AI & ML

aj47 Bundle

Browser automation using agent-browser CLI connected to a logged-in Chrome session via CDP. Use when asked to browse a website, fill forms, click buttons, take screenshots, scrape data, automate browser tasks, or any web interaction. Also use when asked to 'start chrome debugging', 'connect to chrome', or 'launch chrome for browser automation'.

aj47 Skill

Runs OpenAI Codex CLI agents in iTerm slots to work on GitHub issues. Use when asked to 'run codex on an issue', 'assign an issue to codex', 'spin up a codex agent', or 'have codex work on issue #N'.

aj47 Bundle

Teaches the agent how to create new Agent Skills - the open standard for extending AI agent capabilities. Use this skill when asked to create, write, or develop new skills for AI agents.

aj47 Bundle

Fetch supplementary media (logos, GIFs, landing pages, diagrams, videos) to accompany video clips. Uses APIs and Playwright MCP for browser automation.

microsoft Bundle

Independent, multi-model review of a design or spec **before** any code is written, for the microsoft/winappcli repo. Activate when a contributor asks to "review this spec", "review my design", "review this design doc", "validate this approach", "should we build this", "spec review", "design review", or "feature review". Fans out parallel sub-agents — each doing its OWN research against the real codebase and ecosystem rather than trusting the spec — covering necessity & scope, approach & alternatives, feasibility vs reality, risks & unknowns, DX & user impact, and a different-model-family cross-check. Emits a decision-oriented recommendation (proceed / proceed-with-changes / reconsider) to stdout. This is the PRE-CODE companion to the pr-review skill (which reviews code already written); use spec-review at the design/spec stage, not on an implemented diff. Does NOT write code or edit the spec.

microsoft Bundle

Inspect and interact with running Windows app UIs from the command line using UI Automation (UIA). Use when an AI agent or developer needs to inspect a UI element tree, find controls, take screenshots, click buttons, read or set text, or verify UI state in a running Windows app. Works with any framework WinUI 3, WPF, WinForms, Win32, Electron.

pluginagentmarketplace Bundle

Master writing plugins including agent implementation, skill creation, command development, and hook scripting. Learn best practices for plugin coding.

hifriendbot Skill

Save the current conversation context as a persistent memory using CogmemAi so it survives compaction, session end, or model handoff. Use when the user says "save context", "save this conversation", "write this down", "don't lose this", "checkpoint", "save state", or when the context window is filling up and important facts may be evicted. Also use proactively before risky tool calls or long-running tasks where losing context would be costly.

iurykrieger Skill

Re-synchronizes the vault with external sources. In default mode, scans the `sources` field of all entities, deduplicates URLs, fetches updated content from each source (Confluence, GDocs, GitHub, Markdown), performs incremental diff and delegates writing to /bedrock:preserve. With --people, scans actor repositories via GitHub API and identifies active contributors. With --github, detects relevant activity in repositories and correlates PRs with topics/projects via LLM semantic matching. Use when: "bedrock sync", "bedrock-sync", "/bedrock:sync", "synchronize", "update sources", "sync people", "sync github".

iurykrieger Bundle

Internal fetcher module for Google Docs and Sheets. Fetches content via MCP (preferred, when available), Google API with bearer token or public URL export (fallback), or browser DOM extraction via Claude in Chrome (last resort) and returns Markdown. Used by /bedrock:learn and /bedrock:sync — not intended for direct user invocation.

iurykrieger Bundle

Internal fetcher module for Confluence pages. Fetches content via Atlassian MCP (preferred), REST API with Basic Auth (fallback), or browser DOM extraction via Claude in Chrome (last resort) and returns Markdown. Used by /bedrock:learn and /bedrock:sync — not intended for direct user invocation.

photoszzt Skill

This skill runs exhaustive model checking to verify all reachable states of a TLA+ specification using TLC. It should be used when the user asks to "check my spec", "run TLC", "verify my TLA+ spec", "find invariant violations", "exhaustive model checking", "check for bugs in my spec", "model check", "exhaustive check", "verify all states", "run model checker", "verify invariants", "check properties", "check temporal properties", "check liveness", "full check", "check all states", "check safety", or "verify properties".

photoszzt Skill

This skill verifies and configures TLA+ tools installation (Java, tla2tools.jar, CommunityModules, MCP server). It should be used when the user asks to "setup TLA+", "install TLA+", "TLA+ not working", "tools missing", "java not found", "verify TLA+ installation", "check TLA+ tools", "TLA+ prerequisites", "configure TLA+", "MCP server not connecting", "fix TLA+", "SANY not working", "reinstall TLA+", "environment check", or "check prerequisites".

