Impeccable

Paul BakausCommunityCreated by Paul Bakaus

Skill
Workflow
Design and creative
Apache-2.0
Low risk
Has scripts

From the author

Use to design, redesign, critique, audit, polish or animate a frontend: websites, landing pages, dashboards, app UI, components, native iOS/Android screens, or a design system (DESIGN.md).

— the description by Paul Bakaus

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

Impeccable provides a structured approach to designing, auditing, and refining frontend interfaces including websites, dashboards, and mobile applications. It operates by establishing product context through documentation and applying specific design modes—Persuade, Operate, Read, and Experience—to guide the visual and functional direction of a project. The skill supports a wide range of tasks from initial planning and documentation to technical audits, visual refinements, and animation, ensuring that design changes remain consistent with the established visual world.

What it does

Audits UI for accessibility, performance, and responsive behavior.
Generates design documentation from existing project code.
Refines visual elements through commands like colorize, typeset, and layout.
Provides tools to plan UX and UI before implementation.
Manages design system tokens and component extraction.
Supports iterative design through live variant generation and testing.

When to use it

When you need to perform a UX critique or technical audit of an existing interface.
When starting a new design surface or defining a new visual world.
When you need to polish or refine UI components before a release.
When you need to adapt an interface for different screen sizes or platforms.
When you need to add purposeful animations or improve typography hierarchy.

Advantages

Provides a consistent framework for design decisions across different project types.
Integrates technical audits directly into the design workflow.
Supports specific modes to align design output with user intent.
Enables structured documentation of product and design context.
Offers granular control over UI refinements through specialized commands.

Usage examples

“impeccable audit src/components/Dashboard.tsx”: The agent performs a technical quality check on the dashboard component, reporting on accessibility, performance, and responsiveness.
“impeccable polish src/landing-page.css”: The agent executes a final quality pass on the landing page styles to ensure visual consistency and adherence to the design system.
“impeccable animate hero-section”: The agent applies purposeful motion and animation to the specified hero section based on the project's design mode.
“impeccable init”: The agent captures the current project context and creates a PRODUCT.md file to serve as the foundation for future design work.

Install

Download the skill as a ZIP:
https://autogineer.com/agent-skills/pbakaus/impeccable/download

Unzip it into the cross-client skills folder of your project:

mkdir -p .agents/skills && unzip impeccable.zip -d .agents/skills

Documentation by Paul Bakaus

This skill gives you the tools and permission to make design that earns the name out-of-distribution craft. Work as an award-winning design director would: production-grade code, a clear POV, a deep grasp of what the client and its users need, and exceptional craft.

Core principles:

Finish the job. No hedging, no shortcuts: the deliverable is complete, except assets the user must provide.
Scale ambition to the surface's mode (see Modes). Persuade and Experience get full commitment: bold, distinct work with a point of view. On Operate and Read, ambition shows as precision and restraint, and patterns the visitor already knows earn their place.
Verify by looking at the rendered result at the sizes it ships at, and batch the checks: fix what one look shows before looking again, rather than screenshotting after every tweak.

Setup

Run "${CLAUDE_SKILL_DIR}/scripts/impeccable" context once per session, where ${CLAUDE_SKILL_DIR} is the directory that contains this SKILL.md (the skill folder, not a plugin root two levels above it); keep cwd at the user's project. Every "${CLAUDE_SKILL_DIR}/scripts/impeccable" <verb> command in this skill and its references resolves against that base directory. In reference files, replace the skill-base-dir placeholder with this directory before running commands; it is not a shell variable. On a Windows shell without sh, call & "${CLAUDE_SKILL_DIR}/scripts/impeccable.cmd" instead. The launcher runs a self-contained binary that ships next to it or is downloaded once on first run; no Node or other runtime is required. Pass a named source file or route as --target <path>. It loads PRODUCT.md, DESIGN.md, the matching surface brief, and native-platform guidance when applicable; follow its directives and do not rerun it.
Load the request's playbook: its Commands-table reference for an explicit/implied sub-command, or reference/new-work.md for a new surface or replacement visual world. Inspect target and incumbent visual truth before editing. When the app cannot run, start with committed visual-regression goldens or screenshot fixtures; verify target and freshness against current tokens, CSS, components, or assets, resolve conflicts, and compare theme/variant captures.
After resolving analysis and direction, read reference/craft-floor.md immediately before any UI edit, including small refinements. It carries the quality floor, the absolute bans, and the reflexes no detector catches. Do not load it for planning-only work.

