ai-agent-skills 3.5.0 → 3.5.1

package/README.md

@@ -1,43 +1,51 @@
-# AI Agent Skills
+<h1 align="center">AI Agent Skills</h1>
 
-My curated agent skills library.
+<p align="center">
+  <strong>My curated library of agent skills, plus the package to build your own.</strong>
+</p>
 
-There are a lot of skills now. These are the ones I actually keep around.
+<p align="center">
+  A smaller library for Claude Code, Codex, Cursor, and other <code>SKILL.md</code>-compatible agents.
+</p>
 
 <!-- GENERATED:library-stats:start -->
-- 55 skills total
-- 5 shelves
-- 8 house copies
-- 47 cataloged upstream
+<p align="center">
+  <a href="https://github.com/MoizIbnYousaf/Ai-Agent-Skills"><img alt="GitHub stars" src="https://img.shields.io/github/stars/MoizIbnYousaf/Ai-Agent-Skills?style=for-the-badge&label=stars&labelColor=313244&color=89b4fa&logo=github&logoColor=cdd6f4" /></a>
+  <a href="https://www.npmjs.com/package/ai-agent-skills"><img alt="npm version" src="https://img.shields.io/npm/v/ai-agent-skills?style=for-the-badge&label=version&labelColor=313244&color=b4befe&logo=npm&logoColor=cdd6f4" /></a>
+  <a href="https://www.npmjs.com/package/ai-agent-skills"><img alt="npm total downloads" src="https://img.shields.io/npm/dt/ai-agent-skills?style=for-the-badge&label=downloads&labelColor=313244&color=f5e0dc&logo=npm&logoColor=cdd6f4" /></a>
+  <a href="https://github.com/MoizIbnYousaf/Ai-Agent-Skills#shelves"><img alt="Library structure" src="https://img.shields.io/badge/library-55%20skills%20%C2%B7%205%20shelves-cba6f7?style=for-the-badge&labelColor=313244&logo=bookstack&logoColor=cdd6f4" /></a>
+</p>
+
+<p align="center"><sub>8 house copies · 47 cataloged upstream</sub></p>
 <!-- GENERATED:library-stats:end -->
 
-The point is not to be a registry. The point is to be a bookshelf.
+<p align="center"><em>Picked, shelved, and maintained by hand.</em></p>
 
-## What This Is
+## Library
 
 `ai-agent-skills` is a CLI library of agent skills for tools like Claude Code, Codex, Cursor, and other SKILL.md-compatible agents.
 
-The library is organized the way I actually work:
+I organize it the way I work:
 
 - Start with a shelf like `frontend` or `workflow`
-- See a small set of vetted skills, not every possible match
-- Keep provenance visible so upstream repos stay credited
-- Keep editorial notes visible so the curation is the product
+- Keep the set small enough to browse quickly
+- Keep provenance visible
+- Keep notes that explain why a skill is here
 
-If you want the broad open ecosystem, use `skills.sh`.
-If you want my shelves, use this repo.
+Use `skills.sh` for the broad ecosystem.
+Use this repo for my kept set.
 
-## Why This Repo Still Exists
+## Why Keep It
 
 I launched this on December 17, 2025, before `skills.sh` existed and before the ecosystem had a clear default universal installer.
 
-Originally this repo was that universal installer. That part still works.
+Originally this repo was that installer. That part still matters.
 
-What makes it worth keeping now is the library itself: the shelves, the provenance, and the editorial judgment. `skills.sh` is the broad open ecosystem. This repo is the smaller personal library I actually reach for.
+I keep it because the library itself has become useful: shelves, provenance, and notes that make the curation legible.
 
-## The Two-Tier Model
+## How It Works
 
-Every skill in the library is one of two things:
+Each skill here is either a house copy or a cataloged upstream pick.
 
 - `House copies`
   Local folders under `skills/<name>/`.
@@ -47,7 +55,7 @@ Every skill in the library is one of two things:
   Metadata in `skills.json` with no local folder.
   These stay upstream and install live from the source repo when you ask for them.
 
-The library stays lean because it does not pretend to own upstream content.
+Upstream work stays upstream. That keeps the library lean.
 
 ## Quick Start
 
@@ -84,16 +92,16 @@ Default install targets:
 
 Legacy agent-specific targets still work through `--agent <name>`.
 
-## How To Read The Library
+## Browse
 
-There are two main ways to browse it:
+Most browsing starts in one of two places:
 
 | View | Why it exists | Start here |
 | --- | --- | --- |
 | Shelves | The main way to understand the library: start with the kind of work, then drill into the small set of picks on that shelf. | `npx ai-agent-skills list` |
 | Sources | The provenance view: see which publishers feed which shelves and branches. | `npx ai-agent-skills info frontend-design` |
 
-Secondary surfaces still exist, but they are not the main taxonomy:
+The other views are still there. They are just secondary:
 
 - `npx ai-agent-skills browse` for the TUI
 - `npx ai-agent-skills list --collection my-picks` for a cross-shelf starter stack
@@ -102,7 +110,7 @@ Secondary surfaces still exist, but they are not the main taxonomy:
 
 ## Shelves
 
-These are the shelves. They are the product.
+The shelves are the main structure.
 