photoszzt Skill

This skill extracts symbols (constants, variables, operators) from a TLA+ specification and generates a TLC configuration file. It should be used when the user asks to "generate config", "create cfg file", "no config file", "what's in my spec", "extract symbols", "generate .cfg", "list symbols", "show constants", "show variables", "set up TLC config", "prepare for model checking", "show operators", "analyze my spec", "what constants does my spec have", "what variables are defined", "what operators are in my spec", "include extended modules", "symbols from imported modules", "help me create a config", "set up model checking config", or needs a .cfg file for model checking.

photoszzt Bundle

This skill orchestrates the full model checking workflow: parse, configure, smoke test, and exhaustive check. It should be used when the user asks to "model check", "run TLC", "verify specification", "check invariants", "run model checker", "check my spec", "validate spec", "full verification workflow", "end-to-end TLC", "check properties", "check liveness", or mentions model checking workflow and TLC configuration.

photoszzt Bundle

This skill provides introductory guidance for learning TLA+ and writing first specifications. It should be used when the user asks to "learn TLA+", "what is TLA+", "TLA+ tutorial", "get started with TLA+", "first TLA+ spec", "TLA+ basics", "new to TLA+", "TLA+ introduction", "how to write TLA+", "TLA+ help", "TLA+ example", "write a spec", "TLA+ spec template", "formal specification", "create a spec", "model a system", or the user mentions wanting to understand TLA+ fundamentals.

photoszzt Bundle

This skill guides the creation of animations that visualize TLA+ specifications during model checking or trace exploration. It should be used when the user asks to "create animation", "animate my spec", "visualize state transitions", "show me what's happening", "TLA+ animation", "trace visualization", "see state changes", "render animation in terminal", "ASCII animation", "SVG animation", or "show animation in browser".

tomfordrumm Bundle

Manage a changing stream of software tasks through subagents while the main chat handles intake, priorities, dependencies, assumptions, and status. Use for an ADHD or SDVG manager, technical orchestrator, multi-agent coding queue, or an active session with `.codex/adhd-manager/`. Delegate product investigation, implementation, testing, review, and integration.

markus41 Bundle

Use this skill when users ask for Structurizr DSL, architecture diagrams, ADR integration, workspace API/admin API automation, plugins, MCP server usage, static site exports, and Java/DSL modeling workflows.

buzzdan Skill

META ORCHESTRATOR for any Go code change that should end in a commit (features, bug fixes, refactors). WHEN: User requests Go code work (implement, fix, add, refactor), mentions "@ldd"/"ldd", or runs a /go-ldd-* command in a Go project. Runs the five-phase workflow (PREPARE is an autonomous sub-phase, 1.5): DESIGN → PREPARE → IMPLEMENT (per-behavior TDD loop) → FULL LINT (lint-fixer agent) → REVIEW (per slice) → SHIP.

bkircher Bundle

Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to authenticate if not logged in.

joernstoehler-dnd-claude-code Skill

Record an agent behavior incident to feedback/ for the next context engineering pass. Use when Jörn flags something the agent did wrong mid-session.

joernstoehler-dnd-claude-code Bundle

Guidance for Jörn-approved edits to this repo's agent harness: `AGENTS.md`, `.agents/skills/**`, `.codex/agents/*.toml`, Codex config notes, onboarding wording, and subagent/review prompts. Use only when Jörn explicitly asks to revise onboarding, convention routing, skills, subagents, prompt behavior, or agent workflow documentation.

pnp-copilot-prompts Bundle

Review a Model Context Protocol (MCP) server implementation against the 2026-07-28 protocol revision, which removed the initialize handshake and Mcp-Session-Id and made the protocol stateless. Use when the user asks to review, audit, upgrade or migrate an MCP server, asks whether their MCP server is spec compliant, asks which protocol revision their server implements, or reports that an MCP client cannot connect to their server.

pnp-copilot-prompts Bundle

Generates a weekly PowerPoint slide from a PnP copilot-prompts GitHub sample URL (for example, samples/agent-instructions/creator-agent), derives the correct weekly title from the sample folder, and produces a styled .pptx file that matches the Prompt-K template layout.