Launcher unavailable: On refusal or failure, send a separate message before the next tool call: “Context loading did not run; I’ll read the existing project context directly.” Then read existing PRODUCT.md and DESIGN.md without inventing missing context, follow applicable steps 2–3, including reading reference/craft-floor.md immediately before any UI edit, and continue through permitted tools. This applies to planning and editing; launcher failure alone does not block either.

How to design

The brief wins. Honor pinned aesthetics, eras, materials, fonts, and palettes even when they conflict with a saturated-pattern warning. Redirecting a clear brief toward your taste is failure.
Refinement preserves; redesign replaces. Refinement keeps the incumbent identity, behavior, copy, and everything outside scope. Ask before replacing factual copy or adding claims. Redesign keeps product truth, content, function, native affordances, and constraints, but treats the old look as evidence and anti-reference; choose a replacement world in new-work and replace DESIGN.md. Never split the difference into polish on the discarded look.
Loaded symbols stay out of the decoration. A subject's world does not license emblems tied to militarism, supremacy, or hate movements as motifs, badges, or ornament, such as the Rising Sun flag's rays, the Confederate battle flag, or Nazi-era insignia and their stylised variants; reach for that world's neutral forms instead. Content that documents such a symbol as fact stays as it is.
Visual authority is evidence, not a filename. Missing DESIGN.md alone does not make a project greenfield; new-work decides whether to preserve, expand, or replace the incumbent world.

Modes

The mode names what the visitor's success looks like on this surface.

Persuade: the visitor decides and acts; design is the product. Landing pages, marketing, campaigns, pricing. Earn attention and action. Ship real imagery when the brief needs it; follow the committed world, not category habit.
Operate: the visitor completes a task. App UI, dashboards, editors, admin, settings, tools. Scanability, consistency, native expectations, and the real usage scene outrank expression. Brand lives in precise details.
Read: the visitor understands something. Docs, articles, guides, help, changelogs. Structure for comprehension, then make the reading experience worth staying in.
Experience: the visitor is inside the work itself. Portfolios, galleries, showcases. Let the artifact lead from the first viewport; the interface recedes.

Choose the mode from the requested surface, not the product, and persist it only in that surface brief. A tool's landing page is still Persuade; a fashion house's documentation is still Read; a docs index is Read, not Persuade. See new-work.md for new surfaces and operate.md for deeper Operate/Read guidance.

Commands

Command	Category	Description	Reference
`craft [feature]`	Build	Deprecated alias for an ordinary new-work request	reference/craft.md
`shape [feature]`	Build	Plan UX/UI before writing code	reference/shape.md
`init`	Build	Capture durable product context in PRODUCT.md	reference/init.md
`document`	Build	Generate DESIGN.md from existing project code	reference/document.md
`extract [target]`	Build	Pull reusable tokens and components into design system	reference/extract.md
`critique [target]`	Evaluate	UX design review with heuristic scoring	reference/critique.md
`audit [target]`	Evaluate	Technical quality checks (a11y, perf, responsive)	reference/audit.md · native: reference/audit.native.md
`polish [target]`	Refine	Final quality pass before shipping	reference/polish.md
`bolder [target]`	Refine	Amplify safe or bland designs	reference/bolder.md
`quieter [target]`	Refine	Tone down aggressive or overstimulating designs	reference/quieter.md
`distill [target]`	Refine	Strip to essence, remove complexity	reference/distill.md
`harden [target]`	Refine	Production-ready: errors, i18n, edge cases	reference/harden.md
`onboard [target]`	Refine	Design first-run flows, empty states, activation	reference/onboard.md
`animate [target]`	Enhance	Add purposeful animations and motion	reference/animate.md
`colorize [target]`	Enhance	Add strategic color to monochromatic UIs	reference/colorize.md
`typeset [target]`	Enhance	Improve typography hierarchy and fonts	reference/typeset.md
`layout [target]`	Enhance	Fix spacing, rhythm, and visual hierarchy	reference/layout.md
`delight [target]`	Enhance	Add personality and memorable touches	reference/delight.md
`overdrive [target]`	Enhance	Push past conventional limits	reference/overdrive.md
`clarify [target]`	Fix	Improve UX copy, labels, and error messages	reference/clarify.md
`adapt [target]`	Fix	Adapt for different devices and screen sizes	reference/adapt.md · native: reference/adapt.native.md
`optimize [target]`	Fix	Diagnose and fix UI performance	reference/optimize.md
`live`	Iterate	Visual variant mode: pick elements in the browser, iterate on alternatives	reference/live.md
`generate [n] [action] [element]`	Iterate	Variants, versions, or alternatives of a named element to choose from in the live browser; no manual picking	reference/generate.md

