В каталоге 183 730 навыков в 14 категориях.
Executes end-to-end tests for OADP projects with proper environment setup, test selection, and result analysis.
Runs end-to-end or upgrade tests on existing long-running Maestro clusters deployed in Azure AKS
Run the LangSmith evaluation suite and display pass/fail results
do e2e tests, run e2e, validate feature, prove it works, PR proof, frame proof, pnpm evals. Launches iPolloWork on Dayto...
Run the software-factory eval suite from the repo root — deterministic stub mode (the CI PR gate), single-case filtering...
Evaluate the latest Universal Agent run for errors, bottlenecks, and opportunities for improvement. This skill should be...
Execute work items based on their assigned mode (autopilot, confirm, validate). Supports single-item and multi-item (bat...
Use when conducting or designing an exit interview process for departing employees to capture retention insights
This skill should be used when the user wants to design or log an experiment to test a business-model assumption — "desi...
Deploy and run ML experiments on local, remote, Vast.ai, or Modal serverless GPU. Use when user says "run experiment", "...
Run LocalPilot's checks, including type-check, lint, offline smoke tests and the Mocha suites inside a real VS Code Exte...
Run the `fallow` CLI (installed globally, config at .fallowrc.json in repo root) to analyze this codebase for dead code,...
The packaged cold-start campaign workflow - takes an owner with no list, no CRM, and no outbound history from a plain-En...
ฟอร์แมตโค้ดและแก้ไขปัญหาจาก formatter
Discover and run all speckit shell test suites across every feature spec in the repository, then print a consolidated cr...
Executes comprehensive test suite across unit, integration, E2E, database, protocols, and intelligence algorithms
Run cargo-fuzz targets with proper nightly toolchain and options
Acts as a knowledge base providing environment checklists, directory/scratch management, and bash command templates. USE...
Use when preparing to commit or push code and you must satisfy GitHub Actions CI requirements first. Enforce repository-...
Use when asked to set up or repair a repository's GitHub Project configuration, reconcile Project epics or human checkpo...
Build a plan written by /handoff in one long-running session — keep PROGRESS.md, dispatch every unblocked item to a back...
Inspect CCAM dashboard-run history and relate live run handles to persisted Claude Code or Codex sessions. Use when find...
Read Runx's native receipt history and skill catalog, then return deterministic run outcomes, catalog test coverage, and...
Turn a completed task, browser flow, artifact pipeline, failure-recovery trace, or repeatedly refined workflow into a ne...
Use real run evidence, validation failures, source drift, platform drift, and user feedback to plan and, only after expl...
Run the improvement loop: find the one link holding the climb, choose one change against it, prove its path, freeze a pr...
Takes in what a piece of work has to settle, who it is for and when it is due, and names the standing documents it has t...
Run integration tests validating cross-component requirements and system behavior. Executes BDD scenarios, API tests, an...
Build, run, and drive ircx. Use when asked to start ircx, run its tests, build it, take a screenshot of its UI, click th...
Autonomous workflow for processing multiple GitHub issues in parallel with priority-based scheduling and verification.
Provision a Hetzner CCX33 server, deploy the project, run JMH benchmarks, collect results, and destroy the server. Use O...
Run generate_job_data to execute a study definition
Runs the CARLA Leaderboard evaluator over a set of routes with your agent — routes/routes-subset/repetitions/track selec...
Requires Bash 3.2+ and standard POSIX tools; START/END ledger for unattended cron, launchd, systemd or CI jobs to detect...
รัน lint และแก้ code เพื่อให้ผ่าน โดยไม่ใช้ ignore patterns และห้ามแก้ไข config ไฟล์
Run linters after code changes to verify code quality. Use this skill after completing code modifications to catch and f...
[RUN:on-VPS]=>[FIND:IP+port]=>[VERIFY:accessible]=>[REPORT:user]
Run the product's Expo app and its API on this Mac, on an Android phone, an Android emulator or an iOS Simulator, in one...
The warm Docker-free dev loop, `mxcli run --local` — model changes live in about a second, with watch, screenshots, metr...
Build, run, and screenshot Lumina (PySide6 desktop AI agent app). Use when asked to start Lumina, launch main.py, run it...
Start, continue, keep, pause, copy, watch and stop authorised Anabasis v2 campaigns through `bun run runs`: launch a cam...
Manage FABER workflow run lifecycle - create, query, resume, rerun runs
Run Gram meal tracker with hot-reload development servers (backend :8000, frontend :5173)
Shared step of the marketing playbooks (analyze-performance, run-paid-campaigns, research-competitors, email-lifecycle):...
Generate và apply EF Core migration cho một microservice
Autonomně provede naplánovaný milestone: sestaví graf závislostí z issues, ověří v trackeru, že nad plánem proběhlo revi...
Before main skill execution, perform guardrail checks.
Run nx format, lint, test, and build on affected or specified projects, then fix unambiguous failures
Run Nx generators with prioritization for workspace-plugin generators. Use this when generating code, scaffolding new fe...
Launch the agent-office desktop app locally and verify a change in the real UI (screenshot). Use when asked to run, star...
