Impeccable
bestofjs/bestofjs
A skill your agent uses when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a…
Develop or review Harness Anything GUI pages and shared components using its existing design system, entity navigation, motion preferences, and background Electron verification.
$ npx skills add FairladyZ625/harness-anything --skill harness-gui -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install FairladyZ625/harness-anything harness-gui --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/FairladyZ625/harness-anything.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/harness-gui .claude/skills/harness-gui && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "harness-gui" agent skill from https://github.com/FairladyZ625/harness-anything/tree/main/skills/harness-gui into .claude/skills/harness-gui/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-gui", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/FairladyZ625/harness-anything/tree/main/skills/harness-guiType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add FairladyZ625/harness-anything --skill harness-gui -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install FairladyZ625/harness-anything harness-gui --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/FairladyZ625/harness-anything.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/harness-gui .agents/skills/harness-gui && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "harness-gui" agent skill from https://github.com/FairladyZ625/harness-anything/tree/main/skills/harness-gui into .agents/skills/harness-gui/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-gui", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add FairladyZ625/harness-anything --skill harness-gui -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install FairladyZ625/harness-anything harness-gui --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/FairladyZ625/harness-anything.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/harness-gui .cursor/skills/harness-gui && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "harness-gui" agent skill from https://github.com/FairladyZ625/harness-anything/tree/main/skills/harness-gui into .cursor/skills/harness-gui/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-gui", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/FairladyZ625/harness-anything.git --path skills/harness-gui--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add FairladyZ625/harness-anything --skill harness-gui -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install FairladyZ625/harness-anything harness-gui --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/FairladyZ625/harness-anything.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/harness-gui .gemini/skills/harness-gui && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "harness-gui" agent skill from https://github.com/FairladyZ625/harness-anything/tree/main/skills/harness-gui into .gemini/skills/harness-gui/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-gui", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install FairladyZ625/harness-anything harness-guiInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add FairladyZ625/harness-anything --skill harness-gui -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/FairladyZ625/harness-anything.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/harness-gui .github/skills/harness-gui && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "harness-gui" agent skill from https://github.com/FairladyZ625/harness-anything/tree/main/skills/harness-gui into .github/skills/harness-gui/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-gui", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add FairladyZ625/harness-anything --skill harness-gui -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install FairladyZ625/harness-anything harness-gui --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/FairladyZ625/harness-anything.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/harness-gui .opencode/skills/harness-gui && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "harness-gui" agent skill from https://github.com/FairladyZ625/harness-anything/tree/main/skills/harness-gui into .opencode/skills/harness-gui/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-gui", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
harness-guiDevelop or review Harness Anything GUI pages and shared components using its existing design system, entity navigation, motion preferences, and background Electron verification.
Harness Gui is an agent skill from FairladyZ625/harness-anything. Develop or review Harness Anything GUI pages and shared components using its existing design system, entity navigation, motion preferences, and background Electron verification. Use for packages/gui work and GUI-specific agent missions.
Its SKILL.md is about 2.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).
It sits in Frontend & Design, covering Design systems. The repository describes itself as: Clean-room Harness rewrite monorepo. The licence is AGPL-3.0.
Read from SKILL.md and the folder at commit c805ddf. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Harness Gui loads about 2.3k tokens when it runs. Until then it costs about 62 tokens; SKILL.md has 1,261 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from FairladyZ625/harness-anything at commit c805ddf, republished under its AGPL-3.0 licence (© FairladyZ625). 1,261 words, ~2,345 tokens.
.claude/skills/harness-gui/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.Start with the existing product, not a new visual system. Read the target page and adjacent consumers, then GUI package guidance at packages/gui/README.md (relative to the product repository root) and the actual shared component source under packages/gui/src/renderer/components/primitives. The runnable packages/gui/component-catalog.html imports production primitives and demonstrates their contract; inspect its source for real imports and supported states. Consult the project’s authored GUI design standard when the workspace supplies one. User-approved interaction changes take precedence over older examples.
Before writing JSX, identify the existing component that owns the behavior. A page composes domain data and actions; shared primitives own sizing, overflow, focus and motion. Fix a repeated problem at that boundary and migrate real consumers in the same change. Do not retain a second implementation or turn a domain-specific card into a generic framework merely to reduce a file’s size.
EntityRefLink and the actual navigation callback. Keep the complete canonical reference available when the visible label is shortened. Do not infer entity kinds for arbitrary IDs.Optimize this functional GUI for readable work and efficient navigation. Shared components unify behavior, not dimensions: choose supported density, fill and layout options for the content and available space. Give documents reading width, directories scanning density, and controls only the space they need; do not copy one fixed ratio to every consumer. Respect user-adjusted region proportions.