 <!-- GENERATED:shelf-table:start -->
 | Shelf | Skills | What it covers |
@@ -118,22 +126,22 @@ The full map lives in [WORK_AREAS.md](./WORK_AREAS.md).
 
 ## Collections
 
-Collections still exist, but they are secondary. They can be starter stacks or installable packs, but shelves are still the main taxonomy.
+Collections are smaller sets. Useful, but secondary to the shelves.
 
 <!-- GENERATED:collection-table:start -->
 | Collection | Why it exists | Start here |
 | --- | --- | --- |
-| `my-picks` | The smallest cross-shelf starter stack: the skills I would reach for first on a fresh setup. | `frontend-design`, `mcp-builder`, `pdf` |
-| `build-apps` | Frontend and design implementation skills for shipping polished product work. | `frontend-design`, `frontend-skill`, `shadcn` |
-| `swift-agent-skills` | A curated Swift and Apple-platform hub inside ai-agent-skills, collecting the main upstream Swift skills as one installable set. | `swiftui-pro`, `swiftui-ui-patterns`, `swiftui-design-principles` |
-| `build-systems` | Architecture, MCP, backend, and security picks for deeper engineering work. | `mcp-builder`, `backend-development`, `database-design` |
-| `test-and-debug` | The shelf for QA, regression, CI cleanup, observability, and debugging discipline. | `playwright`, `webapp-testing`, `gh-fix-ci` |
-| `docs-and-research` | File-heavy work, writing, docs, and research flows that end in something usable. | `pdf`, `doc-coauthoring`, `docx` |
+| `my-picks` | A short starter stack. These are the skills I reach for first. | `frontend-design`, `mcp-builder`, `pdf` |
+| `build-apps` | Frontend, UI, and design work for shipping polished apps. | `frontend-design`, `frontend-skill`, `shadcn` |
+| `swift-agent-skills` | The main Swift and Apple-platform set in this library. Install it all at once or pick from it. | `swiftui-pro`, `swiftui-ui-patterns`, `swiftui-design-principles` |
+| `build-systems` | Backend, architecture, MCP, and security work. | `mcp-builder`, `backend-development`, `database-design` |
+| `test-and-debug` | QA, debugging, CI cleanup, and observability. | `playwright`, `webapp-testing`, `gh-fix-ci` |
+| `docs-and-research` | Docs, files, research, and writing work. | `pdf`, `doc-coauthoring`, `docx` |
 <!-- GENERATED:collection-table:end -->
 
-## Catalog Curation
+## Curating The Catalog
 
-The `catalog` command is how I pull from upstream repos without vendoring everything.
+Use `catalog` when you want to add an upstream skill without vendoring it.
 
 ```bash
 npx ai-agent-skills catalog openai/skills --list
@@ -143,15 +151,15 @@ npx ai-agent-skills catalog conorluddy/ios-simulator-skill --skill ios-simulator
 npx ai-agent-skills catalog shadcn-ui/ui --skill shadcn --area frontend --branch Components
 ```
 
-That command does not copy the upstream skill into this repo.
-It adds metadata and editorial placement:
+It does not copy the skill into this repo.
+It adds metadata and placement:
 
 - which shelf it belongs on
 - what branch it lives under
 - why it earned a place
 - how it should install later
 
-For existing picks, `curate` is the fast loop:
+For existing picks, `curate` is the quick loop:
 
 ```bash
 npx ai-agent-skills curate frontend-design --branch Implementation
@@ -161,7 +169,7 @@ npx ai-agent-skills curate frontend-design --why "A stronger note that matches h
 npx ai-agent-skills curate review
 ```
 
