124 skills · sorted by relevance
Turn OpenAPI specifications, GraphQL endpoints, MCP servers, or custom JavaScript functions into bash commands and a JavaScript API. The skill guides implementation so agents can call these tools from the isolated execution environment provided by just-bash.
[omh] Unsure whether Codex or Claude Code is ready: executor runtime readiness - compare Codex, Claude Code, Hermes coding, and oh-my runtimes by tools and handoff mode; use external-connector-readiness for a named plugin or API, and toolbelt-readiness for the whole capability inventory. Use when the user says: executor-runtime-readiness, executor readiness, runtime readiness, codex readiness, claude code readiness, hermes coding readiness, executor tools, missing tools.
The English summary is being prepared. Showing the original description.
Inspect imports and agent patterns in existing Python code to identify its framework and recommend an Omnigent executor, the component that runs the agent. Explain unsupported frameworks and suggest available next steps.
Look up how to configure and organize Omnigent agents. Use examples to choose an executor, the agent's runtime, arrange instructions and skills, add local tools or external services, and define specialized child agents.
The Arbor executor workflow: clone the repo from the git bundle your brief hands you, implement and evaluate exactly ONE hypothesis with the file tools, then report structured results via worker_complete. Preloaded automatically on arbor-executor task workers. Never touch the held-out test split.
The English summary is being prepared. Showing the original description.
ペネトレーションテストを対話的に実行するスキル。認可確認(Authorization Gate)→カテゴリ選択（Methodology, Reconnaissance, Scanning, VulnerabilityScanning, WebAppTesting, APITesting, PasswordAttacks, Exploitation, PrivilegeEscalation, ActiveDirectory, PostExploitation, WirelessAttacks, NetworkAttacks, SocialEngineering, CloudPentesting, MobileAppTesting, ContainerK8s, BinaryExploitation, OWASPTop10, Reporting, EmailSecurity, DatabaseAttacks, VPNRemoteAccess の全23カテゴリ）→ツール選択→コマンド実行→発見記録(Finding)→レポート生成をステップバイステップで進行。スコープ/除外チェック・ガードレール付き。「ペンテスト実行」「pentest」「侵入テスト」「脆弱性診断」「セキュリティテスト」「pentest executor」で発火。
The English summary is being prepared. Showing the original description.
Agent-to-Agent (A2A) executor implementation patterns for task handling, execution management, and agent coordination. Use when building A2A executors, implementing task handlers, creating agent execution flows, or when user mentions A2A protocol, task execution, agent executors, task handlers, or agent coordination.
The English summary is being prepared. Showing the original description.
Generate a report with predictable output for acceptance tests of disposable executors, or temporary task runners. Retrieve agent settings, run the supplied report script with specified arguments, and publish the resulting file to S3.
[omh] Choosing between coding agents on evidence: compare executor or agent choices on reproducible tasks using quality, cost, time, tool, and evidence metrics. Use when the user says: agent-evaluation, agent evaluation, agent eval, agent benchmark, executor evaluation, executor benchmark, compare agents, compare codex claude.
The English summary is being prepared. Showing the original description.
Test agent features across local and remote execution environments using integration tests, which check components working together. Covers Docker and Wine setups, test helpers, and configuration-specific skips for the app-server and exec-server split.
Configure tools and skills for sub-agents before dispatching development tasks. Role presets cover implementation, planning, reviews, testing, and verification, with defined boundaries for what each agent should do and whether it may modify files.
Run a task through your Executor Cloud tool catalog - one MCP endpoint proxying every integration you connected (MCP servers, OpenAPI specs, GraphQL APIs), with per-tool allow/approve/block policies. OAuth Connect via the dashboard MCP panel.
The English summary is being prepared. Showing the original description.
MANUAL-ONLY — load solely when the human owner types `/pl`, uses `$pl`, or asks you to act as the Project Lead (PL). Supervise one project lane and its executor agents. A charter or dispatch means: you are an EXECUTOR, not the PL.
The English summary is being prepared. Showing the original description.
Use when you need to apply Java concurrency best practices — including thread safety fundamentals, ExecutorService thread pool management, concurrent design patterns like Producer-Consumer, asynchronous programming with CompletableFuture, immutability and safe publication, deadlock avoidance, virtual threads, structured concurrency, scoped values, backpressure, cancellation discipline, and observability for concurrent systems. This should trigger for requests such as Review Java code for concurrency; Review Java code for thread safety; Fix race conditions in Java concurrency code; Choose ExecutorService or virtual threads in Java; Improve synchronization and shared mutable state handling; Apply structured concurrency for related Java subtasks. Part of Plinth Toolkit
The English summary is being prepared. Showing the original description.
