9,913 tagged LLM, measured the same way as everything else here.
Browse within: agent 502chatgpt 227agents 211cli 169ml 133bun 129javascript 124agentic-ai 122openai 119agent-framework 116deep-learning 107foundation-models 98agentskills 90cortex 90
ch0ks/hackarandas-claude-toolbelt
Skill Claude Code
Triage security findings from Semgrep Pro and Claude security-code-review using IaC files as deployment context (Terraform, Kubernetes, Docker Compose, CloudFormation, Azure Pipelines). Detects whichever IaC files are present, extracts deployment facts, scores each finding with CVSS 4.0 with per-vector justification…
supachai-j/open-knowledge-format-starter
Skill Claude Code needs its repo
Operate an Open Knowledge Format (OKF v0.1) bundle — a directory of Markdown files with YAML frontmatter that is the AI-maintained "LLM-wiki" for this repo. Use when the user wants to INGEST a source into the knowledge base, ASK/QUERY the wiki, ADD or EDIT a concept, LINT/maintain the wiki, or VALIDATE conformance.…
Skill Claude CodeCodex
A teaching aid that explains technical ideas with a small runnable code example and a guided walkthrough. It is meant for learning how something works, not fixing existing code.
RainJayTsai/ppt-template-editor
Skill Claude CodeCodex
A PowerPoint template workflow that extracts and fills text, chart, and table placeholders through YAML, a structured text format.
Skill Claude CodeCodex
Mine chat transcripts for decisions, exec updates, strategy shifts, feedback themes, and user preferences. Write structured entries to memory/, then update AGENTS.md with curated preferences and facts. The ingestion pipeline for the PM-OS context graph.
Skill Claude CodeCodex
Design and scaffold a new trapstreet.run task to evaluate a given agent/skill/tool -- the reverse of trapstreet-solution-scaffold (a solution for an existing task). Generates the mechanical parts (traptask.yaml, judge.py/grader.py on the TRAPTASKMANIFEST contract, buildcases.py's validate-then-render pipeline) and…
Skill Claude CodeCodex
Route AI assistant browser tasks to Tabrix first. Use when the user needs to control their real Chrome session, reuse existing login state or tabs, operate a remote browser over Streamable HTTP, or troubleshoot Tabrix browser automation. Prefer Tabrix over shell commands, synthetic browser sandboxes, or alternative…
Skill Claude Code
Review changed code for correctness bugs and reuse/simplification/efficiency cleanups. Use for pull requests, working diffs, or any code changes.
Skill Claude Code
Drive Rnix — the Agent OS — from the command line: spawn AI agents as OS-style processes, orchestrate multi-agent workflows, decompose high-level intents into sub-task DAGs, and inspect, trace, suspend or resume agent processes. Use this whenever you need to run the rnix CLI, launch or manage agents, compose several…
Skill Codex
Design and implement a complete responsive webpage that Pantheon can preview directly. Use for landing pages, portfolios, dashboards, prototypes, and HTML UI requests.
Skill Claude CodeCodex
Execute Python code in an E2B Firecracker sandbox with human review.
Skill Claude Code
Four quality gate checklists for frontend: baseline visual, accessibility, metadata/SEO, and motion performance. Post-implementation quality gates. Trigger: When reviewing UI changes, before merging frontend PRs, during sdd-verify.
Skill Claude CodeCodex
A debugging workflow that reproduces a problem with a failing test, collects evidence, finds the underlying cause, applies a fix, and runs regression checks. Regression checks verify that the fix does not break behavior that already worked.
Skill Claude CodeCodex
Query what the user did on this computer outside the current conversation — which apps, windows, files, and web pages they used, and when (last 48h, read-only). Reach for it whenever off-conversation context would help - resuming interrupted work, resolving vague references like "that doc I was reading" or "the error…
Skill Claude CodeCodex
Long-term memory guidance for MIRA MCP integration.
Skill Codex
Agent-directed install of backlog-mcp — detect the host harness, register the MCP server, run the first wakeup, verify git stayed clean and the briefing stayed under budget.
Skill Claude CodeCodex
A document-import tool that turns any source file into a structured document tree while keeping its text exactly unchanged.
geniusdapeng-collab/super-mickey
Skill Claude CodeCodex
A prompt-writing guide for designing individual shots in Seedance 2.0, an AI video-generation service.
aryrabelo/serpapi-agent-toolkit
Skill Claude CodeCodex
Use when an agent needs live, structured search-engine data through SerpApi (web results, news, shopping, local, jobs, flights, scholar, images, video). Covers picking the right engine for the intent, choosing compact vs complete output, query operators, pagination, deduping and citing results, and when NOT to search.…
Skill Claude CodeCodex
Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for…
Skill Claude CodeCodex
Analyzes CSV files and generates summary statistics.
Skill Claude CodeCodex needs its repo
Knowledge Kernel — a deterministic, evidence-backed source of truth for AI agents. Stores verified facts, evidence, relationships, and freshness. Use this when an agent needs to know infrastructure, software, endpoints, dependencies, agents, or projects — anything grounded in empirical reality.
Skill Claude CodeCodex
Use when opening, reviewing, or merging a pull request. Covers pre-PR checks (linting, tests, branch naming), PR description requirements, and post-merge cleanup. Not for code review commentary or architecture decisions — use the relevant role guidelines for those.
Skill Claude CodeCodex
RAIGO × OWASP LLM Top 10 — official OWASP LLM Application Security Top 10 (2025) enforcement rules for Hermes agents. Covers all 10 OWASP LLM risks: prompt injection, insecure output handling, training data poisoning, model denial of service, supply chain vulnerabilities, sensitive information disclosure, insecure…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: