Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Impeccable Pointer

ASecurity

Point to Paul Bakaus's Impeccable design skill and explain when to use it. Use when asked how to install impeccable, which skill critiques and audits a built UI, or what handles the critique stage of the design pipeline. Produces the install command, the one-time init step, guidance on when it fits and when it does not, and credit to the author with a link. Contains no upstream skill content.

1,417 stars
0 votes
0 copies
0 views
Added 10/1/2026
ai-agentsbashgitfrontend

Works with

claude codecli

Security Analysis

A100/100

Scanned 10/1/2026

$npx -y skills add mohitagw15856/pm-claude-skills --skill impeccable-pointer --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Impeccable Pointer?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Impeccable Pointer
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/mohitagw15856-impeccable-pointer/badge)](https://www.skillsdirectory.com/skills/mohitagw15856-impeccable-pointer)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: impeccable-pointer
description: "Point to Paul Bakaus's Impeccable design skill and explain when to use it. Use when asked how to install impeccable, which skill critiques and audits a built UI, or what handles the critique stage of the design pipeline. Produces the install command, the one-time init step, guidance on when it fits and when it does not, and credit to the author with a link. Contains no upstream skill content."
homepage: https://mohitagw15856.github.io/pm-claude-skills/skill/impeccable-pointer.html
metadata:
  {
    "openclaw": { "emoji": "🧠" }
  }
---

# Impeccable (pointer)

This is a pointer, not a copy. It tells you when Paul Bakaus's Impeccable is the right tool, how to install it from the source, and who to credit. The skill, its commands and its detector rules live upstream and are not reproduced here.

## What This Skill Produces

- **A recommendation**: whether the upstream skill fits the task in front of you
- **The install command and the init step**
- **Its place in the pipeline**: stage 4, Critique, in `ui-design-pipeline`
- **Attribution**: author, licence and link

## Required Inputs

Ask for these if not provided:
- **The page or component to review**, already built
- **The direction and system files** from stages 1 and 2, so the review judges against intent
- **Which assistant is in use**, since the installer supports several

## Framework: When to Use It

Use it when:
- A page is built and needs a design review covering hierarchy, clarity and polish
- You want a shared vocabulary of design commands to push a page bolder or quieter
- You want deterministic checks that run without a model as well as a model-led critique

Look elsewhere when:
- Nothing is built yet. Start at stage 1.
- You need to see the page rendered at real widths. Use `playwright-cli-pointer`.
- You want a written critique with no install. Use this library's `design-critique`.

## Install

From the project root:

```bash
npx impeccable install
```

Then, inside your AI coding tool, run once per project:

```
/impeccable init
```

The init step records product context in a `PRODUCT.md` file so later commands know the audience and purpose. In the pipeline, base that file on the direction from stage 1 so the two do not disagree.

Alternative for Claude Code, as documented upstream: `/plugin marketplace add pbakaus/impeccable`, then install it from the `/plugin` list.

Confirm the install: run `/impeccable critique` on a page and check that it responds.

## Output Format

### Pointer: impeccable
1. **Fit**: use it or not, in one sentence, with the reason
2. **Install**: the command, then the init step
3. **Check**: how to confirm it is loaded
4. **Next**: the pipeline stage that follows
5. **Credit**: author, licence, link

## Credit

- **Project**: Impeccable
- **Author**: Paul Bakaus
- **Licence**: Apache 2.0
- **Link**: https://github.com/pbakaus/impeccable
- **Docs**: https://impeccable.style
- **Lineage**: upstream states that it started from Anthropic's frontend-design skill
- **Checked**: 2026-09-28

## Quality Checks
- [ ] The install command and the init step were both given, in that order
- [ ] The author was credited with a link
- [ ] No upstream skill text, command text or detector rule was reproduced
- [ ] The critique was run on a built page, not on a plan

## Anti-Patterns
- **Skipping init.** Without product context the critique has nothing to judge against.
- **Running it together with the direction skill.** They share lineage and will still pull in different directions.
- **Treating a clean audit as proof the page looks right.** Rendering is checked in stage 5.

## Example Trigger Phrases
- "How do I install Impeccable?"
- "Which skill can critique this page for hierarchy and polish?"
- "What handles the critique stage of the design pipeline?"
- "Do I need to run anything after npx impeccable install?"

---

Part of the pm-design-taste bundle in the library at https://github.com/mohitagw15856/pm-claude-skills.

Attribution

mohitagw15856mohitagw15856
View sourceSee grades on GitHubMore from mohitagw15856 →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →