give Claude Code a repeatable way to write tests for your code; Claude Code then runs them and can fix what fails. The descriptions below come from the listings, and we have not run these skills ourselves.
Claude testing skills by task
Unit tests: Test Gen detects your stack and writes edge case tests for Jest, Vitest, Pytest, Go testing and JUnit, per its listing, which does not say whether it runs them. Ask Claude to run the suite right after.
End-to-end tests: Playwright E2E Test Writer and Flaky Test Fixer writes browser tests, and Robot to Playwright Converter is free and converts Robot Framework files into Playwright TypeScript specs; it needs Playwright and Node.js. Keep end-to-end tests for key user flows and leave edge cases to unit tests, which run faster.
API tests: API Contract Tester turns an OpenAPI spec into Jest, Vitest, Supertest, Playwright or Pytest suites. Data Faker covers test data.
CI and coverage: Diff Coverage Checker asks for tests on every changed line, and the free Python TestCoverageGuard catches empty tests that AI agents sometimes write. Run them in CI on pull requests.
Claude Code debugging skills
Flaky Test Detective for AI Coding Agents diagnoses unreliable tests and plans stabilization; it is a $9.99 monthly subscription. Production Bug Hunter is free and targets Firebase, Next.js and Vercel stacks, per its listing, and Env Doctor and Lobster Debugging are free too. Compare them with Claude code quality and review skills.
Testing AI agents, RAG and skills themselves
Testing an agent differs from testing a function. Agent Regression Guard runs after each code change and needs Git, per its listing, and Diagnosing Rag Failure Modes sorts retrieval failures into patterns. To test a skill itself, Skill Creator is free and helps you write, test and refine a SKILL.md; try any skill on a sample task in a scratch repository before live use. Our guide to testing and debugging AI agents explains the method.
How to choose a Claude testing skill
Choose on test type (unit, end-to-end, API or agent), then framework. A skill's frontmatter can list allowed-tools, the tools Claude may use without asking while the skill is active, so read the SKILL.md preview, the scan result and our security skills for Claude. Connect your agent to Agensi once, then ask for a skill by name or let Claude load it when the task matches; nothing is saved to a skills folder. The MCP setup guide covers the connection. Review generated tests yourself before you trust them. Our guide to the best Claude Code testing skills compares more. Browse the full Claude skills marketplace.
Frequently asked questions
Connect an MCP-compatible agent to Agensi and ask it to use the skill on your task. Approve any required purchase. The latest approved instructions load on each use; never save skill files to disk.
Some are free, but most are paid. Paid skills show the price upfront, are a one-time purchase, and include future updates from the creator.
Yes. Every listing is checked by an 8-point automated security scan before it can go live, and the result is shown on each skill page alongside the file list.
Get in touch
Questions, partnership ideas, or feedback on the platform? Tell us what's working and what isn't, we love to hear from you!
SR
Samuel Rose
Founder & CEO of Agensi
Email UsBook a Callinfo@agensi.io
We typically respond within a few hours during business hours.