-When I explicitly want a new house copy, `vendor` is the only path that does it:
+When I want a local copy, I use `vendor`:
 
 ```bash
 npx ai-agent-skills vendor <repo-or-path> --skill <name> --area <shelf> --branch <branch> --why "Why this deserves a local copy."
@@ -170,7 +178,7 @@ npx ai-agent-skills vendor <repo-or-path> --skill <name> --area mobile --branch
 
 ## Source Repos
 
-Current source mix:
+Current upstream mix:
 
 <!-- GENERATED:source-table:start -->
 | Source repo | Skills |
@@ -204,8 +212,8 @@ Current source mix:
 | `vanab/swiftdata-agent-skill` | 1 |
 <!-- GENERATED:source-table:end -->
 
-The two major upstream publishers in this library are Anthropic and OpenAI.
-I do not import everything they ship. I browse, pick, and shelve.
+The two biggest upstream publishers in this library are Anthropic and OpenAI.
+I browse, pick, and shelve. I do not mirror everything they publish.
 
 ## Commands
 
@@ -250,8 +258,6 @@ npx ai-agent-skills vendor <repo-or-path> --skill <name> --area <shelf> --branch
 
 ## Testing
 
-There are two layers on purpose:
-
 - `npm test`
   Fast regression coverage for CLI behavior, schema rules, routing, and local install flows.
 - `npm run test:live`
@@ -261,7 +267,7 @@ There are two layers on purpose:
 
 ## Legacy Agent Support
 
-These still work through `--agent <name>`:
+Still supported through `--agent <name>`:
 
 - `claude`
 - `cursor`
@@ -276,19 +282,17 @@ These still work through `--agent <name>`:
 - `kilocode`
 - `project`
 
-## Why It Feels Different
-
-This repo is opinionated on purpose.
+## What I Care About
 
-- Small shelves beat giant taxonomies
-- Editorial notes beat anonymous tags
-- Provenance should stay visible
-- Upstream repos should stay upstream
-- A curated library should feel maintained, not harvested
+- Small shelves
+- Clear provenance
+- Notes that explain the keep
+- Upstream repos staying upstream
+- A library that looks maintained
 
 ## Contributing
 
-This is a curated library, not an open registry.
+This is a curated library.
 
 Read [CURATION.md](./CURATION.md) before opening a PR.
 

package/cli.js

@@ -1788,7 +1788,7 @@ function listSkills(category = null, tags = null, collectionId = null, workArea
     };
     log(`\n${colors.bold}Curated Library${colors.reset}`);
     log(`${colors.dim}${formatCount(counts.total, 'pick')} on ${formatCount(orderedAreas.length, 'shelf', 'shelves')} · ${formatCount(counts.house, 'house copy', 'house copies')} · ${formatCount(counts.upstream, 'cataloged upstream pick', 'cataloged upstream picks')}${colors.reset}`);
-    log(`${colors.dim}Small enough to scan. Opinionated enough to trust.${colors.reset}\n`);
+    log(`${colors.dim}Browse by shelf first.${colors.reset}\n`);
 
     orderedAreas.forEach(areaId => {
       const meta = getWorkAreaMeta(data, areaId);
@@ -2991,7 +2991,8 @@ function installFromLocalPath(source, agent = 'claude', dryRun = false) {
 
 function showHelp() {
   log(`
-${colors.bold}AI Agent Skills${colors.reset} \u2014 My curated agent skills library
+${colors.bold}AI Agent Skills${colors.reset}
+Curated agent skills library and installer
 
 ${colors.bold}Usage:${colors.reset}
   npx ai-agent-skills [command] [options]

package/lib/render-docs.cjs

@@ -37,11 +37,27 @@ function buildLibraryStatsSection(data) {
   const total = data.skills.length;
   const house = data.skills.filter((skill) => skill.tier === 'house').length;
   const upstream = total - house;
+  const badgeBase = 'https://img.shields.io';
+  const repoUrl = 'https://github.com/MoizIbnYousaf/Ai-Agent-Skills';
+  const npmUrl = 'https://www.npmjs.com/package/ai-agent-skills';
+  const libraryUrl = `${repoUrl}#shelves`;
+  const labelBg = '313244';
+  const lightText = 'cdd6f4';
+  const starsAccent = '89b4fa';
+  const versionAccent = 'b4befe';
+  const downloadsAccent = 'f5e0dc';
+  const libraryAccent = 'cba6f7';
+  const libraryMessage = encodeURIComponent(`${total} skills · ${data.workAreas.length} shelves`);
+
   return [
-    `- ${total} skills total`,
-    `- ${data.workAreas.length} shelves`,
-    `- ${house} house copies`,
-    `- ${upstream} cataloged upstream`,
+    '<p align="center">',
+    `  <a href="${repoUrl}"><img alt="GitHub stars" src="${badgeBase}/github/stars/MoizIbnYousaf/Ai-Agent-Skills?style=for-the-badge&label=stars&labelColor=${labelBg}&color=${starsAccent}&logo=github&logoColor=${lightText}" /></a>`,
+    `  <a href="${npmUrl}"><img alt="npm version" src="${badgeBase}/npm/v/ai-agent-skills?style=for-the-badge&label=version&labelColor=${labelBg}&color=${versionAccent}&logo=npm&logoColor=${lightText}" /></a>`,
+    `  <a href="${npmUrl}"><img alt="npm total downloads" src="${badgeBase}/npm/dt/ai-agent-skills?style=for-the-badge&label=downloads&labelColor=${labelBg}&color=${downloadsAccent}&logo=npm&logoColor=${lightText}" /></a>`,
