2.7K skills · sorted by relevance
Create a Markdown threat model grounded in a codebase. Identify valuable assets, boundaries between trusted and untrusted components, realistic attack paths, and mitigations, then prioritize risks using explicit assumptions about likelihood and impact.
Apply a specific set of Rails conventions to design, implementation, and code review. It keeps business logic in models, represents state changes as records, limits dependencies, and uses Minitest with fixtures, or predefined test data.
Guides you through connecting external services to Claude Code plugins using MCP, a protocol for exposing services as tools. Covers connection types, configuration files, authentication, tool permissions, and testing.
Prepare coding tasks for delegation to an authorized agent’s AI command-line tool. Set up and synchronize the workspace, write precise change requests, then review returned changes and run relevant checks before reporting completion.
Fit regression and time series models in Python, then examine coefficients, uncertainty, and predictions. Check model assumptions, investigate unusual observations, and compare alternatives using detailed statistical summaries and diagnostic tests.
Guides you through connecting external services to Claude Code plugins using MCP, a protocol for exposing services as tools. Covers connection types, configuration files, authentication, tool permissions, and testing.
Helps create specialized Claude Code agents for tasks such as code review and debugging. Covers custom instructions, tool access, model selection, configuration files, and ways to connect agents across tasks.
Drive Codeman, the session manager this agent is running inside, over its HTTP API, from any agent CLI (Claude Code, Codex, Gemini CLI, OpenCode, Antigravity, Grok Build, DeepSeek Harness, OMP): list sessions, start worker sessions in any installed CLI, send them prompts, block until they finish (wait / wait-output / send-and-wait), read their output, and clean up; where available, message claude workers directly (Claude Code cross-session messaging). Use when asked to orchestrate or parallelize work across Codeman sessions, get a second opinion from another CLI or model, watch another session, or start and manage workers. Only usable inside a Codeman-managed session (CODEMAN_MUX=1); refuse to act otherwise.
The English summary is being prepared. Showing the original description.
This skill should be used to spawn specialized OpenAI Codex CLI subagents for code review, debugging, architecture analysis, security audits, refactoring, documentation, comparative evidence adjudication, and autonomous /goal runs. It adds each persona through process-local developer instructions while preserving the project's AGENTS.md chain, including during parallel launches. Supports GPT-6-Astra across low, medium, high, xhigh, max, and ultra reasoning with default or priority service tiers, plus GPT-5.6 and GPT-5.5 models. Triggers on 'delegate to Codex', 'Codex Astra', 'Astra subagent', 'Codex subagent', 'code review agent', 'security audit', 'refactor with Codex', 'goal run', 'autonomous goal', 'have Codex weigh this'.
The English summary is being prepared. Showing the original description.
Manage persistent coding sessions across Claude Code, Codex, Antigravity (agy), Grok Build, and OpenCode engines. Use when orchestrating multi-engine coding agents, starting/sending/stopping sessions, running multi-agent council collaborations, cross-session messaging, ultraplan deep planning, ultrareview parallel code review, autoloop autonomous workspace iteration, ultraapp building deployable web apps from a structured Q&A interview, switching models/tools at runtime, exposing the orchestrator's 78 tools as an MCP server to Hermes Agent / Claude Desktop / Cursor / Cline / Continue / Zed / Windsurf / Goose, or running as an Agent Client Protocol (ACP) agent that Zed / JetBrains / Neovim / Emacs / VS Code / dsh can drive directly. Triggers on "start a session", "send to session", "run council", "ultraplan", "ultrareview", "autoloop", "ultraapp", "Forge tab", "build a web app", "one-click app", "AppSpec", "autonomous iteration", "iterate until goal", "auto research", "switch model", "hand off a session", "session handoff", "switch engine", "continue on codex", "continue on claude", "move this session to another engine", "multi-agent coding", "coding session", "session inbox", "grok session", "grok build", "opencode", "mcp server", "clawo-mcp", "hermes mcp", "model context protocol", "ultracode", "dynamic workflow", "fanout", "fan-out", "best-of-N", "steer turn", "interrupt turn", "fork thread", "rollback turns", "acp", "agent client protocol", "clawo acp", "zed agent", "jetbrains agent", "external agent", "dsh subagent", "deepseek harness", "clawo runs", "run ledger", "session cost", "coding-agent token usage", "spend cap", "budget limit", "maxBudgetUsd", "durable workflow", "resume a run", "verify a coding run", "acceptance contract", "evidence bundle", "did the agent's tests actually pass", "protected tests", "agent edited the tests", "human gate", "repair loop", "clawo workflow", "clawo verify", "clawo solve", "clawo fanout", "fix and verify", "solve from the terminal".
The English summary is being prepared. Showing the original description.
Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.
The English summary is being prepared. Showing the original description.
Add one optional Codex critique to a decision draft produced by council. With explicit consent to send the draft to OpenAI, examine weak conclusions, missing failure scenarios, and overlooked dissent before the user makes the final decision.
Summarize Claude Code token usage and estimated spending from the local ECC metrics log. Review costs by model, session, or date, compare spending with budgets, and export records to CSV while avoiding duplicate counting of session totals.
Use Claude Code to manage Odysseus tasks, email, calendar events, stored facts, and documents through a permission-scoped API. You can also start, inspect logs for, and stop Cookbook model servers using the access granted by your token.
Audit a Claude Code setup for installation problems, broken settings, unused extensions, and duplicated instructions. It reviews local usage evidence, recommends cleanup, and applies approved fixes, with separate confirmation for permission changes.
Review Git changes with the ocr command-line tool and a configured AI model. Get line-level findings grouped by severity for working changes, commits, or branch comparisons, with code fixes applied when explicitly requested.
Check spreadsheet formulas for errors, broken references, inconsistent calculations, and unit mismatches. Review a selected range, one sheet, or an entire financial model, then receive findings ranked by severity with suggested fixes.
Guide changes and reviews for SGLang’s Scheduler, TokenizerManager, and ModelRunner classes. Keep initialization in small, replaceable helpers and separate computation from coordination so large classes retain clear responsibilities and explicit dependencies.
Run performance improvements as a measured workflow in OMX and Codex goal mode. Define an evaluation command and success criteria, make small reversible changes, and retain evidence before declaring the work complete.
Create a saved plan for multiple goals in a repository, then execute it step by step with Codex goal mode. Track progress, verification evidence, review results, and blockers before marking the plan complete.
Build Avalonia screen logic, navigation, and step-by-step wizards using Zafiro and ReactiveUI. The skill guides ViewModels, which manage screen state and behavior, plus commands, automatic section discovery, and connections between views and their logic.
Reduce the memory needed to run large language models with GPTQ quantization, which stores model weights at lower precision. Covers loading compressed models, quantizing your own models, choosing execution backends, and connecting to memory-efficient fine-tuning.
Connect an AI agent client to Memory Proxy, which adds team memory, skills, and knowledge to model requests. The guided workflow checks existing settings, tests connectivity, and writes the appropriate client configuration.
Test mastracode’s terminal interface in Konsole, covering model setup, conversation switching, task state isolation, and display issues. The guide combines interactive checks with scripted rendering tests and troubleshooting steps for common build and configuration problems.