Public benchLIVE

What's on the bench.

5,040
Artifacts
26
Industries
1
Reads / week

All artifacts

5040
Industry
SKILL0

Android Kotlin

Android Kotlin development with Coroutines, Jetpack Compose, Hilt, and MockK testing

software-engineering+1
0
SKILL0

Android Java

Android Java development with MVVM, ViewBinding, and Espresso testing

software-engineering
0
SKILL0

AI Models

Latest AI models reference - Claude, OpenAI, Gemini, Eleven Labs, Replicate

ai-prompt-engineering+1
0
SKILL0

Agent Teams

Claude Code Agent Teams - default team-based development with strict TDD pipeline enforcement

software-engineering+1
0
SKILL0

Aeo Optimization

AI Engine Optimization - semantic triples, page templates, content clusters for AI citations

marketing-growth-copy+2
0
SKILL0

Update Code Index

Regenerates `CODE_INDEX.md` by scanning the codebase for all functions, classes, hooks, and components. Organizes by capability to prevent semantic duplication.

software-engineering+1
0
SKILL0

Sync Contracts

> Lightweight incremental update of workspace contracts without full re-analysis.

software-engineering
0
SKILL0

Sync Agents

Sync project configuration between Claude Code, Kimi CLI, and Codex CLI.

software-engineering
0
SKILL0

Spawn Team

Spawn the default agent team for this project. Creates a coordinated team of agents that implement features in parallel following the strict TDD pipeline.

software-engineering+1
0
SKILL0

Model Config

View or change the **primary model** that handles your coding work across srooter (the gateway), the route-task hooks, and Maggy. One setting, read everywhere. Stored in `~/.claude/model-config.json`.

ai-prompt-engineering
0
SKILL0

Maggy

Start Maggy (the AI engineering command center) and open the dashboard in a browser.

software-engineering+1
0
SKILL0

Initialize Project

Full project setup with Claude coding guardrails. Works for both new and existing projects.

ai-prompt-engineering+1
0
SKILL0

Icpg Why

Trace any symbol back to its creating ReasonNode — show the original goal, who wrote it, and whether it's still doing what it was made for.

ai-prompt-engineering+1
0
SKILL0

Icpg Impact

Show the blast radius of a ReasonNode or symbol — what depends on it, what breaks if it changes.

software-engineering+1
0
SKILL0

Check Contributors

Checks who's working on the project and optionally converts to a multi-person project with team state management.

software-engineering+1
0
SKILL0

Build In Public

Build-in-Public — generate posts from your engineering work, anonymize, and schedule via Buffer

software-engineering+1
0
SKILL0

Analyze Workspace

> Full dynamic analysis of workspace topology, dependencies, and contracts.

software-engineering+1
0
SKILL0

Analyze Repo

Analyze an existing repository's structure, conventions, and guardrails.

software-engineering+1
0
AGENT0

6 Test Generator

Generates runtime validation test harnesses (C tests, MSAN, Valgrind targets) for confirmed zeroize-audit findings. Produces a Makefile for automated test execution.

cybersecurity-soc+1
0
AGENT0

5c Poc Verifier

Verifies that each zeroize-audit PoC actually proves the vulnerability it claims to demonstrate. Reads PoC source code, finding details, and original source to check alignment between the PoC and the finding. Produces poc_verification.json consumed by the orchestrator.

cybersecurity-soc+1
0
AGENT0

5b Poc Validator

Compiles and runs all PoCs for zeroize-audit findings. Produces poc_validation_results.json consumed by the verification agent and the orchestrator.

cybersecurity-soc+1
0
AGENT0

5 Poc Generator

Crafts bespoke proof-of-concept programs demonstrating that zeroize-audit findings are exploitable. Reads source code and finding details to generate tailored PoCs — each PoC is individually written, not templated. Each PoC exits 0 if the secret persists or 1 if wiped. Mandatory for every finding.

cybersecurity-soc+1
0
AGENT0

4 Report Assembler

Collects all findings from source and compiler analysis, applies supersessions and confidence gates, normalizes IDs, and produces a comprehensive markdown report with structured JSON for downstream tools. Supports dual-mode invocation: interim (findings.json only) and final (merge PoC results, produce final-report.md).

cybersecurity-soc
0
AGENT0

3b Rust Compiler Analyzer

Performs crate-level MIR and LLVM IR analysis for Rust in zeroize-audit. A single instance runs per crate (unlike 3-tu-compiler-analyzer which runs one per C/C++ TU). Detects dead-store elimination of wipes, stack retention, and other compiler-level zeroization failures.

cybersecurity-soc+1
0

Want your own bench?

Free for crews of 5. Connect your team in minutes.

Sign up free