Distinguish parent task headers from child session rounds through hierarchy and continuous grouping. Make the round identifier primary and repeated agent metadata secondary. Remove repeated information and nested padding before squeezing text; neither crowded single-line records nor oversized cards and decorative gaps are acceptable. Do not shrink typography to claim higher density.
Keep explicit monitoring surfaces visible when empty: WIP still shows zero and its current limit. Loading, stale data and failure are different states. Compare before/after at the same window size, font settings and content: useful information visible, readable text width and the actions needed to reach the intended item. Component reuse alone proves neither usability nor a performance improvement.
Every potentially long content surface—documents, logs, review prose, timelines and file previews—uses the shared bounded layout contract. Use BoundedContent and the shared --long-content-cap token, currently 55cqb of the sized content-viewport. Maximum height derives from the available container, not page-specific px/rem limits. Small content keeps its natural height; do not turn a maximum into a mandatory empty panel. Establish a finite parent height with shrinkable flex/grid children; keep titles, toolbars and primary actions outside the content scroll area. Overflow scrolls vertically inside that surface; wide tables/code scroll horizontally inside their own column without crossing adjacent text. Verify resizing, single/two-column layouts and nested wheel behavior. Use DocReader for Markdown documents, MarkdownDocument for shared Markdown parsing, and BinaryDocumentPreview for already-authorized image/PDF/Word bytes; DocumentFrame owns the bounded viewport and fixed toolbar. Exercise these in components/catalog/ComponentCatalog.tsx. Reuse the shared document viewer rather than mounting independent Markdown renderers; declare unsupported formats truthfully and preserve actual binary bytes through the authorized daemon read path.
The independent workbench has been removed. Implement layout in the actual route body; do not restore a floating canvas, panel catalog or second query state. Overview, work overview and task detail share PageRegions and existing split preferences. Use Region headers (or RegionDragHandle in document headers) for dedicated drag handles. Keep text selection, file clicks and graph input outside drag activation. Preserve semantic focus expansion and navigation.
Persist region order, orientation and ratios locally by connection + repository + page slot. Reuse SplitDivider / ColumnResizeHandle for pointer and keyboard resizing; reset the whole page slot including nested splits. Verify pointer movement, keyboard movement, cancellation, reload and reset on the real route, including root task details nested in a work page.
Structural seams use 2–4px spacing and a thin visible divider with a separate 12px hit target. Avoid stacked page padding and extra card shadows around an already bounded region. Keep document typography and readable row spacing. Each long body owns its scroll area; headers and controls remain reachable. Verify actual 1440 and 1120 window sizes and measure usable document geometry.
Use a preview drawer when the user needs the surrounding list or canvas, and full detail when the task is processing that entity. Relationship graphs retain inline node reading and progressive exploration; explicit refocus changes the center. Opening full details and returning must preserve exploration state and viewport. Do not replace graph exploration with a universal drawer rule.
Use the existing motion configuration and reduced-motion preference. New shared interactions may extend the existing primitives; there is no frozen allowlist of animation files. Animate a defined interaction, keep text undistorted, and keep keyboard focus visible. A modal owns focus while open and returns it on close; a non-modal preview keeps its background reachable. Name icon-only controls and expose selected/disabled state semantically. Desktop functional controls use shared compact density: small buttons start at 24px, ordinary buttons and segmented controls at 28px, growing with their text. Do not force every desktop control to 40px. Coarse-pointer targets use real boxes of at least 40px in both axes; do not expand transparent hit areas over adjacent controls. Verify actual geometry under the product font settings. Keep adjacent body/remove targets separate. Static chips may retain compact sizing.
Use focused behavior tests for the changed contract, then the repository’s applicable GUI checks. Prove the defect with the supported input that caused it; DOM class names alone do not prove layout. In Electron, measure the actual container and window size—minimum window constraints can invalidate a requested width. Include light/dark, narrow containers and keyboard paths when touched; exercise dynamic preference changes rather than module-load snapshots.
Electron verification is hidden by default, uses an independent profile and Playwright/CDP input, and never calls show/focus/bringToFront or controls the user’s keyboard. Waiting for a process does not mean foregrounding its window. Place the ephemeral Chromium profile/cache in a temporary directory outside task artifacts; publish only intended screenshots and evidence, never browser storage. Use the repository’s GUI capture/test tools, verify the selected project and final entity heading, wait for the intended content, and inspect the image. A loading screen or another entity is not acceptance. Wait for the relevant transition to settle before measuring or capturing; a wide-window drawer does not prove narrow-window detail behavior. Validate both the page and its opened detail at the actual narrow viewport. Copy tests must use an isolated clipboard or an explicit test boundary that captures the requested text; never save and restore the user’s system clipboard, which can overwrite content copied while the test runs. Label simulated clipboard checks honestly and never put existing clipboard contents in logs. Show a window only for an explicit user-requested demonstration.