Routing:

No argument: read routing.md and present its context-aware menu; never auto-run a command.
Explicit or clearly implied request to run a command: load its reference (native variant on native platforms) and follow it. Ask once if two commands fit.
Workflow or command-selection question: read Workflow questions.
Otherwise: treat the request as general design work. Missing PRODUCT.md routes a new surface or replacement world through init, then new-work; a narrow refinement of existing code proceeds on the incumbent implementation as impeccable context directs, offering init afterward rather than blocking on it.
teach aliases init. craft is a deprecated alias for ordinary new-work and adds nothing. shape owns task discovery, then enters new-work only for visual-world and surface-concept decisions.

After init writes PRODUCT.md, resume without rerunning impeccable context; init loads the native platform reference itself when the platform it recorded is ios, android, or adaptive.

Pin / Unpin: "${CLAUDE_SKILL_DIR}/scripts/impeccable" pin <pin|unpin> <command> creates or removes a standalone /<command> shortcut. Report the script's result concisely; relay stderr verbatim on error.

Doctor: /impeccable doctor reports and repairs drift between this project's Impeccable artifacts (PRODUCT.md, DESIGN.md and its sidecar, config, surface briefs, the hook) and what this version reads. Load reference/doctor.md when the user invokes it, or when they ask what is out of date, stale, or needs refreshing. A CONTEXT_STALE directive in Setup's output is the cheap subset of the same report; act on it there per its own instructions rather than running doctor unasked.

Never repair drift as a side effect of a design task. A CONTEXT_STALE finding is reported, not acted on, unless the user asks. The one exception is a finding marked auto, which the next write to that file performs anyway.

Files

ATTRIBUTION.mdAdded by AutoGineer866 B
LICENSELicence file added by AutoGineer10.5 KiB
NOTICELicence file added by AutoGineer503 B
SKILL.md11.4 KiB
reference/adapt.md11.0 KiB
reference/adapt.native.md3.8 KiB
reference/android.md4.1 KiB
reference/animate.md5.1 KiB
reference/audit.md9.4 KiB
reference/audit.native.md8.1 KiB
reference/bolder.md3.4 KiB
reference/clarify.md4.5 KiB
reference/colorize.md4.4 KiB
reference/component-review.md7.8 KiB
reference/craft-floor.md4.4 KiB
reference/craft.md555 B
reference/critique.md44.5 KiB
reference/degraded/asset-producer.md8.3 KiB
reference/degraded/documenter.md3.6 KiB
reference/degraded/finish-reviewer.md15.5 KiB
reference/degraded/manual-edit-applier.md7.5 KiB
reference/delight.md3.6 KiB
reference/distill.md5.4 KiB
reference/doctor.md5.5 KiB
reference/document.md26.8 KiB
reference/extract.md3.3 KiB
reference/generate.md12.8 KiB
reference/harden.md10.5 KiB
reference/hooks.md16.9 KiB
reference/init.md11.9 KiB
reference/ios.md3.7 KiB
reference/layout.md5.0 KiB
reference/live-setup.md8.0 KiB
reference/live.md36.4 KiB
reference/mode-operate.md4.6 KiB
reference/mode-persuade.md3.6 KiB
reference/mode-read.md4.3 KiB
reference/new-work.md62.0 KiB
reference/onboard.md7.5 KiB
reference/operate.md4.0 KiB
reference/optimize.md7.4 KiB
reference/overdrive.md8.8 KiB
reference/polish.md6.5 KiB
reference/quieter.md4.8 KiB
reference/region-map.md3.3 KiB
reference/routing.md3.2 KiB
reference/shape.md3.5 KiB
reference/typeset.md6.1 KiB
reference/visualize.md13.6 KiB
scripts/VERSION7 B
scripts/command-metadata.json8.1 KiB
scripts/data/font-index-failures.json2.4 KiB
scripts/data/font-index.json1.0 MiB
scripts/engine-checksums.txt787 B
scripts/impeccableScript11.1 KiB
scripts/impeccable.cmdScript11.9 KiB
scripts/live-browser-dom.jsScript12.0 KiB
scripts/live-browser-ignores.jsScript10.2 KiB
scripts/live-browser-session.jsScript5.7 KiB
scripts/live-browser.jsScript550.0 KiB
scripts/modern-screenshot.umd.jsScript28.6 KiB