Use ExecuTorch to export PyTorch models to edge runtime artifacts, build host/device runtimes, choose delegates, profile/debug execution, and operate specialized Qualcomm, Cortex-M, LLM, and binary-size workflows.
The English summary is being prepared. Showing the original description.
Evaluates assumption, rejection, and assignment decisions for executory contracts and unexpired leases in bankruptcy. Use when analyzing contract decisions, evaluating lease rejections, or modeling cure cost exposure.
The English summary is being prepared. Showing the original description.
Execute TDD task pairs autonomously with RED-GREEN-REFACTOR verification. Orchestrates wave-based execution with strategic parallelism, routing TDD tasks to tdd-executor agents and non-TDD tasks to standard task-executor. Use when user says "execute tdd tasks", "run tdd tasks", "start tdd execution", or wants to execute TDD-paired tasks from create-tdd-tasks.
The English summary is being prepared. Showing the original description.
Split a dirty working tree into single-concern Conventional Commits. The deterministic inventory.mjs helper groups dirty paths by concern (docs, source + paired test, config, governance); main context refines the grouping and presents a commit plan. Read-only until the user approves the plan — it never stages, never commits, never touches consent paths. Disjoint from the commit skill (Phase 11 executor): the planner proposes a split; the executor lands one consented commit. Use when a working tree has accumulated heterogeneous changes that should not land as one commit.
The English summary is being prepared. Showing the original description.
Authors reproducible bioinformatics pipelines with Snakemake - rules wired by output-file pattern, wildcards and expand() for sample fan-out, checkpoints for runtime-unknown outputs, resource/retry escalation, and conda/container software deployment on HPC and cloud. Use when deciding rule-based (Snakemake) vs channel/dataflow (Nextflow) authoring; wiring rules by OUTPUT-file pattern rather than imperative order; using wildcards + expand() for sample fan-out and constraining them to stop silent mis-routing; adding checkpoints when the set of outputs is unknown until a step runs (dynamic DAG); diagnosing why a job reran (or did not) under the mtime-plus-provenance trigger set; escalating memory on retry for OOM-killed jobs; and porting a Snakemake 7 `--cluster`/remote-provider command to the Snakemake 8+ executor-plugin and storage-plugin model (snakemake-executor-plugin-slurm) with `--software-deployment-method`.
The English summary is being prepared. Showing the original description.
Specifies bounded DAG execution contracts and evaluates executor receipts for dispatch, cancellation, joins, and effect reconciliation. Use when an implementation must bind a planned DAG to named runtime controls. NOT for claiming an executor is active, spawning agents, or certifying an effect from a plan.
The English summary is being prepared. Showing the original description.
Build production-grade AI agents from scratch using patterns inspired by production-grade agentic systems like Claude Code. Covers two audiences — (1) workflow builders who need planner+executor pipelines, human-in-the-loop checkpoints, and multi-agent orchestration, and (2) application embedders who need HTTP/SSE APIs, multi-user session management, and React frontend integration. Use when asked to build an AI agent, create a coding assistant, embed an agent in an app, build an API agent, clone Claude Code, build a CLI agent, design an agent architecture, scaffold an agentic system, or automate a multi-step workflow. Triggers on keywords like agent builder, agent blueprint, coding assistant, CLI agent, agentic tool, claude code clone, agent scaffold, agent architecture, workflow automation, multi-agent, planner executor, SSE streaming, agent API.
The English summary is being prepared. Showing the original description.
Build, run, and troubleshoot data processing pipelines with Nextflow and nf-core. The skill guides modular workflow development, input preparation, testing, cached restarts, and configuration for local computers, computing clusters, or cloud environments.
Guides contributors through adding a new programming language to Airflow, covering SDK structure, runtime coordination, communication rules, executable packaging, tests, and the documentation and configuration changes needed for a pull request.
Improve slow Apache Spark jobs by reviewing data partitions, caching, memory settings, and shuffles, which move data between workers. Use the guidance to investigate bottlenecks and tune pipelines for larger datasets.