Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
claude-code-eyes
SkillsGive Claude Code eyes 👁️ — a camera skill so it can SEE real hardware, displays and wiring: verify a rendered panel, check wiring before power-on, and catch bugs that live on the glass, not the logs.
git clone https://github.com/fcavalcantirj/claude-code-eyes.git -
{ "task": "comprehensive_repository_analysis", "objective": "Conduct exhaustive analysis of entire codebase to identify, prioritize, fix, and document ALL verifiable bugs, security vulnerabilities, and critical issues…
-
wrapper-mcp
MCP serversCzech NLP tools: NER (35 langs), anonymization (80+ PII), morphology, translation, spellcheck
wrapper-mcp@0.8.5 -
## Objective Conduct a thorough analysis of the entire repository to identify, prioritize, fix, and document ALL verifiable bugs, security vulnerabilities, and critical issues across any programming language…
-
skill-creator-plus
SkillsBased on Anthropic's skill-creator — with bug fixes, working Cowork support, and official best practices baked in. Claude skill for creating, testing, and improving other Claude skills.
git clone https://github.com/yaniv-golan/skill-creator-plus.git -
Czech PII Anonymizer & NLP
MCP serversAnonymize PII & redact text (GDPR): Czech + 35-lang NER, morphology, translation, spellcheck
anonymize-mcp@0.10.2 -
Shelly Smart Home
MCP serversLocal-first MCP server for Shelly smart-home devices (Gen1-Gen4): control, energy, automation.
shelly-mcp@0.1.3 -
Agent Lease
MCP serversKeep Claude Code and Codex off each other's files: hook-enforced path leases, presence, messages.
agent-lease-mcp@0.2.0 -
Koschei
MCP serversRun agent-written code under a capability policy: see what a program can touch before it runs.
koschei-lang@0.14.0 -
You are a meticulous senior software engineer doing code review. Goals, in priority order: 1. Correctness bugs (logic errors, off-by-one, null/undefined, race conditions, wrong error handling). 2. Security (injection…
-
claude-mem-lite
MCP serversPersistent long-term memory for Claude Code via MCP — captures coding decisions, bugfixes, and context across sessions. Hybrid FTS5 + TF-IDF search with episode batching. Single SQLite DB, no external services. Alternative to claude-mem with 600x lower cost.
git clone https://github.com/sdsrss/claude-mem-lite.git -
Rein
MCP serversSpend limits for AI agents that pay with x402: every paywall is policy-checked before a cent moves.
@reinconsole/mcp@0.8.0 -
Debugging Detective
PromptsAct as a senior debugging engineer with 15+ years of experience finding root causes in production systems. I will describe a bug or unexpected behavior in my code, and you will help me systematically diagnose it. For…
-
product-mode
PromptsThe most expensive bug in AI-assisted building is shipping the wrong thing, well. A drop-in CLAUDE.md / AGENTS.md for PM + eng teams using Claude Code, Cursor, or Codex: 7 principles for problem framing, scope, tradeoffs, and outcome measurement. Built on @karpathy's observations.
git clone https://github.com/sohaibt/product-mode.git -
skills
SkillsProfessional skills for any work and software factory, nasty bugs, hard decisions and reliable software delivery with Claude Code, Codex and other AI agents.
git clone https://github.com/simonasrazm/skills.git -
skills-from-the-artificer
Skills29 drop-in Claude Code skills: cost-tier model routing, debugging (rubber-duck, test-first-bugfix, trust-but-verify), and 24 laws-of-software reference skills. Install with: npx skills add The-Artificer-of-Ciphers-LLC/skills-from-the-artificer --all
git clone https://github.com/The-Artificer-of-Ciphers-LLC/skills-from-the-artificer.git -
Visual QA & Cross-Browser Audit
PromptsYou are a senior QA specialist with a designer's eye. Your job is to find every visual discrepancy, interaction bug, and responsive issue in this implementation. ## Inputs - **Live URL or local build:** [URL / how to…
-
Act as a software developer specializing in data analysis portals. You are responsible for developing and debugging the HTS Veri Analiz Portalı. Your task is to: - Identify bugs in the current system and propose…
-
dualkit
SkillsFree, open-source tools for products that ship in Arabic and English: agent skills, Gulf formats, a bilingual design system, and a check that finds Arabic and RTL bugs on any page.
git clone https://github.com/dualkit/dualkit.git -
Anthropic: Claude Opus 5
ModelsClaude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...
anthropic/claude-opus-5 -
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 -
Anthropic: Claude Sonnet 5.5
ModelsClaude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing...
anthropic/claude-sonnet-5.5 -
Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...
anthropic/claude-opus-5:batch -
first-pass
SkillsRules and checks that make Claude Code look around a change, not just at the lines it writes: ten questions before code, a reviewer that didn't write it, proof before done, bugs fixed as a class.
git clone https://github.com/joetawil7/first-pass.git
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.