메뉴
SkillsMP는 AhmiDarrow/RemedyAI에서 54개의 skill을 수집했습니다. skill을 열어 소스와 세부 정보를 확인하세요.
수집된 skill 54개 중 40개를 표시합니다.
Blast-radius protocol before code changes — name the surface, list coupled neighbors, run paired checks, and smoke UI/chrome/messengers that unit tests miss. Use when implementing, fixing, refactoring, reviewing risk, or when the user says don't break…
원문 언어: 영어
Default ship discipline for any serious project — blast radius first, then fix, test, update code/docs, build, commit, wait for CI, publish only if green. Use when the user says ship, release, finish, or "test everything then update/build/commit/CI/PyPI".
원문 언어: 영어
Make 2D game art with local ComfyUI txt2img plus a Pillow post-process script: backgrounds, seamless tiles, 9-slice UI, key art, single sprites, then slice/pack/quantize/alpha-key/downscale and set Godot import flags. Use when the owner asks for sprites,…
원문 언어: 영어
Use for materials and device work: structure-property-processing reasoning, characterisation (XRD, SEM/TEM/EDS, AFM, DSC/TGA), mechanical testing and Weibull statistics for brittle failure, FEA mesh convergence and material models, SPICE and CFD sanity…
원문 언어: 영어
Use for sequence and omics work: FASTQ/BAM/VCF/GTF/BED handling and their coordinate conventions, reference builds and liftover, read QC and trimming, alignment and variant calling, RNA-seq and single-cell analysis, Snakemake and Nextflow pipelines, and…
원문 언어: 영어
Use when the work involves molecular structures, reactions, spectra, computational chemistry, crystallography or chemical databases. Covers SMILES/InChI round-trips, RDKit standardisation and fingerprints, NMR/IR/MS interpretation workflows, DFT method and…
원문 언어: 영어
Human-subject studies run to the standard the field expects: choosing a design that can answer the question, randomisation and blinding, endpoints fixed before data, ITT analysis populations, survival methods, prospective registration, CONSORT/STROBE/PRISMA…
원문 언어: 영어
Simulation and numerics you can defend: floating-point and conditioning understood before blaming the physics, solvers chosen for the problem, convergence and refinement studies as evidence, verification separated from validation, benchmarks with warm-up and…
원문 언어: 영어
Use for earth, ocean, atmosphere and ecology data work: NetCDF/CF, GRIB, Zarr, HDF5, GeoTIFF and vector formats, coordinate reference systems, regridding and land/sea masks, non-standard calendars, anomalies and baselines, trends with autocorrelation,…
원문 언어: 영어
Use for bench biology: designing and reading wet-lab experiments, choosing controls, telling biological from technical replicates, randomisation and blinding, batch effects, dose-response curves, image and blot quantification, antibody and cell-line…
원문 언어: 영어
Empirical machine-learning claims that survive scrutiny: a baseline strong enough to be worth beating, splits that respect grouping and time, leakage hunted before any number is trusted, ablations that isolate one change, results reported as a spread over…
원문 언어: 영어
Brain data from acquisition to inference: what each modality actually measures (BOLD haemodynamics, EEG/MEG timing, spikes and LFP, calcium kinetics, optogenetic controls), BIDS layout and NIfTI/EDF/NWB formats, preprocessing choices that move results, and…
원문 언어: 영어
Use when the work is a physical measurement, a fit, an error budget, a detector or instrument analysis, or a simulation that has to agree with known physics. Covers dimensional checks, CODATA constants, Type A/B uncertainty and coverage factors, chi-square…
원문 언어: 영어
The research loop for any field: sharpen the question until it can be refuted, find what is known and what is disputed, fix the analysis before the data, run it, interpret against effect size and uncertainty, write it so someone else can repeat it, and leave…
원문 언어: 영어
Use when a claim is being made about people from survey, administrative, behavioural or interview data: sampling and what it licenses, instrument and scale design, measurement validity and reliability, experiments versus quasi-experiments, causal inference…
원문 언어: 영어
Choose, run and report the right analysis: descriptives before inference, test selection driven by the design, assumptions checked with a statistic rather than assumed, effect sizes with intervals as the headline and p-values as support, multiplicity handled,…
원문 언어: 영어
Use when the data is text and the claim is empirical: building and licensing a corpus, sampling frames for documents, cleaning and tokenisation that does not destroy the signal, annotation as a measurement instrument with multiple coders and agreement,…
원문 언어: 영어
Build Rust games with Bevy: ECS mental model, plugins, schedules, states, assets, 2D sprites, fast iteration (cargo check, dynamic_linking, opt-level), backgrounded cargo run plus game_playtest. Use when the owner mentions Bevy or Cargo.toml depends on bevy.
