CorrectRoadH

Use when working in this repository after receiving recurring coding feedback, adding or reviewing durable lint guardrails from AGENTS.md, updating rules/*.md, or finishing changes that should be checked by harness-lint.

Use when working in this repository and needing package management, development, build, lint, test, formatting, or JS tool execution through the Vite+ toolchain.

Build and verify real-Postgres Go tests and thin transport smoke for tracking behavior.

Build and verify page-flow and E2E coverage for the tracking browser surface.

Build cross-layer regression coverage that ties browser-visible behavior to backend truth.

Harden shared test infrastructure, runtime readiness, schema setup, and parallel lane behavior.

Update backend timer/time-entry contracts, regressions, and source docs for the timer refactor mission.

Audit and finalize inline source-document status blocks for the timer refactor mission.

Use this skill when asked to prove that a locally-sourced (non-repo) niceeval Skill fixture was installed and is readable inside the sandbox. It exists purely as an e2e fixture with a unique marker string, not as real guidance.

Find and remove AI slop — the generic, machine-default visual and copy tics of vibe-coded products — from a web project. Use when the user asks to "kill AI slop", "de-slop", "remove the AI look", "make this not look AI-generated", or clean up a landing page / UI / docs that feels templated. Detects and fixes: indigo→violet gradients, gradient-clip headline text, warm amber/stone "cozy" palettes, the default semantic palette (info-blue / tip-amber / success-green / error-red), one-hue status boxes, atmospheric/ambient gradients, serif-italic emphasis on one word, serif where sans belongs, decorative strikes and highlights, highlighted keywords in copy, AI copywriting voice ("not just X — it's Y"), emoji everywhere, glowing status dots, rounded colored-left-border callouts, pastel rounded-square icon tiles, glassmorphism and over-rounding, oversized drop shadows, corners that don't nest, badge & pill spam, AI-drawn SVG icons, icons in a tint of themselves, all-caps card grids, and the "tasteful terminal". Works

Use this skill when the current task touches Effect code, reviews behavior implemented with Effect, or depends on Effect patterns, services, layers, schemas, streams, runtimes, resource management, retries, observability, testing, or typed error handling. Do not trigger it merely because the repository contains Effect if the task is unrelated documentation, site copy, README text, or non-Effect code.

Use when installing, configuring, migrating, authoring, debugging, or fixing `harness-lint` rules in a code repository. Covers command setup, shared/local rule packs, config upgrades, converting recurring feedback into local rules, writing rule Markdown/GritQL, inspecting a specific rule after lint failures, and fixing code without weakening rules.

Close the Lint Driven Development loop: review this session's corrections and feedback and capture any reusable constraint as a harness-lint rule. Trigger: /harness-lint-capture, "capture this as a lint rule", "close the LDD loop".

Read and write tasks in an Obsidian vault through the Task Center plugin's CLI. Use when the user wants to list, schedule, complete, abandon, nest, or add tasks — or when they want estimate-accuracy / review / agent-brief stats. Obsidian must be running with the `task-center` plugin enabled; all verbs are namespaced `obsidian task-center:<verb>`.