impeccable
Skill263 starsChanged 35 days agoMITView on GitHub
Use when the user wants distinctive, production-grade frontend design, anti-generic AI aesthetics, UX critique, technical UI audits, or final polish through bundled Impeccable references and an optional upstream detector CLI.
- Installs packages
168 other projects use a version of this.
Adopted by
Most recently taken up by
- podo/design-agent-skillstheir own version, first seen Nov 8, 2026
- longhang2004/vietnamese-humanizertheir own version, first seen Nov 8, 2026
- cafe3310/public-agent-skillstheir own version, first seen Nov 8, 2026
- microsoft/frontier-agentic-modernization-rvastheir own version, first seen Nov 8, 2026
- taixuann/development-spacetheir own version, first seen Nov 8, 2026
- sellerhunghienhoa/hunghienhoa2110their own version, first seen Nov 8, 2026
Used with
Projects with it also use cloud-architecture-diagram, shelra-workspace-quality and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
MicrosoftSkillcloud-architecture-diagram
Create, edit, or troubleshoot Azure-first architecture diagrams as editable draw.io files, with AWS and multicloud topology support and identity, API, and CI/CD flow diagrams. Use for architecture visualization, network boundaries, interaction flows, or missing diagram icons. Not for deploying infrastructure, live cloud discovery, security certification, or unrelated charts.
Also in 3 projects that use this
ShelraSkillshelra-workspace-quality
Audit or refine ShelraCode's main OpenTUI coding workspace when chat activity, live status, plan/context sidebar, agent visibility, or verification UX must match a supplied visual specification. Do not use for onboarding, settings, or unrelated screens.
Also in 3 projects that use this
owshq-mecSkilllayout
Improve layout, spacing, and visual rhythm. Fixes monotonous grids, inconsistent spacing, and weak visual hierarchy. Use when the user mentions layout feeling off, spacing issues, visual hierarchy, crowded UI, alignment problems, or wanting better composition.
Also in 8 projects that use this
FldicoahkiinSkillcontribute-catalog
Author a new HyperFrames registry block (caption style, VFX block, transition, lower third) or component (text effect, overlay, snippet) and ship it as an upstream PR to the hyperframes repo. Use ONLY when the user wants to CONTRIBUTE to the public catalog — for in-project caption/transition authoring use the `hyperframes` skill, for installing existing registry items use the `hyperframes-registry` skill.
Also in 3 projects that use this
HK-hubSkilloverdrive
Pushes interfaces past conventional limits with technically ambitious implementations — shaders, spring physics, scroll-driven reveals, 60fps animations. Use when the user wants to wow, impress, go all-out, or make something that feels extraordinary.
Also in 11 projects that use this
HK-hubSkillbolder
Amplify safe or boring designs to make them more visually interesting and stimulating. Increases impact while maintaining usability. Use when the user says the design looks bland, generic, too safe, lacks personality, or wants more visual impact and character.
Also in 12 projects that use this
- +3 more from HK-hub
Other versions168 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 168
- pbakaus/impeccable★ 106ksame name
- clidey/whodb★ 5.1ksame name
- guilhermerodz/input-otp★ 3.3ksame name
- bestofjs/bestofjs★ 3.1ksame name
- bergside/awesome-design-skills★ 2.9ksame name
- compozy/compozy★ 2.9ksame name
- Draculabo/AntigravityManager★ 2.5ksame name
- monoscope-tech/monoscope★ 2.1ksame name
- danieleteti/delphimvcframework★ 1.4ksame name
- FidelusAleksander/ghcertified★ 996same name
158 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository37 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .cursor/rules/code-citation-clickable.mdcCursor rule
- .cursor/rules/commit-message-english.mdcCursor rule
- autonomous-maintainability-campaignSkill
- autonomous-requirement-discoverySkill
- delivering-delegated-linear-issuesSkill
- development-deliverySkill
- development-designSkill
- development-implementationSkill
- development-lifecycleSkill
- development-retrospectiveSkill
- development-reviewSkill
- development-task-understandingSkill
- development-validationSkill
- idea-search-funnelSkill
- nextclaw-agent-instructions-governanceSkill
- nextclaw-product-blog-storytellingSkill
- nextclaw-product-visual-assetsSkill
- x-twitter-birdSkill
- aigen-image-generationSkill
- bb-browserSkill
- browser-controlSkill
- claude-code-narp-runtimeSkill
- clawhub-nextclawSkill
- codex-narp-runtimeSkill
- find-skillsSkill
- gemigo-cliSkill
- lark-cliSkill
- linear-cliSkill
- mmx-cliSkill
- nextclaw-skin-studioSkill
- opencliSkill
- proxy-local-ai-subscriptionsSkill
- publish-to-nextclaw-marketplaceSkill
- skillhub-guideSkill
- superpowersSkill
- ui-ux-pro-maxSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
30 rules. 0 are common, 21 are distinctive, and 9 are very specific to this project.
0
Common
Most of the 167 edited versions we read keep these.