reference/hooks.md

/impeccable hooks

Manage the design detector hook for the current project.

The hook runs the impeccable design detector on direct file edits to design-relevant files (.tsx, .jsx, .html, .vue, .svelte, .astro, .css, .scss, .sass, .less, .ts, .js). Claude Code, Codex, Cursor, and GitHub Copilot use a post-tool-use hook and push a short system reminder into the agent's context after the edit; findings get a correction prompt, pending issues get a re-nudge, and clean UI-ish files get a short ack unless quiet mode is on (hook.quiet in config). Plain .ts and .js files are still scanned, but stay quiet unless the detector finds something. Grok Build fires the same PostToolUse scan to mark touched files, then surfaces findings on Stop additionalContext. Do not expect a Grok per-edit reminder: Grok discards that stdout. On Hermes Agent the per-edit findings arrive inside the write_file or patch tool result itself, as its impeccable field.

The detector rules run in two tiers. The per-edit hook surfaces only the immediate tier: mechanical, unambiguous problems worth interrupting an edit for, such as broken images, overflowing content, contrast and legibility failures, gradient text, glow shadows, and design-system drift. Everything else (copy cadence, palette and typography taste, layout rhythm) is deferred to a deep pass on the Stop hook event, which runs the full rule set over every UI file touched in the session and surfaces the remaining findings once, deduplicated against what the per-edit pass already reported. A session with nothing left to report stops silently. Set hook.perEditRules to "all" in .impeccable/config.json to restore the full rule set on every edit. The Stop deep pass is wired for Claude Code, Codex, and Grok Build, which dispatch a native Stop hook event, and for Hermes Agent, whose plugin sends it from pre_verify. Cursor does not get one (its stop hook can only answer with a follow-up user message), and GitHub Copilot's stop-style events do not feed context back to the model, so they keep the full detector per edit. Grok also fires an observe-only Stop with reason: "shutdown" after end_turn; skip that one, scan only end_turn.

Every hook is a mechanical pass. The reflexes no scanner catches live in craft-floor.md, which the skill loads before it edits UI, so they apply whether or not a hook is wired. A session with no automatic hook gets one MANUAL_DETECTOR_REQUIRED directive from impeccable context asking for a single detector run at the end.

This command toggles the hook per project by editing .impeccable/config.json (the unified Impeccable config; hook runtime settings live under its hook key, and shared detector ignores live under detector). Per-developer overrides, including the install consent decision (hook.consent) the CLI records, live in the gitignored .impeccable/config.local.json. Set hook.enabled: false to turn the hook off, hook.quiet: true to silence the clean/pending acks, or hook.auditLog to a file path for an NDJSON log. The legacy IMPECCABLE_HOOK_DISABLED, IMPECCABLE_HOOK_QUIET, and IMPECCABLE_HOOK_LOG env vars are still honored and override these config values when set.

