Skip to content

ericrisco/rsc-harness / skills/electron

electron

Verified

Use when building, hardening, or shipping a cross-platform Electron desktop app — main/renderer/preload process model, typed contextBridge IPC, locking down nodeIntegration/contextIsolation/sandbox/CSP, or packaging with signing and auto-update. NOT a Rust-backed shell on the native webview (that is tauri), nor the web UI inside it (that is react).

FileKindSize
SKILL.mdskill md11.4 KB
evals/README.mdmarkdown1009 B
evals/cases.yamlconfig2.1 KB
references/packaging-and-updates.mdmarkdown4.3 KB
references/security-and-ipc.mdmarkdown5.8 KB
scripts/verify.shexecutablescript5.8 KB

evals/README.md

View on GitHub
# electron evals

`cases.yaml` is the source of truth. There is no fully automated runner: triggering and
capability are graded **semantically** by an agent harness (an agent with the catalog's sibling
names available for routing) plus a human or judge-agent spot-check, because "did it route to
tauri" and "did it set the secure baseline" are intent judgments, not string matches. For
triggering, feed each `should_trigger` / `should_not_trigger` prompt to a fresh session 3–5
times and record whether the electron skill fires (and, for near-misses, whether it hands off to
the named `route_to` sibling). For capability, answer each scenario once with the skill and once
without, then score against its `must_include` rubric — the skill passes only if the with-skill
answer covers the rubric and clearly beats the baseline. The one mechanical check is
`scripts/verify.sh`: run it against any code the capability case produces to confirm the
hardening is real (it exits non-zero on any insecure pattern).
brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).Stars: 322kUpdated Claude CodeCodexVerifiedInstall
brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).Stars: 198kUpdated Claude CodeCodexVerifiedInstall