+    `  <a href="${libraryUrl}"><img alt="Library structure" src="${badgeBase}/badge/library-${libraryMessage}-${libraryAccent}?style=for-the-badge&labelColor=${labelBg}&logo=bookstack&logoColor=${lightText}" /></a>`,
+    '</p>',
+    '',
+    `<p align="center"><sub>${house} house copies · ${upstream} cataloged upstream</sub></p>`,
   ].join('\n');
 }
 
@@ -126,9 +142,9 @@ function renderWorkAreas(data) {
   return ensureTrailingNewline([
     '# Work Areas',
     '',
-    'This is the shelf map for the library.',
+    'Shelf map for the library.',
     '',
-    'The repo folders stay flat under `skills/<name>/` for house copies. The catalog carries the real organization.',
+    'House copies stay flat under `skills/<name>/`. The catalog holds the real structure.',
     '',
     sections.join('\n'),
   ].join('\n'));

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "ai-agent-skills",
-  "version": "3.5.0",
-  "description": "My curated agent skills library, with a CLI that installs from any source.",
+  "version": "3.5.1",
+  "description": "Curated agent skills library and CLI installer.",
   "main": "cli.js",
   "bin": {
     "ai-agent-skills": "cli.js"

package/skills.json

@@ -1,5 +1,5 @@
 {
-  "version": "3.5.0",
+  "version": "3.5.1",
   "updated": "2026-03-27T00:00:00Z",
   "total": 55,
   "workAreas": [
@@ -33,7 +33,7 @@
     {
       "id": "my-picks",
       "title": "My Picks",
-      "description": "The smallest cross-shelf starter stack: the skills I would reach for first on a fresh setup.",
+      "description": "A short starter stack. These are the skills I reach for first.",
       "skills": [
         "frontend-design",
         "mcp-builder",
@@ -46,7 +46,7 @@
     {
       "id": "build-apps",
       "title": "Build Apps",
-      "description": "Frontend and design implementation skills for shipping polished product work.",
+      "description": "Frontend, UI, and design work for shipping polished apps.",
       "skills": [
         "frontend-design",
         "frontend-skill",
@@ -58,7 +58,7 @@
     {
       "id": "swift-agent-skills",
       "title": "Swift Agent Skills",
-      "description": "A curated Swift and Apple-platform hub inside ai-agent-skills, collecting the main upstream Swift skills as one installable set.",
+      "description": "The main Swift and Apple-platform set in this library. Install it all at once or pick from it.",
       "skills": [
         "swiftui-pro",
         "swiftui-ui-patterns",
@@ -89,7 +89,7 @@
     {
       "id": "build-systems",
       "title": "Build Systems",
-      "description": "Architecture, MCP, backend, and security picks for deeper engineering work.",
+      "description": "Backend, architecture, MCP, and security work.",
       "skills": [
         "mcp-builder",
         "backend-development",
@@ -102,7 +102,7 @@
     {
       "id": "test-and-debug",
       "title": "Test & Debug",
-      "description": "The shelf for QA, regression, CI cleanup, observability, and debugging discipline.",
+      "description": "QA, debugging, CI cleanup, and observability.",
       "skills": [
         "playwright",
         "webapp-testing",
@@ -114,7 +114,7 @@
     {
       "id": "docs-and-research",
       "title": "Docs & Research",
-      "description": "File-heavy work, writing, docs, and research flows that end in something usable.",
+      "description": "Docs, files, research, and writing work.",
       "skills": [
         "pdf",
         "doc-coauthoring",
@@ -149,7 +149,7 @@
       "trust": "verified",
       "syncMode": "live",
       "sourceUrl": "https://github.com/anthropics/skills/tree/main/skills/frontend-design",
-      "whyHere": "Kept because Anthropic's frontend design guidance is still high-signal for interface craft, visual direction, and polished product execution without collapsing into generic app UI.",
+      "whyHere": "Still one of the stronger frontend skills around for interface craft, visual direction, and polished product work.",
       "lastVerified": "2026-03-13",
       "vendored": false,
       "installSource": "anthropics/skills/skills/frontend-design",
@@ -177,7 +177,7 @@
       "trust": "verified",
       "syncMode": "live",
       "sourceUrl": "https://github.com/anthropics/skills/tree/main/skills/pdf",
-      "whyHere": "Kept because Anthropic's PDF guidance is still high-signal for docs, file-heavy tasks, and long-form output, and the library ships a stable snapshot so installs stay deterministic.",
+      "whyHere": "Worth keeping as a stable copy for PDF-heavy work.",
       "lastVerified": "2026-03-13",
       "vendored": false,
       "installSource": "anthropics/skills/skills/pdf",
@@ -202,7 +202,7 @@
       "trust": "verified",
       "syncMode": "live",
       "sourceUrl": "https://github.com/anthropics/skills/tree/main/skills/xlsx",
