Przydatne Agent Skills ocenione według realnego użycia

changhochien

AI film director for scene blocking, shot composition, visual storytelling. Use when: directing, blocking, shot design, coverage, cinematography. Generates image prompts for scenes. Keywords: film, directing, blocking, shots, visuals.

Instalacje / 1h: 1
GitHub Stars: 0
Aktualizacja: 24 mar

MIT7 Pliki

comparing-competitors

Use when you need to benchmark a provider against its competitors on the same eval prompt, or write a defensible "you vs them" narrative.

Instalacje / 1h: 1
GitHub Stars: 0
Aktualizacja: 20 paź

designing-agent-error-messages

Audit and rewrite error messages, exceptions, and API/SDK/CLI failure output so an AI agent (and a human) can self-correct without leaving the terminal. Use when designing or reviewing how a tool fails — error strings, HTTP error bodies, auth/credential errors, CLI errors, thrown exceptions — especially for libraries, APIs, and CLIs that AI agents consume. Grounded in patterns from 2027.dev's evals of 136 dev tools across 3,500+ agent runs.

Instalacje / 1h: 1
GitHub Stars: 0
Aktualizacja: 20 paź

filing-feedback

When and how to report a platform bug, confusing behaviour, or missing feature through sendfeedback.

Instalacje / 1h: 1
GitHub Stars: 0
Aktualizacja: 20 paź

harnesses-and-models

Use when a question involves which coding agent (harness) or model ran an eval, comparing runs across harnesses/models, or pinning a harness+model when triggering a run.

Instalacje / 1h: 1
GitHub Stars: 0
Aktualizacja: 20 paź

interpreting-scores

Use when reading or explaining an eval run's metrics, insights, or overall experience, or when a run has no score.

Instalacje / 1h: 1
GitHub Stars: 0
Aktualizacja: 20 paź

linking-to-the-dashboard

Use when citing a run, prompt, or trace moment in your answer — always give the user a clickable dashboard link instead of a bare slug or id.

Instalacje / 1h: 1
GitHub Stars: 0
Aktualizacja: 20 paź

reading-an-agent-trace

Use when you need to reconstruct what an agent actually did during an eval run, or localize where it got stuck, from the session log.

Instalacje / 1h: 1
GitHub Stars: 0
Aktualizacja: 20 paź

spotting-friction

Use when you need to identify what hurt an agent's experience in an eval run and turn it into a concrete fix the dev-tool owner can ship.

Instalacje / 1h: 1
GitHub Stars: 0
Aktualizacja: 20 paź

vent-friction

Use the moment you hit friction with an EXTERNAL developer tool — an SDK, API, CLI, database, auth, or cloud provider — a bug, a misleading or missing error, an undocumented gotcha, a broken default, a deprecated-without-warning change, a painful auth/login flow, or you just burned real time fighting a third-party tool. This includes catching yourself venting about it ("ugh why does X…", "wait, that's not in the docs", "finally got Y working after all that", "fuck, Z silently…"). Also use when t

Instalacje / 1h: 1
GitHub Stars: 0
Aktualizacja: 20 paź

flatbedj

luau-best-practices

Use when writing, reviewing, or refactoring Luau code for Roblox - modules, services, controllers, error handling (pcall), memory leaks and connection cleanup, server-authoritative security, input validation, naming conventions, or project organization. Triggers include "best practices", "clean code", "code review", "refactor", "memory leak", "server authority".

Instalacje / 1h: 1
GitHub Stars: 0
Aktualizacja: 20 wrz

6 Pliki

flatbedj

roblox-networking

Use for Roblox multiplayer communication across the client-server boundary: designing RemoteEvent, UnreliableRemoteEvent, and RemoteFunction flows; validating client requests; handling replication-aware gameplay; applying rate limits and anti-exploit checks; reasoning about network ownership, server-authority patterns, Input Action System use in authoritative gameplay, and streaming-sensitive multiplayer correctness.

