OWASP LLM Top 10 (2026) and Agentic Top 10 (2026) when a model can see untrusted content or act with real credentials. Trust boundaries, tools, memory, MCP, supply chain, output handling, and human approval.
Plugin llm-agent-security from marketplace leahycc-skills in LeahyCC/claude-skills. Commands read from the repo's manifest — 13 days ago.
llm-agent-securityDefensive review when a model can see untrusted content or act with real credentials. Covers prompt injection as an architecture problem, tool agency, memory and compaction, MCP and inter-agent traffic, AI supply chain, output handling, and human approval. Maps the OWASP LLM Top 10 (2026) and the OW
OWASP API Security Top 10 (2023) and Web Top 10 (2025) with production Next.js App Router code: access control, authentication with MFA and password reset, input validation, rate limiting, security headers and CSRF, data exposure, supply chain, SSRF, file uploads, and AI tools on those APIs
1 skill
Everything drawn with text characters, for work or fun: diagrams, tables, bar charts, sparklines, banners, boxes, pictures, pixel sprites, kaomoji, game boards and mazes. Draws on a grid, hands the counting to 5 Node scripts, and checks alignment before showing.
1 skill
Code a cold reader can follow: no floating (magic) numbers or strings without a name or a unit-and-why note nearby, names that carry units and do not lie, small single-purpose functions, shallow nesting, honest comments, no dead code, and balanced ESLint tuning.
1 skill
Silent bugs that pass typecheck and happy-path tests: 200 HTML fallbacks, pre-await state commits, swallowed catches, module singletons, Web API footguns, fresh-clone gaps, and false-green tests.
1 skill
Version-aware Next.js App Router guidance: component boundaries, data, caching, routing, proxy, errors, metadata, assets and migration. Scoped source review in skills/nextjs-app-router/SOURCES.md.
1 skill
Docs cut to what the reader needs: a fixed 5 layer page shape (why, picture, substance, edges, detail on demand), a cut ladder for sections, and the AI sound tells to fix. Write new docs or trim existing ones.
1 skill
AI-powered codebase understanding — analyze, visualize, and explain any project
9 skills · 10 agents · hooks
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Rewrite AI-sounding text so it reads like the writer without changing what it says.
1 skill
AI memory system — mine projects and conversations into a searchable palace. 47 MCP tools, auto-save hooks, guided setup.
3 skills · 6 commands · 1 MCP server · hooks
Perform AI code review on Git diffs — supports workspace changes, branch ranges, and single commits with concurrent per-file analysis, codebase search, and deep context-aware review.
2 commands
Eval-gated LLM fine-tuning lifecycle (LoRA/QLoRA, DPO, GRPO/RLVR, vision SFT, quantized export). Use when fine-tuning an open-weights model end-to-end: building the eval harness first, selecting method and model, preparing data, training with Unsloth or TRL, gating checkpoints, and exporting GGUF/FP8.
10 skills · 2 commands · 3 agents
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.