-      "whyHere": "Kept because Anthropic's Spreadsheets guidance is still high-signal for docs, file-heavy tasks, and long-form output, and the library ships a stable snapshot so installs stay deterministic.",
+      "whyHere": "Worth keeping as a stable copy for spreadsheet work.",
       "lastVerified": "2026-03-13",
       "vendored": false,
       "installSource": "anthropics/skills/skills/xlsx",
@@ -227,7 +227,7 @@
       "trust": "verified",
       "syncMode": "live",
       "sourceUrl": "https://github.com/anthropics/skills/tree/main/skills/docx",
-      "whyHere": "Kept because Anthropic's Documents guidance is still high-signal for docs, file-heavy tasks, and long-form output, and the library ships a stable snapshot so installs stay deterministic.",
+      "whyHere": "Worth keeping as a stable copy for document work.",
       "lastVerified": "2026-03-13",
       "vendored": false,
       "installSource": "anthropics/skills/skills/docx",
@@ -252,7 +252,7 @@
       "trust": "verified",
       "syncMode": "live",
       "sourceUrl": "https://github.com/anthropics/skills/tree/main/skills/pptx",
-      "whyHere": "Kept because Anthropic's Presentations guidance is still high-signal for docs, file-heavy tasks, and long-form output, and the library ships a stable snapshot so installs stay deterministic.",
+      "whyHere": "Worth keeping as a stable copy for presentation work.",
       "lastVerified": "2026-03-13",
       "vendored": false,
       "installSource": "anthropics/skills/skills/pptx",
@@ -282,7 +282,7 @@
       "trust": "verified",
       "syncMode": "live",
       "sourceUrl": "https://github.com/anthropics/skills/tree/main/skills/mcp-builder",
-      "whyHere": "Kept because Anthropic's MCP guidance is still high-signal for systems, architecture, and deeper codebase work, and the library ships a stable snapshot so installs stay deterministic.",
+      "whyHere": "One of the clearest MCP skills in the ecosystem. Worth keeping close as a stable copy.",
       "lastVerified": "2026-03-13",
       "vendored": false,
       "installSource": "anthropics/skills/skills/mcp-builder",
@@ -307,7 +307,7 @@
       "trust": "verified",
       "syncMode": "live",
       "sourceUrl": "https://github.com/anthropics/skills/tree/main/skills/skill-creator",
-      "whyHere": "Kept because Anthropic's Skills guidance is still high-signal for execution, planning, and day-to-day operating flow, and the library ships a stable snapshot so installs stay deterministic.",
+      "whyHere": "Useful when a repo needs a new skill or a cleanup pass on an old one.",
       "lastVerified": "2026-03-13",
       "vendored": false,
       "installSource": "anthropics/skills/skills/skill-creator",
@@ -332,7 +332,7 @@
       "trust": "verified",
       "syncMode": "live",
       "sourceUrl": "https://github.com/anthropics/skills/tree/main/skills/doc-coauthoring",
-      "whyHere": "Kept because Anthropic's Writing skill remains one of the strongest starting points for docs, file-heavy tasks, and long-form output.",
+      "whyHere": "Still one of the better starting points for collaborative writing and document work.",
       "lastVerified": "2026-03-13",
       "vendored": false,
       "installSource": "anthropics/skills/skills/doc-coauthoring",
@@ -357,7 +357,7 @@
       "trust": "verified",
       "syncMode": "live",
       "sourceUrl": "https://github.com/anthropics/skills/tree/main/skills/canvas-design",
-      "whyHere": "Kept because Anthropic's Canvas guidance is still high-signal for visual direction and design craft, and the library ships a stable snapshot so installs stay deterministic.",
+      "whyHere": "Useful for visual direction and design craft when a task starts rough.",
       "lastVerified": "2026-03-13",
       "vendored": false,
       "installSource": "anthropics/skills/skills/canvas-design",
@@ -387,7 +387,7 @@
       "trust": "verified",
       "syncMode": "live",
       "sourceUrl": "https://github.com/anthropics/skills/tree/main/skills/webapp-testing",
-      "whyHere": "Kept because Anthropic's Web QA guidance is still high-signal for review, QA, and product-quality work, and the library ships a stable snapshot so installs stay deterministic.",
+      "whyHere": "Good web QA guidance with real product-testing value.",
       "lastVerified": "2026-03-13",
       "vendored": false,
       "installSource": "anthropics/skills/skills/webapp-testing",
@@ -412,7 +412,7 @@
       "trust": "verified",
       "syncMode": "live",
       "sourceUrl": "https://github.com/anthropics/skills/tree/main/skills/brand-guidelines",
-      "whyHere": "Kept because Anthropic's Brand guidance is still high-signal for adjacent business and operating work, and the library ships a stable snapshot so installs stay deterministic.",
+      "whyHere": "Useful when product work spills into brand and visual system decisions.",