원문 언어: 영어
How to use Remedy's optional MCP client bridge for game editors: the owner lists servers in config.toml mcp_servers (name=command), their tools show up as mcp_<name>_<tool>, and a decision table says when to use them versus native headless tools. Covers…
원문 언어: 영어
The studio loop for making a game with the owner: pin the fantasy and core loop, write a short GDD, build a vertical slice, iterate on feel, add content, polish and export. Use when the owner wants to make, prototype or playtest a game of any genre; pairs…
원문 언어: 영어
Work inside a Godot 4.x project: find the engine, read project.godot, edit scenes and GDScript/C#, verify headless after every change, playtest windowed, export. Use whenever the project has project.godot or the owner mentions Godot, GDScript, .tscn,…
원문 언어: 영어
Build LÖVE (love2d) games: main.lua callbacks, conf.lua, locating the love binary, windowed launch in the background, luac/luacheck as cheap oracles, busted tests for pure Lua, sprites/quads/animation, fused executables and .love export. Use when the project…
원문 언어: 영어
Build Python games with pygame (or pygame-ce) and arcade: event loop, clock and delta time, surfaces and sprite groups, arcade Window/View/SpriteList, a main.py layout whose logic stays testable without a display, pytest with SDL_VIDEODRIVER=dummy, windowed…
원문 언어: 영어
Work on a Unity project from the outside: fingerprint the version, write and fix C# MonoBehaviours/ScriptableObjects, run Edit/PlayMode tests and builds through the editor's batchmode CLI, wire CI. Use when the project has ProjectSettings/ProjectVersion.txt…
원문 언어: 영어
Work on an Unreal Engine 5 project from the shell: read the .uproject, decide C++ vs Blueprint, build with UnrealBuildTool, cook/package with RunUAT BuildCookRun, run Automation tests via UnrealEditor-Cmd, generate project files. Use when a *.uproject exists…
원문 언어: 영어
Build and verify browser games with Phaser 3 or PixiJS on Vite: scaffold, scene lifecycle, assets, input, arcade physics, logic tests with vitest, dev-server playtest through the browser, production build, static hosting and itch.io HTML5 zips. Use when the…
원문 언어: 영어
When changing Grove, Studio, Settings, or chat chrome, keep WebUI (browser on :7400) at parity with Tauri. Grove unmounts off-surface; serve mounts SPA once at start. Use after any desktop/src UI change the owner will also see in the browser.
원문 언어: 영어
Run one test-gated self-improvement round on the Remedy codebase: draft a change, snapshot the diff, gate it with tests only, apply (restart sidecar / rebuild SPA) on green or roll back on red, record in the ledger, and continue. Use when self-improve,…
원문 언어: 영어
After green verify, push and optionally create a GitHub release without rewriting green code.
원문 언어: 영어
Meta-loop for Remedy developing herself — self-inject, change-safety, unit tests, security gauntlet, product soak, stress, then ship gates. Use when self-dev, hot-inject, improve the codebase, work on RemedyAI monorepo end-to-end, or "run the full quality…
원문 언어: 영어
Full product soak for Remedy — API health, computer-use, plan mode, browser rail, concurrency, docs check, and sign-off artifacts. Use when soak, product soak, e2e live, computer-use checklist, or pre-merge confidence on desktop+API.
원문 언어: 영어
Live stress and break suites for Remedy API/desktop — multi-turn storms, concurrent sessions, multi-provider rotation, adversarial break battery. Use when stress, load, break suite, hammer, continuous test, or find weak spots.
원문 언어: 영어
Default ship discipline for any serious project — blast radius first, then fix, test, update code/docs, build, commit, wait for CI, publish only if green. Use when the user says ship, release, finish, or "test everything then update/build/commit/CI/PyPI".
원문 언어: 영어
Security gauntlet for Remedy — unit jail/SSRF/auth suite plus controlled live red-team probes. Use when security audit, red-team, gauntlet, harden, jail, SSRF, auth bypass, or before ship after security-sensitive changes.
원문 언어: 영어
Small, behavior-preserving refactors with verification.
원문 언어: 영어
Blast-radius protocol before code changes — name the surface, list coupled neighbors, run paired checks, and smoke UI/chrome/messengers that unit tests miss. Use when implementing, fixing, refactoring, reviewing risk, or when the user says don't break…
원문 언어: 영어
Work with GitHub using the gh CLI and git — PRs, issues, checks, releases, forks, reviews, and repo hygiene. Prefer gh over raw API curl when available.
원문 언어: 영어
Local ComfyUI image generation end-to-end: from a blank machine (download, install, start, fetch models, workflows) through queue/poll/download and chat embeds. Defaults to http://127.0.0.1:8188 (Flux.2 Klein + Qwen3-ready). Use when the user wants images and…
원문 언어: 영어
Structure a decision with options, trade-offs, recommendation, and store it.
원문 언어: 영어
Structured UX/UI and product design critique with clear priorities.
원문 언어: 영어