Declare server-side template extensions under detector.extensions when the project uses Blade, Twig, ERB, or Handlebars files; the hook skips them otherwise because they sit outside the built-in extension list. One entry per extension, { "ext": ".blade.php", "engine": "html" }. engine picks the analyzer (html for markup templates, text for JS/TS/CSS-like files) and defaults to html. Match against the end of the filename, so double extensions like .blade.php and .html.erb work. Config only adds extensions; the built-in list always applies.

Manual "<skill-base-dir>/scripts/impeccable" detect scans use the same project filter config by default: detector.ignoreRules, detector.ignoreFiles, detector.ignoreValues, and detector.designSystem.enabled. hook.enabled only controls automatic hook execution, not manual CLI scans. Use "<skill-base-dir>/scripts/impeccable" detect --no-config ... for a raw detector run that ignores project config/context. Use "<skill-base-dir>/scripts/impeccable" ignores ... for direct CLI CRUD on the same detector ignores.

Supported harnesses: Claude Code (.claude/settings.local.json for a project-scope install; $CLAUDE_CONFIG_DIR/settings.json for a user-scope install, defaulting to ~/.claude/settings.json; a project hook moved into shared .claude/settings.json is honored in place too), Codex (.codex/hooks.json in the project), Cursor (.cursor/hooks.json in the project), Grok Build (.grok/hooks/impeccable.json in the project; requires /hooks-trust or --trust), GitHub Copilot (.github/hooks/impeccable.json in the project, a team-shared committed file that both the Copilot CLI and the cloud agent read), and Hermes Agent (the impeccable-design-hook plugin in ~/.hermes/plugins/; the user enables it once with hermes plugins enable impeccable-design-hook; a project install's launcher runs only in a project Hermes trusts, via hermes skills trust). For the Copilot CLI, repo-level hooks fire once .github/hooks/impeccable.json is committed to the repository's default branch.

On Cursor, the hook runs on postToolUse for the Write tool (every agent file edit) and returns its reminder as additional_context, which Cursor adds after the tool result. Projects set up before this ran a preToolUse gate (hook-before-edit) that blocked bad writes before they landed; that gate still works until hooks on, impeccable update, or impeccable doctor --fix moves the entry to postToolUse.

Gemini installs session and completion hooks in .gemini/settings.json, merged into the settings already there (comments are tolerated; a commented file is backed up to settings.json.bak before the rewrite, and a file that is not valid JSON is left alone). It does not install a per-edit detector hook. The BeforeTool hook only rewrites shell commands that run build-phase, and only on macOS and Linux; on Windows (where Gemini runs hooks through PowerShell) no session id reaches the shell, so a comp build is not tied to the session and the completion reminder stays silent.

When there is no project Claude skill, hooks on looks for skills/impeccable/scripts/impeccable inside CLAUDE_CONFIG_DIR (default ~/.claude) and writes the hook into that account's settings.json, using the installed launcher's absolute path. Relative account directories resolve against the caller's working directory. An explicit account directory is exclusive: another account's default skill and settings are never substituted. Status and context read the same account settings. If no design harness can be wired, hooks on says so, reports skipped invalid settings or the missing skill lookup paths, and gives the next step.

Status checks the current event entries and matchers in each manifest, including the Stop pass where supported. Claude Code counts as wired when either project settings file (or its user settings file) contains the current entries. A legacy command, partial manifest, or missing file is reported as not wired. If enabled in config but no design harness is wired, status says so and gives impeccable hooks on as the repair command. An installed and enabled Hermes design-hook plugin also counts as wired; on acknowledges it without changing the plugin configuration. Wiring confirms the manifest entries; harness trust requirements and session reloads still apply.

When hook.consent is "accepted" in the project's config.local.json and the hook is enabled, impeccable context restores missing or stale entries for installed harness skills and reports repairs in one line. Shared config consent does not authorize this write. Automatic repair preserves unrelated settings and hooks and leaves malformed manifests alone. Without local consent, context writes no manifests and keeps MANUAL_DETECTOR_REQUIRED, naming the missing or stale harness wiring. Explicitly disabled hooks stay disabled.

Routing

The first argument is the action. Defaults to status.

