AI & ML

vheins Skill

A skill for generating and maintaining high-quality documentation following established standards (JSON:API, Mermaid ERDs, Positive/Negative testing).

vheins Skill

Skill for implementing features based on documentation, bridging technical specs (API, ERD, Stories) and code using a Test-Driven Approach.

jaaaackielai Bundle

Transform research papers and their code repositories into high-quality reusable skills through multi-agent council deliberation. Three specialist analysts independently examine the paper and code, then anonymously peer-review each other's work, and a chairman synthesizes the best content into structured skill files. Use when users want to package a paper with its implementation code, create a reference guide for a specific paper, or build a skill that captures a paper's problem, solution, and contributions. Triggers include requests like "package this paper as a skill", "create a skill from paper X and its code", or "analyze paper and code to make a reusable reference".

robusta-dev Bundle

This skill should be used when the user asks to "create an eval", "write an eval test", "add a new eval", "create a test case", "write a test for Holmes", or discusses LLM evaluation tests, eval fixtures, or test_case.yaml files for the HolmesGPT project.

robusta-dev Skill

Any Elasticsearch error-log query against app-279-logs-* — these indices use ``lvl`` (keyword) for log severity, not ``severity`` or ``level``.

robusta-dev Skill

Guide for investigating slow PostgreSQL queries

robusta-dev Skill

Troubleshooting Application Gateway Problems

robusta-dev Skill

Python Application Memory Troubleshooting

frankxai Skill

Build an economics model that survives someone checking the numbers. Use during the cost stage of /architect to write 04-roi.md and prices.json — sourced unit prices, a sensitivity band on the drivers that actually move the answer, payback expressed as a range, and never an IRR.

frankxai Skill

Record a decision so the next person doesn't have to re-derive why. Use whenever a decision affects tool choice, data boundaries, deployment shape, or agent authority — most often by principal-architect writing adr/ADR-NNNN-<slug>.md during decide, but any stage can write one when it makes a call worth remembering.

frankxai Skill

Architecture Development Lifecycle for systems that call a language model. Use when running /architect, adding a stage, or deciding which gated artifact to write next. The stage table in WORKFLOW.md is the contract — do not hardcode the stage list.

deepread-tech Skill

Bring Your Own Key to DeepRead. Connect your OpenAI, Google, or OpenRouter API key — all document processing routes through YOUR account at zero DeepRead LLM cost. Page quota skipped entirely. Same API, same endpoints, one toggle.

openhands-software-agent-sdk Bundle

This skill should be used when the user asks to "release the SDK", "prepare a release", "publish a new version", "cut a release", "do a release", or mentions the SDK release checklist or release process. Guides through the full software-agent-sdk release workflow from version bump to PyPI publication, emphasizing human checkpoints.

juanre Skill

Use when getting started with llmemory document storage and search - covers installation, initialization, adding documents, vector search, hybrid search, semantic search, BM25 full-text search, document management, and building RAG systems with multi-tenant support

arvindand Bundle

JVM dependency intelligence via Maven Tools MCP server. Use when the user asks about Maven or Gradle dependencies, safe upgrades, CVEs, license risks, release history, or project dependency health. Use when reviewing `pom.xml`, `build.gradle`, `build.gradle.kts`, or Maven coordinates. Use when the user says 'check my dependencies', 'should I upgrade X', 'what can I safely bump', or 'is this version safe'. Use even when the user just pastes a `groupId:artifactId` coordinate without a verb.

gosu-code Bundle

Use this `codex-mcp` skill to instruct another AI Agent to invoke a tool or execute a workflow on your behalf for the following scenario, 1.When you are requested to invoke a mcp tool that you don't have access (can use `ListMcpResourcesTool` to check) such as `context7`, `github`, `linear`, `jira`; 2.When you are requested to execute a complex workflow that require interacting with multiple mcp tools and bash CLI commands for example `github-project-create-items`, `github-project-list-items` workflows;

gosu-code Bundle

Utility tool to create new git worktrees with proper setup for development environments. Automates creation, copying, symlinking, and ownership management for smooth developer onboarding or isolated task/feature work.

frankxai Bundle

Find the line where retrieved text becomes an instruction instead of data, and gate every irreversible tool behind a human step. Use during the secure stage of /architect to write 05-trust-boundary.md — trust tiers T0-T3, the trace-the-retrieved-text procedure, tool gating, and the OWASP GenAI LLM Top 10 2026 mapping.

frankxai Skill

Review the architecture of a system that calls a language model. Use when adding an agent loop, a retrieval path, a tool surface, or an MCP server to a codebase; when a system that worked in a demo is being prepared for production; or when asked to audit, review, or plan AI/agent architecture. Checks the four decisions that are expensive to reverse, then the seven planes and their boundaries.

webthree549-bot Bundle

Anticipates needs, keeps work moving, and improves through use so the agent gets more proactive over time.

webthree549-bot Bundle

Control ROS1/ROS2 robots via natural language with real-time feedback. Use when users want to control robots, navigate, check sensors, manage fleets, or perform robot tasks. Supports ROS1 (Noetic) and ROS2 (Jazzy/Humble) through WebSocket, MQTT, or gRPC. Features include intelligent navigation, sensor interpretation, fleet coordination, safety management, and bidirectional real-time streaming to OpenClaw and Web UI.

