New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

80 20 Redesign Targeting

by hashgraph-online in hashgraph-online/awesome-codex-plugins

A skill your agent uses when scoping a redesign or refactor — choosing which existing surfaces deserve full attention and which can be left mostly alone.

Apache-2.0Auto-check passed

Install 80 20 Redesign Targeting

skills CLI
$ npx skills add hashgraph-online/awesome-codex-plugins --skill 80-20-redesign-targeting -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install hashgraph-online/awesome-codex-plugins 80-20-redesign-targeting --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/HDeibler/universal-design-principles/plugins/cognition-and-learnability-principles/skills/80-20-redesign-targeting .claude/skills/80-20-redesign-targeting && rm -rf skills-src

Use ~/.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/

Facts

Skill name
80-20-redesign-targeting
GitHub stars
1.3k
Token cost
~1.3k tokens
SKILL.md length
565 words
Files
2 (incl. references)
Skills in repo
716
Repo updated
First seen
Licence
Apache-2.0

At a glance

A skill your agent uses when scoping a redesign or refactor — choosing which existing surfaces deserve full attention and which can be left mostly alone.

  • Works in 4 steps: Pain analysis → Traffic analysis → Business-impact analysis → …
  • Scoping a redesign
  • SKILL.md covers How to identify high-value…, The redesign 80/20 plan, When the 80/20 cut hurts and Anti-patterns, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

80 20 Redesign Targeting is an agent skill from hashgraph-online/awesome-codex-plugins. Use this skill when scoping a redesign or refactor — choosing which existing surfaces deserve full attention and which can be left mostly alone. Trigger when the user asks "where should we focus our redesign?", "do we need to redo all of this?", or when planning incremental design improvements with limited capacity. Sub-aspect of 80-20-rule; read that first.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/redesign-case-patterns.md`).

The repository describes itself as: A curated list of awesome OpenAI Codex / ChatGPT plugins, skills, and resources. The 1 Codex Marketplace. See live plugins at: https://hol.org/plugins/best-codex-plugins. The licence is Apache-2.0.

When your agent uses it

  • Scoping a redesign
  • Refactor — choosing which existing surfaces deserve full attention and which can be left mostly alone
  • The user asks where should we focus our redesign?
  • Do we need to redo all of this?

Example prompts

  • “where should we focus our redesign?”
  • “do we need to redo all of this?”
  • “/80-20-redesign-targeting”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Pain analysis
  2. Traffic analysis
  3. Business-impact analysis
  4. Strategic-fit analysis

What it can do on your machine

Read from SKILL.md and the folder at commit 3e1456a. It shows what the files ask for, not the result of running them.

  • Tool permissions

    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.

  • Runs code

    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.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

80 20 Redesign Targeting loads about 1.3k tokens when it runs, and up to ~2k if it reads all its reference files. Until then it costs about 97 tokens; SKILL.md has 565 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~97
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2k

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.

Safety

Auto-check passed

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.

SKILL.md

The full file from hashgraph-online/awesome-codex-plugins at commit 3e1456a, republished under its Apache-2.0 licence (© hashgraph-online). 565 words, ~1,304 tokens.

Download SKILL.mdSave it as .claude/skills/80-20-redesign-targeting/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
80-20-redesign-targeting
description
Use this skill when scoping a redesign or refactor — choosing which existing surfaces deserve full attention and which can be left mostly alone. Trigger when the user asks "where should we focus our redesign?", "do we need to redo all of this?", or when planning incremental design improvements with limited capacity. Sub-aspect of `80-20-rule`; read that first.

80/20 in redesign targeting

A common failure mode of redesigns: trying to redo everything. The result is years-long projects that ship late, lose institutional context, and arrive in a state no better than incremental updates would have produced. The 80/20 rule applied to redesign: identify the surfaces that produce most of user pain or business value; concentrate redesign effort there; leave the rest alone or batch into a maintenance pass.