       "lastVerified": "2026-03-13",
       "vendored": false,
       "installSource": "anthropics/skills/skills/brand-guidelines",
@@ -519,7 +519,7 @@
       "trust": "listed",
       "syncMode": "snapshot",
       "sourceUrl": "https://github.com/wshobson/agents/tree/main/plugins/documentation-generation",
-      "whyHere": "Kept because this wshobson pattern still earns a place for docs, file-heavy tasks, and long-form output, even though upstream has since reorganized around plugins.",
+      "whyHere": "Still a good documentation skill, even after upstream reorganized around plugins.",
       "tier": "house",
       "vendored": true,
       "distribution": "bundled",
@@ -549,7 +549,7 @@
       "trust": "verified",
       "syncMode": "adapted",
       "sourceUrl": "https://github.com/MoizIbnYousaf/Ai-Agent-Skills/tree/main/skills/ask-questions-if-underspecified",
-      "whyHere": "Kept because this requirement-clarification pattern is one of the cleanest ways to stop agents from running ahead on underspecified work.",
+      "whyHere": "A clean guardrail against agents sprinting through half-specified work.",
       "lastVerified": "2026-03-13",
       "tier": "house",
       "vendored": true,
@@ -605,7 +605,7 @@
       "trust": "listed",
       "syncMode": "mirror",
       "sourceUrl": "https://github.com/ComposioHQ/awesome-claude-skills/tree/master/changelog-generator",
-      "whyHere": "Kept because release notes are a real recurring workflow task, and this one is more practical than a generic writing skill when a ship checklist needs finishing.",
+      "whyHere": "Practical release-note help for real ship cycles.",
       "tier": "house",
       "vendored": true,
       "distribution": "bundled",
@@ -629,7 +629,7 @@
       "trust": "listed",
       "syncMode": "mirror",
       "sourceUrl": "https://github.com/ComposioHQ/awesome-claude-skills/tree/master/content-research-writer",
-      "whyHere": "Kept because the research shelf needs one skill that turns raw findings into a usable written brief instead of stopping at collection.",
+      "whyHere": "Turns research into usable writing.",
       "tier": "house",
       "vendored": true,
       "distribution": "bundled",
@@ -658,7 +658,7 @@
       "trust": "reviewed",
       "syncMode": "live",
       "sourceUrl": "https://github.com/openai/skills/tree/main/skills/.system/openai-docs",
-      "whyHere": "Kept because it gives the library a current, official path into OpenAI docs, model guidance, and implementation help.",
+      "whyHere": "Gives the library a direct path into current OpenAI docs and model guidance.",
       "vendored": false,
       "installSource": "openai/skills/skills/.system/openai-docs",
       "tier": "upstream",
@@ -687,7 +687,7 @@
       "trust": "reviewed",
       "syncMode": "live",
       "sourceUrl": "https://github.com/openai/skills/tree/main/skills/.curated/gh-fix-ci",
-      "whyHere": "Kept because OpenAI's CI skill is current, high-signal, and fits the library well for review, QA, and product-quality work.",
+      "whyHere": "Worth keeping for CI cleanup and broken checks.",
       "vendored": false,
       "installSource": "openai/skills/skills/.curated/gh-fix-ci",
       "tier": "upstream",
@@ -716,7 +716,7 @@
       "trust": "reviewed",
       "syncMode": "live",
       "sourceUrl": "https://github.com/openai/skills/tree/main/skills/.curated/figma",
-      "whyHere": "Kept because OpenAI's Figma skill is current, high-signal, and fits the library well for visual direction and design craft.",
+      "whyHere": "A good fit for UI and design-engineering work.",
       "vendored": false,
       "installSource": "openai/skills/skills/.curated/figma",
       "tier": "upstream",
@@ -745,7 +745,7 @@
       "trust": "listed",
       "syncMode": "live",
       "sourceUrl": "https://github.com/openai/skills/tree/main/skills/.curated/sentry",
-      "whyHere": "Kept because OpenAI's Observability skill is current, high-signal, and fits the library well for review, QA, and product-quality work.",
+      "whyHere": "Useful for debugging and observability work.",
       "vendored": false,
       "installSource": "openai/skills/skills/.curated/sentry",
       "tier": "upstream",
@@ -774,7 +774,7 @@
       "trust": "reviewed",
       "syncMode": "live",
       "sourceUrl": "https://github.com/openai/skills/tree/main/skills/.curated/playwright",
-      "whyHere": "Kept because OpenAI's Browser Automation skill is current, high-signal, and fits the library well for review, QA, and product-quality work.",
+      "whyHere": "Useful when a task needs real browser work, not guessed output.",
       "vendored": false,
       "installSource": "openai/skills/skills/.curated/playwright",
       "tier": "upstream",
@@ -801,7 +801,7 @@
       "trust": "listed",
       "syncMode": "live",