pnp-copilot-prompts Skill

This skill should be used when the user asks to "create a new skill sample", "add a skill", "scaffold a new skill", "contribute a skill", "create a GitHub Copilot skill", "build a custom skill", or needs to create a new GitHub Copilot custom skill sample with proper folder structure, SKILL.md, README, and sample.json metadata inside the skills folder. Do NOT use this skill for simple prompt samples or agent instructions.

pnp-copilot-prompts Skill

This skill should be used when the user asks to "create a new prompt sample", "add a new prompt sample", "scaffold a new prompt sample", "create a prompt contribution", "add a prompt", or needs to create a new prompt sample with proper folder structure, README, and sample.json metadata. Do NOT use this skill for agent instructions or system prompts.

pnp-copilot-prompts Skill

This skill should be used when the user asks to "create an agent instruction", "add agent instructions", "scaffold an agent sample", "create a system prompt sample", "add a system prompt", "create a new agent", "build an agent", or needs to create a new agent instruction sample with proper folder structure, README, and sample.json metadata inside the agent-instructions folder. Do NOT use this skill for simple prompt samples that are not agent instructions.

pnp-copilot-prompts Bundle

Transform any rough prompt, request, or idea into a well-structured, context-engineered prompt using Andrej Karpathy's context engineering principles. Use this skill whenever the user asks to improve, rewrite, restructure, optimize, or "engineer" a prompt; mentions prompt engineering or context engineering; pastes a prompt and asks to make it better; wants help writing a system prompt or instructions for an AI; or says things like "turn this into a good prompt", "make this prompt work better", or "Claude isn't giving me what I want with this prompt". Also use it when the user shares a vague request and explicitly wants it converted into a reusable, high-quality prompt. Do NOT use this skill to answer or execute the original prompt itself, to write general (non-prompt) documents, or for code or content generation that isn't about crafting a prompt.

pnp-copilot-prompts Bundle

Generate comprehensive documentation for Microsoft Copilot Studio agents from exported Dataverse solutions using the Power Platform CLI. Use when asked, to analyse the solution with the agents file and create documentation from the contents.

hardw00t Bundle

LLM and AI application security testing skill for prompt injection (direct, indirect, multimodal), system-prompt extraction, RAG poisoning, memory poisoning, MCP server injection, skill-file injection, agentic tool misuse, computer-use UI injection, and excessive agency. Authorization required — this skill tests AI systems you are explicitly permitted to assess. Triggers on requests to test LLM / AI-agent / RAG / MCP / computer-use security, perform prompt injection, extract system prompts, poison RAG or memory, audit agent tool use, or evaluate AI guardrails.

hardw00t Bundle

Comprehensive Android mobile application penetration testing with rooted-device ADB and Frida-based MCP tooling. Covers OWASP MASTG full methodology: recon, static + dynamic analysis, SSL/root bypass, IPC fuzzing, data exfiltration, crypto audit, and reporting. Triggers on requests to pentest Android apps, analyze APKs, bypass mobile security controls, or run MASVS/MASTG assessments.

hardw00t Bundle

Automated Dynamic Application Security Testing (DAST) using Playwright MCP plus standard OS pentest tooling. Performs blackbox or greybox scans on single or multiple domains with orchestrated crawling, vulnerability detection, and structured output. Trigger on requests like "scan this domain", "run DAST on these URLs", "automated pentest", or "security-test the staging app".

hardw00t Bundle

Systematic threat modeling skill for applications, APIs, and systems using STRIDE, PASTA, Attack Trees, DREAD, LINDDUN, and OCTAVE. Use when assessing security architecture, creating data flow diagrams (Mermaid), enumerating threats from OpenAPI specs or architecture docs, building attack trees, mapping threats to NIST/CIS/OWASP ASVS controls, or producing a threat model report. Triggers on requests to threat model, analyze attack surface, create a DFD, apply STRIDE, or design security mitigations.

llm-coding Bundle

Empirically test whether a candidate term qualifies as a semantic anchor by probing how densely it sits in LLM training data — across several model tiers in a clean room — before proposing it. Use when triaging an anchor proposal, deciding anchor vs contract, or vetting a rename. Produces a verdict against the four criteria (Precise, Rich, Consistent, Attributable), a tier rating, and a ready-to-paste proposal or rejection.

llm-coding Skill

DEPRECATED alias of semantic-contracts-installer. Renamed because the skill's high-value job is installing Semantic Contracts (compositions the LLM cannot guess), not bare anchor lists. Use semantic-contracts-installer instead; this alias forwards to it and will be removed after one release.