How to identify high-value surfaces

1. Pain analysis

Where do users struggle? Sources:

  • Support ticket categorization (which surfaces generate the most "how do I..." or "I can't..." tickets)
  • Session recordings and rage-click analytics
  • Drop-off / abandonment metrics (where users leave the funnel)
  • Time-on-task for primary flows (where users get stuck)

The 80/20 cut: ~20% of surfaces typically account for ~80% of pain.

2. Traffic analysis

Where do users actually spend time? A beautiful but rarely-visited page deserves less polish than an ugly but constantly-used one.

Cross-reference traffic with the surface's role: a low-traffic but business-critical surface (Settings → Billing) earns redesign even if traffic alone wouldn't justify it.

3. Business-impact analysis

Conversion surfaces (sign-up, checkout, upgrade) often punch above their traffic weight. A 5% lift on a low-traffic checkout might exceed a 30% lift on a high-traffic blog.

4. Strategic-fit analysis

Some surfaces represent the brand or category position. The marketing home page, the first-run experience, the demo screen for sales. These deserve disproportionate attention because they shape perception of the whole product.

The redesign 80/20 plan

A typical redesign plan that respects 80/20:

Phase 1 (the critical 20% — heavy investment)
  - Top 3–5 user-facing surfaces by pain × traffic × business impact
  - Full redesign: research, design, build, polish, A/B test
  - Often 60–70% of the project budget

Phase 2 (the meaningful tail — moderate investment)
  - Next 10–15 surfaces
  - Update to new design system; fix obvious issues; don't redesign whole flows
  - 20–30% of budget

Phase 3 (the rest — minimal investment)
  - All remaining surfaces
  - Apply new design system tokens; update components; cosmetic only
  - 10% of budget

Phase 4 (revisit)
  - Six months in: re-measure. The "rest" that wasn't redesigned might still be performing fine.
  - For surfaces that turn out to be problematic, fold into the next cycle.

Phases 1–3 ship over the course of the project; Phase 4 is the post-mortem that informs the next cycle.

When the 80/20 cut hurts

  • Design system consistency. If only 20% of surfaces get the new design and 80% don't, the product feels visually fragmented. Mitigation: even surfaces that don't get full redesign should adopt the design system tokens (color, type, spacing) for consistency.
  • Migration burden. Mixing old and new components creates maintenance complexity. Plan for the eventual deprecation of old components even if you're not redesigning every surface that uses them.
  • Edge-case surfaces. A surface used by 1% of users might be the only surface for a critical use case. The 80/20 cut shouldn't drop it.
Show full SKILL.md (197 more words)Show less

Anti-patterns

  • The Big Bang redesign. Two-year project to redesign everything. Ships late, loses context, doesn't move metrics.
  • Surface-by-surface without strategy. Each surface designed independently with no shared system. Result: visual inconsistency.
  • Pet-surface focus. The team enjoys redesigning the most fun surfaces (marketing landing) while neglecting the highest-pain ones (settings, billing).
  • No measurement. A redesign ships with no before/after metrics. The team can't tell if it worked.

Heuristics

  1. The pain-traffic matrix. Plot surfaces by pain × traffic. Concentrate redesign on the top-right quadrant.
  2. The "would users notice?" check. For each candidate surface, ask: if we redesigned this and showed users, would they tell us it's better? If "probably not," lower priority.
  3. The conversion-impact estimate. For business-critical surfaces, estimate revenue impact of a 10% lift. Surfaces where 10% lift is meaningful deserve A/B tested redesign; surfaces where it isn't deserve cosmetic-only updates.
  4. The post-redesign metric. Define metrics before the redesign ships. If you can't measure improvement, you didn't redesign for the right reason.
  • 80-20-rule (parent).
  • 80-20-feature-prioritization — applied to new feature planning rather than redesign.
  • iteration (process) — redesigns benefit from iterative releases, not big bangs.
  • factor-of-safety (process) — redesign with safety: A/B test, kill-switch, rollback paths.