Run and test directly on the server. No local dev environment needed. What you build is what goes live.
Runs standard-format scenarios through ScenarioRunner — ASAM OpenSCENARIO 1.x (.xosc, via --openscenario, with catalogs...
Runs a brand's organic social: how each platform works now, a strategy per platform and two weeks of posts in the brand'...
Launch the pages/ site (Vite dev server or production build) and drive it in a real browser to screenshot it. Use when a...
Runs the paid leg of an approved plan: checks tracking, pages and stock before money moves, then stages one weekly propo...
Compare React Doctor diagnostics for a GitHub pull request (PR) with Daytona. Use when asked to run parity, check a PR f...
Run every remaining phase of a workstream unattended. Thin entry point for the execution skill's workstream scope.
Execute and monitor Harness pipeline runs via MCP tools. Find pipelines, provide runtime inputs, trigger executions, mon...
Run the full data science pipeline: validate raw data, preprocess, engineer features, train model, and evaluate. Use thi...
Plan the scope of a run by discovering available work items and suggesting groupings. Invoked before run-execute.
Execute a continuous plan deterministically by following the skill sequence. Use after continuous-planner creates a plan...
Interpret the user's high-level research intent into `RUN_POLICY.yaml` and `state/POLICY_DECISION.json`.
Reconstruct what a finished agent run or overnight branch actually did — plan lineage, commit ownership, working/not-wor...
Premortem on a business plan that writes how it fails and gives each top risk a warning signal, a kill criterion set in...
รัน preview build เพื่อทดสอบก่อน deploy จริง
Run one or more Lanekeeper prompts end to end with subagents, spec first. Plans from the prompt, stops for human approva...
Run saved prompts in isolated sub-agent contexts, single, sequential or parallel. Carries its own DOCTYPE: a declared ou...
Step-by-step execution of the OWC protocol with mandatory checkpoint at each step. Prevents skipping steps (including ve...
Build and run the Nomos Terraform Remote State Provider. Use this when testing the provider, verifying functionality, or...
Run pw workflow commands reliably from a non-interactive shell by calling prompt_workflow.bat directly instead of relyin...
Execute Python snippets for data filtering, aggregation, and cross-tool joins. Use when you need to sort, filter, comput...
This skill should be used when user asks to "run QA", "verify real playback", "test provider connections", or "check web...
Run QA regression using `qa-use` toolkit
Ejecuta la suite completa de pruebas (tipos, pruebas unitarias y E2E con Playwright) y reporta el estado general del pro...
Automatically run RAG evaluations using the local framework and output a benchmark report.
Auto-detect platforms, release ไปยัง external platforms, gen CHANGELOG
Generate the styled HTML closeout report after a run, round, or notable package landing — what shipped, what changed vis...
Full research workflow orchestration from knowledge elicitation to consolidated findings. PROACTIVELY activate for: (1)...
Guide for designing Run resources in OptAIC. Use when creating PipelineRun, ExperimentRun, BacktestRun, PortfolioOptimiz...
alias → /update-review-cli-then-run (รัน review CLI วิเคราะห์ผล และแนะนำ action items)
Runs a route through ScenarioRunner's RouteScenario mode (--route / --route-id) with an autonomous agent driving the ego...
Use this skill to drive a research question (RQ) end-to-end: validate the RQ README, generate a fill batch-plan, start t...
รัน ast-grep scan เพื่อตรวจสอบ codebase ด้วย AST-based patterns
Runs a single ScenarioRunner Python scenario (or a whole group) against a running CARLA server — FollowLeadingVehicle, C...
Runs Scenic probabilistic scenarios against a running CARLA server with the `scenic FILE --simulate --2d` CLI — the carl...
Navigate the AI-SDLC workflow for a given work item or artifact: report where it is in the lifecycle and what to do next...
Start the Gambit game server on 0.0.0.0:1234. Use when the user wants to run just the server, test server functionality,...
Run shell commands where long (many tokens) output is expected. Use when you need to
Run an Applora research workflow from a prepared brief or a direct Shopify App Store question. Use for selected template...
Create or run simulation features for analyzing work flow through value streams
Run and analyze one or multiple PDE simulations.
Build, install, launch, and screenshot an iOS app in the Simulator to verify a change visually. Use when the user wants...
Build and launch the app in the iOS Simulator. Automatically selects an appropriate simulator device, boots it if needed...
Run Playwright smoke tests, debug failures, and verify fixes. Use for smoke, e2e, Playwright, or pre-ship browser verifi...
Inspect an unfamiliar repository, interpret a broad Markdown user journey at runtime, operate the real product through i...
Use this skill when executing the text-only replication stage of the appraisal-transfer project, including dataset prepa...
Use this skill when executing the cross-modal transfer stage of the appraisal project, including image-side data prepara...
Manage FlowRun state at `.flow/runs/<ISO-timestamp-id>/run.yaml` — create runs at command entry, write activity records...
Display current run status and progress. Shows work item, mode, duration, and files changed.
Show the state of the active research run: stages completed, branch scoreboard, selected solution, grounding ratio, arti...