Loading...
Loading...
Found 2,435 Skills
Use when an agent needs to operate the user's real Chrome session — listing tabs, reading the page, clicking, filling, typing into rich editors, pressing keys, evaluating JS, capturing screenshots, and reading console/network buffers. All actions go through CDP and run on backgrounded tabs without stealing focus.
Prepare a research artifact package for conference artifact evaluation, reproducibility review, badges, supplementary material, or post-acceptance artifact release. Use this skill whenever the user needs install instructions, reviewer-facing reproduction commands, Docker or environment checks, data/checkpoint packaging, hardware/runtime estimates, anonymized or public artifact metadata, artifact evaluation forms, or a claim-to-artifact reproducibility audit for ML/AI venues.
Track where a feature sits on Rogers' Diffusion of Innovations bell curve and produce a Go/No-Go release recommendation. Use this skill when deciding whether to expand a feature rollout, evaluating adoption signals, or planning phased release milestones.
Evaluate, select, and contract with vendors and SaaS tools. Use this skill when comparing alternatives, running an RFP, scoring vendors against criteria, negotiating contracts, planning a switch, or assessing a vendor's risk. Triggers on vendor evaluation, RFP, vendor selection, build vs buy, SaaS evaluation, vendor scorecard, vendor comparison, contract negotiation, vendor switch, procurement. Also triggers when a renewal is coming up or when a tool isn't meeting expectations.
Use when writing, reviewing or debugging Luau in a Roblox experience: task.spawn vs task.defer vs task.wait, replacing wait() or spawn(), Deferred events and SignalBehavior, handlers running in the wrong order or not at all, 'attempt to yield across metamethod/C-call boundary', --!strict and the new type solver, typed classes and metatables, Destroy and cleanup, 'server memory keeps growing' or memory leaks, Parallel Luau with Actors and SharedTable, 'not safe to write in parallel', --!native or 'make this script faster', buffers, coroutines.
Modern, type-safe Luau for Roblox, covering --!strict and the new type solver, generics, string interpolation, if-expressions, task library, require-by-string, module/OOP patterns, error handling with retries, buffer/vector, and legacy APIs to avoid. Use when writing, refactoring, or explaining any Roblox script, fixing type errors, or modernizing old Lua code.
This skill should be used when building agent evaluation systems: deterministic checks, regression suites, multi-dimensional rubrics, quality gates, production monitoring, baseline comparison, and outcome measurement for agent pipelines.
Constitution / Operating Model / Practice / Skillがorganizational outcomeとinvariantを維持するかを、formal model・deterministic checks・cold eval・grader controls・context budgetで検証する時に使用する。
Use when reviewing, debugging, or optimizing Luau scripts written directly in Roblox Studio (no Rojo, no VS Code) - memory leaks, dangling connections, client/server mistakes, exploitable RemoteEvents, lag from wait() or polling loops, animation scripts that stutter or stack, DataStore data loss, or "why does my script break on respawn / when a player leaves".
Use when training Roboflow models, diagnosing why a model underperforms, improving accuracy, or setting up a production feedback loop — covers architecture selection, model IDs, checkpoints, Model Evaluation (confusion matrix, per-class metrics, MCP eval tools), the diagnosis-first improvement playbook, and Active Learning through the Project Model Workflow block.
Operate the Agent Evaluation (agent-test) platform through ae-cli: manage evaluation assets, configure and run Agent or preset-output evaluations, and analyze results. Use for platform evaluation tasks and their model, credential, integration, or schedule setup.
Send an independent judge that is not the author: a fresh evaluator subagent that checks finished work against pass criteria written before it was built (evaluator mode), or audits a batch against its source of truth (audit mode), with evidence for every verdict and never a fix. Use when the owner asks for an evaluator, reviewer, auditor or judge, or says 'send a judge', 'evaluate this', 'check my work with a fresh agent', 'get a second agent to review this', 'audit this folder', 'audit my registry', 'verify this against the source of truth', or 'LLM-as-judge'. Runs only when asked; it does not fire on its own at the end of a task. Not for checks a machine can run (tests, schema validation, a search that must return zero), not for hundreds of identical units, and not for fixing anything.