© hashgraph-online, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in plugins/HDeibler/universal-design-principles/plugins/cognition-and-learnability-principles/skills/80-20-redesign-targeting of hashgraph-online/awesome-codex-plugins.

  • SKILL.md
  • references/redesign-case-patterns.md

Open the folder on GitHubat commit 3e1456a

Compare with similar skills

80 20 Redesign Targeting 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.

80 20 Redesign Targeting compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
80 20 Redesign Targeting this skillhashgraph-online/awesome-codex-plugins1.3k—~1.3kAutomated safety check: PassApache-2.0
Refactorgithub/awesome-copilot40k6 repos~4.2kAutomated safety check: PassMIT
Component Refactoringlangflow-ai/langflow155k—~3.5kAutomated safety check: PassMIT
Openclaw Refactor Docsopenclaw/openclaw392k—~1.9kAutomated safety check: PassMIT
Code Refactoring Workflowluongnv89/claude-howto42k—~3.1kAutomated safety check: PassMIT
Refactoring Skill (Vietnamese)luongnv89/claude-howto42k—~3.1kAutomated safety check: PassMIT

Similar skills

  • Refactor

    github/awesome-copilot

    Official

    Surgical code refactoring to improve maintainability without changing behavior.

    40k GitHub starsUsed in 6 repos~4.2k tokens
    DevelopmentAuto-check passed

  • Component Refactoring

    langflow-ai/langflow

    Refactor high-complexity React components in Langflow frontend.

    155k GitHub stars~3.5k tokensUpdated yesterday
    DevelopmentAuto-check passed

  • Openclaw Refactor Docs

    openclaw/openclaw

    Refactor an existing OpenClaw docs page with source-audited preservation, restructuring, and verification.

    392k GitHub stars~1.9k tokensUpdated today
    DevelopmentAuto-check passed

  • Code Refactoring Workflow

    luongnv89/claude-howto

    Guides systematic, test-backed refactoring in the style of Martin Fowler, moving through research, planning and small incremental changes with your approval at each phase.

    42k GitHub stars~3.1k tokensUpdated 10 days ago
    DevelopmentAuto-check passed

  • Refactoring Skill (Vietnamese)

    luongnv89/claude-howto

    Vietnamese edition of a systematic refactoring skill based on Martin Fowler's book, working in approved phases with small, test-backed changes.

    42k GitHub stars~3.1k tokensUpdated 10 days ago
    DevelopmentAuto-check passed

  • Systematic Code Refactoring

    luongnv89/claude-howto

    Guides refactoring in phases based on Martin Fowler's method: research, test coverage check, planning and small tested steps, with your approval at each phase.

    42k GitHub stars~3k tokensUpdated 10 days ago
    DevelopmentAuto-check passed

More from hashgraph-online/awesome-codex-plugins

All 716 skills in this repo

  • Anime Reaction Gif

    hashgraph-online/awesome-codex-plugins

    Create original anime-style reaction stickers as looping GIFs and MP4 previews, using generated character pose sheets and timed key poses.

    1.3k GitHub stars~922 tokensUpdated yesterday
    Auto-check passed

  • Calibredb

    hashgraph-online/awesome-codex-plugins

    Manage and query Calibre libraries with the calibredb CLI (local paths or Calibre Content server URLs).

    1.3k GitHub stars~1k tokensUpdated yesterday
    Auto-check passed

  • Rust API Test Harness

    hashgraph-online/awesome-codex-plugins

    A skill your agent uses when adding, changing, testing, or debugging Rust HTTP APIs and services, especially when Codex needs black-box integration tests, random-port app startup, real database test…

    1.3k GitHub stars~1.7k tokensUpdated yesterday
    Auto-check passed

  • Art

    hashgraph-online/awesome-codex-plugins

    Make a studio's game look like something at build time — a cover from a real frame of the game (free), painted covers, backdrops, textures and character plates from image models through the…

    1.3k GitHub stars~2.4k tokensUpdated yesterday
    Auto-check passed

  • Calle

    hashgraph-online/awesome-codex-plugins

    Use CALL-E from Codex through the calle CLI. An agent skill from hashgraph-online/awesome-codex-plugins.