21
Distinctive
This author's own choices. Worth a look.
9
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 10
Use this skill when the user wants stronger frontend design quality inside NextClaw.
- Very specific: line 26
Do not present third-party detector output as built-in NextClaw capability.
- Distinctive: line 27
Do not pretend the detector is ready when it is not.
- Distinctive: line 51
Always distinguish these paths:
- Distinctive: line 66
When this skill triggers, follow this order.
- Distinctive: line 78
If any of these checks fail, the skill is not correctly installed in the current workspace.
- Distinctive: line 95
Before doing meaningful design work, confirm these minimum inputs:
- Distinctive: line 101
Do not infer these from code alone.
- Very specific: line 103
If the user already supplied them in the current conversation, proceed.
- Very specific: line 104
If not, ask the smallest number of targeted questions needed to unblock the work.
- Very specific: line 105
If the user wants this context persisted for future sessions, ask before writing a local .impeccable.md.
- Distinctive: line 109
Prefer the smallest relevant asset instead of reading everything:
- Distinctive: line 149
Only use the upstream detector when the user wants automated anti-pattern evidence, or when audit or critique would materially benefit from …
- Very specific: line 161
If impeccable is already installed, verify it with:
- Distinctive: line 167
If the CLI is missing:
- Distinctive: line 170
keep going with the bundled references when the user only needs design guidance,
- Very specific: line 171
ask before any install or download step because npm install -g impeccable or npx impeccable ...
- Distinctive: line 173
If the detector is available, prefer a read-only smoke before a large scan:
- Very specific: line 179
Use --fast for large directories.
- Distinctive: line 201
If the issue sounds implementation-heavy rather than experiential, prefer:
- Distinctive: line 238
Do not start real design work until the minimum design context is known.
- Distinctive: line 239
Prefer shaping before large greenfield frontend work.
- Distinctive: line 241
Prefer read-only critique or audit before sweeping rewrites when the problem is still unclear.
- Very specific: line 242
Ask before writing .impeccable.md or installing/downloading the detector runtime.
- Distinctive: line 243
Treat detector findings as evidence, not unquestionable truth.
- Distinctive: line 245
Keep recommendations grounded in the user's product, not a stock aesthetic template.
- Distinctive: line 252
Ask the smallest targeted question set needed to recover the audience, use case, and tone.
- Distinctive: line 262
Follow the stricter local system.
- Distinctive: line 263
Use Impeccable as a quality and taste layer, not as authority to override established product rules.
- Distinctive: line 268
Keep the detector result as a signal, but prioritize verified user impact and visual judgment.
“Common” is measured: kept by at least 6 in 10 of the 167 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Impeccable
Overview
Use this skill when the user wants stronger frontend design quality inside NextClaw.
This marketplace skill adapts the upstream pbakaus/impeccable project into a single installable NextClaw skill package with:
- one top-level workflow router,
- bundled local references for typography, color and contrast, layout, motion, interaction, responsive design, and UX writing,
- bundled workflow guides for shaping, crafting, critique, audit, polish, and design-system extraction,
- and an optional upstream
impeccabledetector CLI for deterministic anti-pattern scans.
Be explicit about the boundary:
- This skill owns design-context gating, workflow selection, expectation-setting, and detector readiness guidance.
- The bundled local references own the detailed design vocabulary.
- The optional upstream
impeccableCLI owns deterministic anti-pattern detection. - NextClaw, the current repository rules, and the active runtime own actual implementation and execution.
Do not present third-party detector output as built-in NextClaw capability. Do not pretend the detector is ready when it is not.
What This Skill Covers
- design context setup before UI work,
- feature shaping before code is written,
- distinctive frontend implementation guidance that avoids generic AI aesthetics,
- focused passes on typography, color, layout, motion, interaction, responsive behavior, and microcopy,
- design critique and technical UI audit,
- final polish before shipping,
- design-system extraction from repeated patterns,
- optional detector-assisted anti-pattern scans when the upstream CLI is available.
What This Skill Does Not Cover
- inferring the real audience or brand tone purely from code,
- silently installing npm packages or downloading the detector runtime,
- claiming detector-based evidence when Node/npm or the CLI are unavailable,
- overriding a stricter local design system or project rulebook,
- turning every design request into the same maximalist or marketing-style aesthetic,
- pretending that an upstream multi-command ecosystem maps one-to-one onto NextClaw command surfaces.
Install Boundary
Always distinguish these paths:
- NextClaw marketplace install:
nextclaw skills install impeccable - Installed NextClaw skill assets:
<workspace>/skills/impeccable/ - Optional upstream detector runtime:
npm install -g impeccable - Upstream standalone bundles for other tools:
https://github.com/pbakaus/impeccable
Installing the marketplace skill does not install the upstream detector automatically.
Deterministic First-Use Workflow
When this skill triggers, follow this order.
Step 0: Verify the bundled assets exist
Check:
test -f skills/impeccable/SKILL.md
test -f skills/impeccable/references/typography.md
test -f skills/impeccable/workflows/critique.mdIf any of these checks fail, the skill is not correctly installed in the current workspace.