       "sourceUrl": "https://github.com/openai/skills/tree/main/skills/.curated/linear",
-      "whyHere": "Kept because it gives the workflow shelf a real project-management endpoint instead of only prompting advice, and Linear is a tool I actually reach for.",
+      "whyHere": "I actually use Linear, so the workflow shelf should reflect that.",
       "addedDate": "2026-03-21",
       "tier": "upstream",
       "distribution": "live",
@@ -827,7 +827,7 @@
       "trust": "listed",
       "syncMode": "live",
       "sourceUrl": "https://github.com/openai/skills/tree/main/skills/.curated/frontend-skill",
-      "whyHere": "Kept because OpenAI's frontend taste is distinct from Anthropic's interface-craft guidance; together they make the frontend shelf feel like a real set instead of one repo repeated.",
+      "whyHere": "Brings a different frontend taste than Anthropic's. The shelf is better with both.",
       "addedDate": "2026-03-21",
       "tier": "upstream",
       "distribution": "live",
@@ -837,7 +837,7 @@
     },
     {
       "name": "shadcn",
-      "description": "Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for \"shadcn init\", \"create an app with --preset\", or \"switch to --preset\".",
+      "description": "Manages shadcn components and projects, including adding, searching, fixing, debugging, styling, and composing UI. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for \"shadcn init\", \"create an app with --preset\", or \"switch to --preset\".",
       "category": "development",
       "workArea": "frontend",
       "branch": "Components",
@@ -853,7 +853,7 @@
       "trust": "listed",
       "syncMode": "live",
       "sourceUrl": "https://github.com/shadcn-ui/ui/tree/main/skills/shadcn",
-      "whyHere": "Kept because shadcn/ui is a real part of modern frontend work, and this skill gives the shelf practical component-system leverage instead of only visual theory.",
+      "whyHere": "shadcn/ui is common enough that the shelf should have a dedicated skill.",
       "addedDate": "2026-03-21",
       "tier": "upstream",
       "distribution": "live",
@@ -879,7 +879,7 @@
       "trust": "listed",
       "syncMode": "live",
       "sourceUrl": "https://github.com/emilkowalski/skill/tree/main/skills/emil-design-eng",
-      "whyHere": "Kept because Emil's sensibility sharpens polish, spacing, motion, and restraint in a way the rest of the shelf does not.",
+      "whyHere": "Sharpens polish, spacing, motion, and restraint in a way nothing else here quite does.",
       "addedDate": "2026-03-21",
       "tier": "upstream",
       "distribution": "live",
@@ -907,7 +907,7 @@
       "trust": "listed",
       "syncMode": "live",
       "sourceUrl": "https://github.com/openai/skills/tree/main/skills/.curated/security-best-practices",
-      "whyHere": "Kept because the backend shelf needed an explicit security lens, not just architecture and data-modeling guidance.",
+      "whyHere": "Backend work needs a real security lens.",
       "notes": "",
       "labels": [],
       "addedDate": "2026-03-21",
@@ -933,7 +933,7 @@
       "trust": "listed",
       "syncMode": "live",
       "sourceUrl": "https://github.com/openai/skills/tree/main/skills/.curated/notion-spec-to-implementation",
-      "whyHere": "Kept because the workflow shelf should include a real spec-to-plan bridge, not just ticketing and prompting.",
+      "whyHere": "A useful bridge between a written spec and actual work.",
       "notes": "",
       "labels": [],
       "addedDate": "2026-03-21",
@@ -994,7 +994,7 @@
       "trust": "reviewed",
       "syncMode": "live",
       "sourceUrl": "https://github.com/twostraws/SwiftUI-Agent-Skill/tree/main/swiftui-pro",
-      "whyHere": "Curated because the SwiftUI branch needs concrete build and refactor guidance from installable upstream skills, not just a list of links.",
+      "whyHere": "A solid anchor for day-to-day SwiftUI work.",
       "lastVerified": "",
       "notes": "Curated via twostraws/Swift-Agent-Skills.",
       "labels": [
@@ -1033,7 +1033,7 @@
       "trust": "reviewed",
       "syncMode": "live",
       "sourceUrl": "https://github.com/Dimillian/Skills/tree/main/swiftui-ui-patterns",
-      "whyHere": "Curated because the SwiftUI branch needs concrete build and refactor guidance from installable upstream skills, not just a list of links.",
+      "whyHere": "Good component and layout patterns for SwiftUI screens.",
       "lastVerified": "",
       "notes": "Curated via twostraws/Swift-Agent-Skills.",
       "labels": [
@@ -1072,7 +1072,7 @@
       "trust": "reviewed",
       "syncMode": "live",
       "sourceUrl": "https://github.com/arjitj2/swiftui-design-principles",
-      "whyHere": "Curated because the SwiftUI branch needs concrete build and refactor guidance from installable upstream skills, not just a list of links.",