gosu-code Bundle

This skill should be used when the user asks to "create a session hook", "add a temporary hook", "create a hook for this session", "set up a hook that activates immediately", "configure a one-time hook", or mentions "session-specific hook", "per-session hook", or "temporary hook". Provides guidance for creating session-scoped hooks that activate immediately without restarting Claude Code.

agentsmesh Bundle

Selects and runs the appropriate AgentsMesh end-to-end suite for Web, Desktop, MCP, or iOS, including worktree-specific environment setup and browser-level verification. Use when a change needs E2E coverage, a user asks to execute or diagnose an E2E test, or a cross-service workflow must be verified against the real development stack.

glassbead-tc Bundle

Develop and extend the Audius Code Mode MCP server — the Effect-TS server that exposes the Audius and Open Audio Protocol APIs to LLMs via search + execute tools. Use this skill whenever the user wants to add features, fix bugs, refactor, or extend this MCP server. Trigger on mentions of MCP server development, adding new tools, modifying the sandbox, changing the transport layer, updating the spec loader, extending the search index, or any work on the audius-mcp-atris codebase itself. Also use when the user asks about the server architecture, how the components connect, or wants to understand the Effect-TS service/layer patterns used here.

glassbead-tc Bundle

Test all tools and endpoints of the Audius MCP server in parallel using subagents. Use this skill when the user asks to test the server, run a smoke test, verify the tools work, check if the API is responding, or validate the MCP server end-to-end. Also trigger when the user says 'run tests', 'test everything', 'smoke test', 'health check', or 'verify the server'. This runs read-only tests only — no writes, no mutations, no side effects.

glassbead-tc Skill

Guide for designing, implementing, and advising on MCP servers that use Code Mode — the pattern where an LLM writes and executes code to orchestrate API calls instead of calling individual tools one at a time. Use this skill whenever the user mentions Code Mode, MCP tool proliferation, context window bloat from MCP tools, programmatic tool calling, LLM code execution in MCP, building a Code Mode server, or wants to compress a large API into a small MCP surface. Also use when the user asks how to reduce token cost of MCP tools, how to expose an entire API over MCP efficiently, or how to implement search+execute patterns in FastMCP, Cloudflare Workers, or custom servers.

philo-groves Bundle

Build human-friendly, screen-recordable proof-of-concept reproduction kits from already proofed triage-verifier evidence. Use after triage-verifier accepts a finding as proofed, or when Codex needs to turn an agent-focused PoC, proof packet, request log, crash repro, or verifier artifact into direct step-based human reproduction artifacts for bounty triagers, researchers, auditors, or screen recordings.

s-morgan-jeffries Skill

Use BEFORE adding any new tool, parameter, or endpoint to the Apple Mail MCP server. Also use when considering API changes, evaluating feature requests, or when tempted to create a specialized operation. Contains the decision tree that prevents tool sprawl and the anti-pattern catalog.

s-morgan-jeffries Skill

Use when optimizing Apple Mail MCP operations, diagnosing slow queries, adding new filtering logic, or modifying how data is fetched from Mail.app. Covers osascript overhead, whose clause optimization, batch operation patterns, and known operation timings.

yfge Bundle

Use when evaluating repository agent-readiness, mapping harness roles, choosing the next smallest improvement, or designing and reconciling agent entrypoints such as AGENTS.md, CLAUDE.md, GEMINI.md, Cursor rules, or GitHub instructions.

lyfe2025 Skill

当你面对 2 个以上彼此独立的任务（无共享状态、无顺序依赖）时使用：为每个独立问题域派发一个 agent 并行推进。

philo-groves Bundle

Establish authorized engagement context, look up public bounty scope evidence, and route cyber tasks before using specialized skills. Use for any request to model security boundaries, review code vulnerabilities, inspect web or mobile apps, research CVEs, build fuzzers, reverse or debug binaries, or analyze exploit chains, especially when target authorization, bounty program scope, impact tolerance, or the desired deliverable is unclear.

philo-groves Bundle

Analyze authorized exploit chains by combining tracked findings, confident or proofed issues, and de-escalated leads into higher-impact vulnerability hypotheses. Use when Codex needs to correlate findings, model preconditions and postconditions, consider de-escalated leads as conditional chain edges, create chain packets, update finding-tracker, or send chain findings through triage-verifier.

philo-groves Bundle

Plan and coordinate authorized multi-agent cyber workflows with explicit subagent roles, bounded assignments, tracker discipline, debate, deduplication, proof handoffs, and synthesis. Use when the user explicitly asks for subagents, parallel agents, delegation, debate, multiple reviewers, or staged agentic security work.

philo-groves Bundle

Perform authorized live or local web application security inspection using browser-visible behavior, HTTP traffic, API calls, authentication and authorization flows, session state, client-side storage, security headers, browser console evidence, and safe runtime validation. Use when Codex needs to inspect a web app, SPA, API-backed UI, admin panel, SaaS workflow, OAuth/OIDC flow, GraphQL/REST endpoint, WebSocket, upload/import/export feature, AI/agent web feature, or bug bounty target through a browser or controlled HTTP/runtime testing.

huskydanny Skill

Assess overall market sentiment and how the target stock fits