Step 1: Classify the user's need
Choose the smallest matching workflow:
- design context setup,
- feature shaping,
- build or redesign,
- design critique,
- technical audit,
- final polish,
- design-system extraction,
- focused pass: typography, color, layout, motion, interaction, responsive behavior, or UX copy.
Step 2: Gate on design context before real design work
Before doing meaningful design work, confirm these minimum inputs:
- target audience,
- primary use cases or jobs to be done,
- brand personality or interface tone.
Do not infer these from code alone.
If the user already supplied them in the current conversation, proceed.
If not, ask the smallest number of targeted questions needed to unblock the work.
If the user wants this context persisted for future sessions, ask before writing a local .impeccable.md.
Step 3: Load only the matching local workflow
Prefer the smallest relevant asset instead of reading everything:
- feature shaping: workflows/shape.md
- build or redesign: workflows/craft.md
- design critique: workflows/critique.md
- technical audit: workflows/audit.md
- final polish: workflows/polish.md
- design-system extraction: workflows/extract.md
For focused passes, load only the relevant references:
- typography: references/typography.md
- color and contrast: references/color-and-contrast.md
- layout and spacing: references/spatial-design.md
- motion: references/motion-design.md
- interaction: references/interaction-design.md
- responsive behavior: references/responsive-design.md
- UX writing: references/ux-writing.md
For critique scoring or persona framing, also load:
- references/critique-cognitive-load.md
- references/critique-heuristics-scoring.md
- references/critique-personas.md
Step 4: Treat the detector CLI as optional runtime, not a default assumption
Only use the upstream detector when the user wants automated anti-pattern evidence, or when audit or critique would materially benefit from it.
First verify runtime prerequisites:
command -v node
node --version
command -v npm
command -v npx
command -v impeccableIf impeccable is already installed, verify it with:
impeccable --helpIf the CLI is missing:
- explain that the bundled NextClaw skill is ready, but the optional detector runtime is not,
- keep going with the bundled references when the user only needs design guidance,
- ask before any install or download step because
npm install -g impeccableornpx impeccable ...changes local machine state.
If the detector is available, prefer a read-only smoke before a large scan:
impeccable detect --fast --json <target>Use --fast for large directories. Narrow scope before scanning very large repos.
Workflow Routing Guidance
New feature or major redesign
Start with:
- workflows/shape.md
Then continue with:
- workflows/craft.md
Load the minimum supporting references based on the brief.
Existing UI needs feedback
Use:
- workflows/critique.md
If the issue sounds implementation-heavy rather than experiential, prefer:
- workflows/audit.md
Existing UI is close but not finished
Use:
- workflows/polish.md
Existing product has repeated patterns that should become a design system
Use:
- workflows/extract.md
Focused fixes without a full redesign
Choose the smallest relevant reference and stay scoped:
- typography issue only: references/typography.md
- color or contrast issue only: references/color-and-contrast.md
- spacing or layout issue only: references/spatial-design.md
- motion or transition issue only: references/motion-design.md
- form, state, or affordance issue only: references/interaction-design.md
- mobile or responsive issue only: references/responsive-design.md
- unclear labels, errors, or empty states: references/ux-writing.md
Safe Usage Rules
- Do not start real design work until the minimum design context is known.
- Prefer shaping before large greenfield frontend work.
- Preserve the existing design system when the user is working within an established product.
- Prefer read-only critique or audit before sweeping rewrites when the problem is still unclear.
- Ask before writing
.impeccable.mdor installing/downloading the detector runtime. - Treat detector findings as evidence, not unquestionable truth; false positives must be called out.
- Be honest when the result still feels generic or AI-generated.
- Keep recommendations grounded in the user's product, not a stock aesthetic template.
Troubleshooting
Design context is missing
- Stop guessing.
- Ask the smallest targeted question set needed to recover the audience, use case, and tone.
The user wants critique or audit, but the detector CLI is unavailable
- Continue with the bundled critique or audit workflow.
- Be explicit that the result is expert review without detector evidence.
- Offer the optional detector install path only if the user wants it.
The current repo already has a stricter design system
- Follow the stricter local system.
- Use Impeccable as a quality and taste layer, not as authority to override established product rules.
Detector output conflicts with good product judgment
- Say so plainly.
- Keep the detector result as a signal, but prioritize verified user impact and visual judgment.
Success Criteria
This skill is working correctly when:
- design work starts from explicit audience, use case, and tone rather than guesswork,
- the smallest relevant workflow or reference is loaded,
- the resulting interface avoids obvious generic AI aesthetics,
- critique and audit outputs are specific, prioritized, and actionable,
- optional detector scans are only used when their runtime is actually ready,
- and the skill raises the design bar without hiding setup reality.
Attribution
This skill adapts the upstream pbakaus/impeccable project for the NextClaw marketplace.
Source mapping is documented in references/SOURCES.md.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