    1.3k GitHub stars~2.9k tokensUpdated yesterday
    Auto-check passed

  • Game Balance Economy

    hashgraph-online/awesome-codex-plugins

    Balance game difficulty, resources, rewards, probability, progression, economies, and dominant strategies.

    1.3k GitHub stars~618 tokensUpdated yesterday
    Auto-check passed

Questions about 80 20 Redesign Targeting

What does 80 20 Redesign Targeting do?

A skill your agent uses when scoping a redesign or refactor — choosing which existing surfaces deserve full attention and which can be left mostly alone. 80 20 Redesign Targeting is an agent skill from hashgraph-online/awesome-codex-plugins. Use this skill when scoping a redesign or refactor — choosing which existing surfaces deserve full attention and which can be left mostly alone.

When should I use 80 20 Redesign Targeting?

80 20 Redesign Targeting fits situations like: scoping a redesign; refactor — choosing which existing surfaces deserve full attention and which can be left mostly alone; the user asks where should we focus our redesign?; do we need to redo all of this?.

How do I install 80 20 Redesign Targeting in Claude Code?

Run `npx skills add hashgraph-online/awesome-codex-plugins --skill 80-20-redesign-targeting -a claude-code`. Or copy the skill folder (plugins/HDeibler/universal-design-principles/plugins/cognition-and-learnability-principles/skills/80-20-redesign-targeting in hashgraph-online/awesome-codex-plugins) into .claude/skills/80-20-redesign-targeting in your project. Claude Code loads it when a task matches its description.

How do I install 80 20 Redesign Targeting in Codex?

Run `npx skills add hashgraph-online/awesome-codex-plugins --skill 80-20-redesign-targeting -a codex`. Or copy the skill folder (plugins/HDeibler/universal-design-principles/plugins/cognition-and-learnability-principles/skills/80-20-redesign-targeting in hashgraph-online/awesome-codex-plugins) into .agents/skills/80-20-redesign-targeting in your project. Codex loads it when a task matches its description.

Can I use 80 20 Redesign Targeting in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add hashgraph-online/awesome-codex-plugins --skill 80-20-redesign-targeting -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/80-20-redesign-targeting, .gemini/skills/80-20-redesign-targeting, .github/skills/80-20-redesign-targeting and .opencode/skills/80-20-redesign-targeting in your project.

What does 80 20 Redesign Targeting need to run?

SKILL.md names no scripts, command-line tools or credentials: 80 20 Redesign Targeting is instructions for the agent only.

Does 80 20 Redesign Targeting access the network?

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.

Is 80 20 Redesign Targeting safe to install?

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.

What licence does 80 20 Redesign Targeting use?

80 20 Redesign Targeting is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does 80 20 Redesign Targeting use?

About 1.3k tokens (SKILL.md is roughly 5.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 709 tokens, read only when the agent opens those files.

What are the alternatives to 80 20 Redesign Targeting?

Skills that share tags, products or a category with 80 20 Redesign Targeting: Refactor (github/awesome-copilot, 40k stars), Component Refactoring (langflow-ai/langflow, 155k stars), Openclaw Refactor Docs (openclaw/openclaw, 392k stars) and Code Refactoring Workflow (luongnv89/claude-howto, 42k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains 80 20 Redesign Targeting?

hashgraph-online (a GitHub organization) maintains it in hashgraph-online/awesome-codex-plugins, which has 1,267 GitHub stars. The repository holds 716 skills in this directory. The repository was last updated on October 10, 2026.

Source: hashgraph-online/awesome-codex-plugins on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.