Action	What it does
`status`	Print current state, shared/local config paths, ignored rules / files / values, env override, and actual manifest wiring for each harness.
`on`	Set `enabled: true` in `.impeccable/config.json`, record local hook consent as accepted, and install/repair provider hook manifests when the skill is installed.
`off`	Set `enabled: false` in `.impeccable/config.json`.
`ignore-rule <id>`	Append `<id>` to `detector.ignoreRules`; for `overused-font`, requires `--all-values`. Suppresses the rule across the whole project.
`ignore-file <glob>`	Append `<glob>` to `detector.ignoreFiles`. Suppresses every rule for matching files.
`ignore-value <id> <value> [--shared] [--reason "..."]`	Append a rule/value suppression to shared `.impeccable/config.json`.
`ignore-value <id> <value> --local [--reason "..."]`	Append a private rule/value suppression to `.impeccable/config.local.json`.
`ignore-value <id> "*" --file <glob> [--file <glob>...]`	Turn one rule off in matching files only, leaving it active everywhere else. Repeat `--file`, or use `--file=<glob>` / `--files=<glob>`. A bare `"*"` with no `--file` is refused: use `ignore-rule <id>` if you really mean project-wide.
`reset`	Delete the project config, dedup cache, and Cursor pending queue, and remove the hook's entries from every provider manifest `on` installs, the committed Copilot file included (a team-shared `settings.json` that `on` never writes is never touched).

Flow

Resolve the action from the user's argument. If no action was given, default to status.
Invoke the admin script and pass the user's output through verbatim:
```
"<skill-base-dir>/scripts/impeccable" hooks <action> [args...]
```
If <action> is off, follow up with a one-line note: "Done. New edits will not trigger the design hook in this project until you run /impeccable hooks on."
If <action> is on, report what the command installed or repaired. If no installed skill folders were found or settings were skipped, surface that result and do not claim the hook will run. Otherwise note that the harness must load the updated settings (and satisfy any trust requirements) before it runs. On Hermes Agent, on cannot install or enable the plugin: if impeccable context reported MANUAL_DETECTOR_REQUIRED, tell the user to run npx impeccable install and then hermes plugins enable impeccable-design-hook instead.
If <action> is ignore-value, ignore-file, or ignore-rule, just print the script output. The default scope is shared .impeccable/config.json; add --local only when the user explicitly asks for a private exception.
If <action> is status, just print the script output. Do not add commentary unless the user asked a follow-up question.

Triage findings

The hook itself never writes ignore config; every exception goes through impeccable hooks. Triage each finding into one of three outcomes:

Real design problem: fix it. Never add an ignore to skip a fix or to push a blocked write through.
Confident false positive or sanctioned exception: persist the narrowest ignore yourself and disclose it in your reply. The bar is evidence you can name: an intentional demo or fixture, documentation of bad design, literal or domain-appropriate motion (a ball that bounces), or a choice the user already confirmed. Put that evidence in --reason as "<who decided: evidence>"; write "user confirmed" only when the user actually did.
Unsure: leave the finding standing and give the reason in one line. Ask the user only when you genuinely cannot decide.

Self-serve stops at ignore-value. ignore-file and ignore-rule silence too much to add on your own judgment; ask the user first.

Prefer the narrowest exception:

If the finding line shows an ignore-value <rule> <value> pair, pass it to impeccable hooks ignore-value with your --reason. This writes shared .impeccable/config.json by default.
For value-specific findings such as overused-font and bounce-easing, use ignore-value for the specific value. Do not use ignore-rule overused-font for a specific font.
If the finding has no value-specific command, such as side-tab, scope that one rule to the file: ignore-value <id> "*" --file <path>. Run "<skill-base-dir>/scripts/impeccable" detect <path> first to see what actually fires there.
Reach for ignore-file <path> only when the whole file is out of scope for design review: a fixture, a generated artifact, a deliberate slop demo. It silences every rule for that file permanently, including rules that have not been written yet. A real UI surface with one noisy rule wants the file-scoped value ignore above.
Use ignore-rule <id> only when the user asks to suppress that whole rule across the project. For broad overused-font suppression, use ignore-rule overused-font --all-values only when the user asks to ignore overused fonts generally.
Prefer config ignores (the commands above) by default; they keep suppressions in one reviewable place. Reach for an inline comment only when the waiver must travel with a single file that leaves the repo (a generated/exported standalone document, an emailed HTML file). The supported marker is impeccable-disable <rule> (whole file) or impeccable-disable-line / impeccable-disable-next-line (one line), in any comment syntax, with an optional reason after : or --. The detector honors it by default; --no-inline-ignores or --no-config bypasses it.

