Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
vibeweaver
SkillsA bounded, hard-gated graph-engineered state machine, written as a skill — runs on any agent harness, tuned best for opencode so far: full skill, mini variant, and A/B benchmark harness
git clone https://github.com/logandoo/vibeweaver.git -
vps-forge
SkillsAgent Skill that lets Claude Code, Codex, Cursor, Copilot and other AI agents set up and harden a Debian/Ubuntu VPS without locking you out: SSH, firewall, fail2ban, updates, Docker, TLS, backups, phone alerts. Benchmarked on 120 VM runs.
git clone https://github.com/mountain-beaver/vps-forge.git -
Cortex
SkillsCross-platform persistent memory MCP for Codex, Gemini CLI, Claude Code, and other local MCP hosts. 36 cited neuroscience mechanisms, local-first SQLite/PostgreSQL, hybrid retrieval, decay-based consolidation, and reproducible benchmarks. Claude adds optional automatic lifecycle hooks.
git clone https://github.com/cdeust/Cortex.git -
Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thought. It offers competitive benchmark...
tencent/hunyuan-a13b-instruct -
Xiaomi: MiMo-V2.5-Pro
ModelsMiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro....
xiaomi/mimo-v2.5-pro -
devcycle
SkillsTurns a short feature/bug description into a reviewed, on-device-verified implementation — parallel subagents, cross-model review, GitHub reconcile, and a doctor/learn loop that benchmarks and improves the pipeline itself. Built on superpowers.
git clone https://github.com/KonstantinRoehrl/devcycle.git -
MiniMax: MiniMax M3.1 Flash
ModelsMiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and cybersecurity. It is built for complex,...
minimax/minimax-m3.1-flash -
Auto Router
ModelsAuto is OpenRouter’s flagship model router, built for general-purpose usage. It adapts to each request, choosing cost-optimal models and adjusting reasoning effort. It balances task difficulty, benchmark results, live prices,...
openrouter/auto -
Anthropic: Claude Sonnet 4.5
ModelsClaude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...
anthropic/claude-sonnet-4.5 -
Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...
anthropic/claude-sonnet-4.5:batch -
AionLabs: Aion-RP 1.0 (8B)
ModelsAion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto, where LLMs evaluate each other’s responses. It is a fine-tuned base model...
aion-labs/aion-rp-llama-3.1-8b -
delegate-router
SkillsClaude Code and Codex CLI skill: an LLM router that delegates bulk, already-decided coding tasks to another model you already pay for (GPT via Codex, Gemini via agy, a Claude Opus subagent), on another subscription first. Benchmark-checked routes, cost per task measured on a bench, cross-model review. The host verifies every diff.
git clone https://github.com/pvjbuilds/delegate-router.git -
skill-creator
SkillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
/plugin marketplace add anthropics/skills
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.