Report the changed shared contract, real consumers migrated, old implementation removed, commands/results and material unverified behavior. A component catalog, passing structural check or worker self-report alone is not proof that the product page is usable.
© FairladyZ625, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 1 other file in skills/harness-gui of FairladyZ625/harness-anything.
Open the folder on GitHubat commit c805ddf
Harness Gui next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Harness Gui this skillFairladyZ625/harness-anything | 226 | — | ~2.3k | Automated safety check: Pass | AGPL-3.0 | |
| Impeccablebestofjs/bestofjs | 3.1k | 26 repos | ~2.6k | Automated safety check: Pass | MIT | |
| Figma Design System Builderwarpdotdev/warp | 65k | 2 repos | ~4.4k | Automated safety check: Pass | AGPL-3.0 | |
| Figma use_figma Plugin API Ruleswarpdotdev/warp | 65k | 4 repos | ~4.4k | Automated safety check: Pass | AGPL-3.0 | |
| UI StylingOhh-889/skyroc | 795 | 13 repos | ~2.5k | Automated safety check: Pass | MIT | |
| Shadcnsupabase/evals | 144 | 42 repos | ~4.5k | Automated safety check: Pass | Apache-2.0 |
bestofjs/bestofjs
A skill your agent uses when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a…
warpdotdev/warp
Builds or updates a design system in Figma from a codebase in ordered phases: discovery, variables and tokens, components, theming and documentation, with checkpoints.
warpdotdev/warp
Required groundwork before any use_figma call: the rules and reference files for running JavaScript in a Figma file through the Plugin API without common failures.
Ohh-889/skyroc
Create beautiful, accessible user interfaces with shadcn/ui components (built on Radix UI + Tailwind), Tailwind CSS utility-first styling, and canvas-based visual designs.
supabase/evals
Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI.
Ohh-889/skyroc
Token architecture, component specifications, and slide generation.
FairladyZ625/harness-anything
Contribute a public change to Harness Anything from a GitHub issue through an isolated worktree, scoped tests, manifest-selected gates, a complete bilingual PR body, review triage, and maintainer…
FairladyZ625/harness-anything
在目标仓库 harness.yaml 的 settings.gates 里声明与定制任务完成门:local-command 本地命令见证、manual-attest 人工签字、github-actions CI 见证、none 显式免除,治理字段 mandatorySignoff(双控签注)与 allowOverride(owner 特批),以及…
FairladyZ625/harness-anything
Create, review, or update Harness Anything preset-manifest/v3 packages, including profiles, completion gates, template selections, output shapes, script entrypoints, capability declarations, package…
FairladyZ625/harness-anything
Start Harness Anything task creation by choosing a software/coding preset first.
FairladyZ625/harness-anything
产出与增量维护任务包中的活解释页 artifacts/explainer.html;按物化模板中的唯一权威注释编写,并消费派工注入的 task-context 因果上下文。Use when a task-bound dispatch requires creating, updating, or freezing the task's living explainer page, or…
FairladyZ625/harness-anything
Create, review, or update Harness Anything verticals. An agent skill from FairladyZ625/harness-anything.
Categories
Develop or review Harness Anything GUI pages and shared components using its existing design system, entity navigation, motion preferences, and background Electron verification. Harness Gui is an agent skill from FairladyZ625/harness-anything. Develop or review Harness Anything GUI pages and shared components using its existing design system, entity navigation, motion preferences, and background Electron verification.
Harness Gui fits situations like: packages/gui work and GUI-specific agent missions; tasks that involve Design systems.
Run `npx skills add FairladyZ625/harness-anything --skill harness-gui -a claude-code`. Or copy the skill folder (skills/harness-gui in FairladyZ625/harness-anything) into .claude/skills/harness-gui in your project. Claude Code loads it when a task matches its description.
Run `npx skills add FairladyZ625/harness-anything --skill harness-gui -a codex`. Or copy the skill folder (skills/harness-gui in FairladyZ625/harness-anything) into .agents/skills/harness-gui in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add FairladyZ625/harness-anything --skill harness-gui -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/harness-gui, .gemini/skills/harness-gui, .github/skills/harness-gui and .opencode/skills/harness-gui in your project.
SKILL.md names no scripts, command-line tools or credentials: Harness Gui is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Harness Gui is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.3k tokens (SKILL.md is roughly 9.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Harness Gui: Impeccable (bestofjs/bestofjs, 3.1k stars), Figma Design System Builder (warpdotdev/warp, 65k stars), Figma use_figma Plugin API Rules (warpdotdev/warp, 65k stars) and UI Styling (Ohh-889/skyroc, 795 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
FairladyZ625 (a GitHub user) maintains it in FairladyZ625/harness-anything, which has 226 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 10, 2026.
Source: FairladyZ625/harness-anything on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.