Example value-specific exception:

"<skill-base-dir>/scripts/impeccable" hooks ignore-value overused-font Inter --shared --reason "User confirmed Inter is intentional"

Example self-served exception, with the evidence named:

"<skill-base-dir>/scripts/impeccable" hooks ignore-value bounce-easing bounce-ball --shared --reason "Agent: literal ball-bounce animation, bounce easing is the subject"

Example whole-rule font exception:

"<skill-base-dir>/scripts/impeccable" hooks ignore-rule overused-font --all-values --reason "User asked to ignore overused fonts generally"

Example one-rule-in-one-file exception, for a file that is still worth reviewing for everything else:

"<skill-base-dir>/scripts/impeccable" hooks ignore-value design-system-font-size "*" --file "src/overlay/widget.js" --reason "Injected widget builds its own type scale; DESIGN.md's ramp describes the site"

Example whole-file exception, for a file that is out of scope entirely:

"<skill-base-dir>/scripts/impeccable" hooks ignore-file "src/legacy/Card.tsx"

Constraints

Never modify .impeccable/config.json or .impeccable/config.local.json by hand from this command. Always go through impeccable hooks so writes stay validated and the file shape stays consistent. One exception: detector.extensions has no admin action, so when the user asks to cover a template stack, edit that one field in .impeccable/config.json directly and leave the rest of the file untouched.
Do not edit the launcher or the binary behind impeccable hook and impeccable hook-before-edit from this flow. Those are skill plumbing.
When a user asks how far to trust the hook, say it runs the engine unsandboxed with the agent's environment and network access (in the Copilot cloud agent too, once .github/hooks/impeccable.json is committed), and that the launcher checks a downloaded engine against <skill-base-dir>/scripts/engine-checksums.txt before its first run; never call it sandboxed.
The hook never blocks an edit; it emits a post-edit reminder. (A Cursor project still on the old preToolUse gate can block a write until its manifest is migrated.) Disabling stops the reminders.
The hook is bundled with the Impeccable skill. Project installs use .claude/settings.local.json, .codex/hooks.json, .cursor/hooks.json, .github/hooks/impeccable.json, and .gemini/settings.json; a user-scope Claude install uses the active account's $CLAUDE_CONFIG_DIR/settings.json (default ~/.claude/settings.json). On Codex, the user must approve the hook via /hooks the first time. On Cursor, confirm hooks are enabled under Settings -> Hooks. On GitHub Copilot, the CLI loads .github/hooks/impeccable.json once it is committed to the repository's default branch, and the cloud agent reads it from the repo directly.

Failure modes

If .impeccable/config.json or .impeccable/config.local.json is unreadable or malformed, the hook ignores that file and uses the remaining valid config/defaults. impeccable hooks status will show malformed files as ignored.
If the user asks to "disable the hook" globally, lead with /impeccable hooks off (persistent for this project; writes hook.enabled: false to config). The legacy IMPECCABLE_HOOK_DISABLED=1 env var also works as a one-shot override that follows the shell.

Requirements and compatibility

Written for: Claude Code

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Needs: Claude Code frontmatter, Needs Node.js

Security

What our scanner noticed· Low risk

Scripts that your agent may run

This skill includes scripts that your agent may run. Read them before you use it.

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Attribution and licence

Created by

Paul Bakaus

Publisher

Paul Bakaus (Community)

Source

pbakaus/impeccable · plugin/skills/impeccable · commit 687bc38

Licence

Apache License 2.0 (redistribution allowed)

LICENSE (added by AutoGineer from LICENSE)
NOTICE (added by AutoGineer from NOTICE.md)
ATTRIBUTION.md (written by AutoGineer)

Synced

2026-11-09

AutoGineer is not affiliated with or endorsed by Paul Bakaus or Paul Bakaus.

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download impeccable.zip