Instalacje / 1h: 1
GitHub Stars: 0
Aktualizacja: 20 wrz

9 Pliki

design-taste-frontend

Senior UI/UX Engineer. Architect digital interfaces overriding default LLM biases. Enforces metric-based rules, strict component architecture, CSS hardware acceleration, and balanced design engineering.

Instalacje / 1h: 1
GitHub Stars: 0
Aktualizacja: 21 kwi

full-output-enforcement

Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.

Instalacje / 1h: 1
GitHub Stars: 0
Aktualizacja: 21 kwi

high-end-visual-design

Teaches the AI to design like a high-end agency. Defines the exact fonts, spacing, shadows, card structures, and animations that make a website feel expensive. Blocks all the common defaults that make AI designs look cheap or generic.

Instalacje / 1h: 1
GitHub Stars: 0
Aktualizacja: 21 kwi

industrial-brutalist-ui

Raw mechanical interfaces fusing Swiss typographic print with military terminal aesthetics. Rigid grids, extreme type scale contrast, utilitarian color, analog degradation effects. For data-heavy dashboards, portfolios, or editorial sites that need to feel like declassified blueprints.

Instalacje / 1h: 1
GitHub Stars: 0
Aktualizacja: 21 kwi

minimalist-ui

Clean editorial-style interfaces. Warm monochrome palette, typographic contrast, flat bento grids, muted pastels. No gradients, no heavy shadows.

Instalacje / 1h: 1
GitHub Stars: 0
Aktualizacja: 21 kwi

stitch-design-taste

Semantic Design System Skill for Google Stitch. Generates agent-friendly DESIGN.md files that enforce premium, anti-generic UI standards — strict typography, calibrated color, asymmetric layouts, perpetual micro-motion, and hardware-accelerated performance.

Instalacje / 1h: 1
GitHub Stars: 0
Aktualizacja: 21 kwi

MIT2 Pliki

marks97

compact-handoff

Compact the current conversation into a large standalone handoff file on disk, then open a BRAND NEW Claude Code session named after the current chat with an incremented counter, seeded with only a pointer to that file, leaving the current chat fully intact. Use this whenever the user wants a clean context window without losing what was learned, or says any of — "compact to a new chat", "compact but start fresh", "carry this over to a new session", "hand this off", "new chat with this context",

Instalacje / 1h: 1
GitHub Stars: 0
Aktualizacja: 1 paź

MIT5 Pliki

wrestle-r

russelore

Write in Russel Daniel Paul's raw conversational voice for assistant replies, blogs, personal website copy and Git commit messages. Use when Russelore is requested or when writing for Russel. Keep his loose grammar, lingo, dry asides and short casual commit names, with light swearing.

Instalacje / 1h: 1
GitHub Stars: 0
Aktualizacja: 20 paź

6 Pliki

bytedance

github-deep-research

Conduct multi-round deep research on any GitHub Repo. Use when users request comprehensive analysis, timeline reconstruction, competitive analysis, or in-depth investigation of GitHub. Produces structured markdown reports with executive summaries, chronological timelines, metrics analysis, and Mermaid diagrams. Triggers on Github repository URL or open source projects.

Instalacje / 1h: 1
GitHub Stars: 84,2 tys.
Aktualizacja: 20 paź

MIT3 Pliki

diegosouzapw

cli-setup

Run initial setup, configure global CLI settings, manage environment variables, check for updates, and configure autostart via the CLI setup and config commands.

Instalacje / 1h: 1
GitHub Stars: 78,9 tys.
Aktualizacja: 20 paź

mukul975

deploying-tailscale-for-zero-trust-vpn

Deploys and configures Tailscale (or self-hosted Headscale) as a WireGuard-based zero trust mesh VPN, setting up identity-aware ACLs, exit nodes, subnet routers, and MagicDNS for encrypted peer-to-peer connectivity. Use when replacing traditional VPN servers with an identity-authenticated mesh network or enforcing granular per-device access control lists.

Instalacje / 1h: 1
GitHub Stars: 34,8 tys.
Aktualizacja: 31 sie

Apache-2.08 Pliki