+      "whyHere": "Useful when the problem is taste, structure, or visual judgment.",
       "lastVerified": "",
       "notes": "Curated via twostraws/Swift-Agent-Skills.",
       "labels": [
@@ -1111,7 +1111,7 @@
       "trust": "reviewed",
       "syncMode": "live",
       "sourceUrl": "https://github.com/Dimillian/Skills/tree/main/swiftui-view-refactor",
-      "whyHere": "Curated because the SwiftUI branch needs concrete build and refactor guidance from installable upstream skills, not just a list of links.",
+      "whyHere": "Useful when a SwiftUI file has grown past the point of comfort.",
       "lastVerified": "",
       "notes": "Curated via twostraws/Swift-Agent-Skills.",
       "labels": [
@@ -1150,7 +1150,7 @@
       "trust": "reviewed",
       "syncMode": "live",
       "sourceUrl": "https://github.com/twostraws/SwiftData-Agent-Skill/tree/main/swiftdata-pro",
-      "whyHere": "Curated because SwiftData work benefits from specialist skills that stay upstream and keep pace with Apple framework changes.",
+      "whyHere": "Keeps SwiftData coverage current without freezing it in this repo.",
       "lastVerified": "",
       "notes": "Curated via twostraws/Swift-Agent-Skills.",
       "labels": [
@@ -1189,7 +1189,7 @@
       "trust": "reviewed",
       "syncMode": "live",
       "sourceUrl": "https://github.com/vanab/swiftdata-agent-skill/tree/main/swiftdata-expert-skill",
-      "whyHere": "Curated because SwiftData work benefits from specialist skills that stay upstream and keep pace with Apple framework changes.",
+      "whyHere": "A second strong SwiftData voice from upstream.",
       "lastVerified": "",
       "notes": "Curated via twostraws/Swift-Agent-Skills.",
       "labels": [
@@ -1228,7 +1228,7 @@
       "trust": "reviewed",
       "syncMode": "live",
       "sourceUrl": "https://github.com/twostraws/Swift-Concurrency-Agent-Skill/tree/main/swift-concurrency-pro",
-      "whyHere": "Curated because concurrency is one of the sharpest failure modes in modern Swift, and this branch needs real review and remediation skills.",
+      "whyHere": "Concurrency bugs are sharp in Swift. The shelf needs specialists here.",
       "lastVerified": "",
       "notes": "Curated via twostraws/Swift-Agent-Skills.",
       "labels": [
@@ -1267,7 +1267,7 @@
       "trust": "reviewed",
       "syncMode": "live",
       "sourceUrl": "https://github.com/Dimillian/Skills/tree/main/swift-concurrency-expert",
-      "whyHere": "Curated because concurrency is one of the sharpest failure modes in modern Swift, and this branch needs real review and remediation skills.",
+      "whyHere": "Another strong pass on Swift concurrency, with a different angle than the others.",
       "lastVerified": "",
       "notes": "Curated via twostraws/Swift-Agent-Skills.",
       "labels": [
@@ -1306,7 +1306,7 @@
       "trust": "reviewed",
       "syncMode": "live",
       "sourceUrl": "https://github.com/AvdLee/Swift-Concurrency-Agent-Skill/tree/main/swift-concurrency",
-      "whyHere": "Curated because concurrency is one of the sharpest failure modes in modern Swift, and this branch needs real review and remediation skills.",
+      "whyHere": "Worth keeping for AvdLee's take on Swift concurrency review and cleanup.",
       "lastVerified": "",
       "notes": "Curated via twostraws/Swift-Agent-Skills.",
       "labels": [
@@ -1345,7 +1345,7 @@
       "trust": "reviewed",
       "syncMode": "live",
       "sourceUrl": "https://github.com/twostraws/Swift-Testing-Agent-Skill/tree/main/swift-testing-pro",
-      "whyHere": "Curated because Swift testing work needs installable specialists for migration, review, and execution, not another reading list.",
+      "whyHere": "Swift testing deserves its own specialists.",
       "lastVerified": "",
       "notes": "Curated via twostraws/Swift-Agent-Skills.",
       "labels": [
@@ -1384,7 +1384,7 @@
       "trust": "reviewed",
       "syncMode": "live",
       "sourceUrl": "https://github.com/bocato/swift-testing-agent-skill/tree/main/swift-testing",
-      "whyHere": "Curated because Swift testing work needs installable specialists for migration, review, and execution, not another reading list.",
+      "whyHere": "Useful when the work is test migration, setup, or everyday test cleanup.",
       "lastVerified": "",
       "notes": "Curated via twostraws/Swift-Agent-Skills.",
       "labels": [
@@ -1423,7 +1423,7 @@
       "trust": "reviewed",
       "syncMode": "live",
       "sourceUrl": "https://github.com/AvdLee/Swift-Testing-Agent-Skill/tree/main/swift-testing-expert",
-      "whyHere": "Curated because Swift testing work needs installable specialists for migration, review, and execution, not another reading list.",
+      "whyHere": "Adds a second strong testing voice for Swift codebases.",
       "lastVerified": "",
       "notes": "Curated via twostraws/Swift-Agent-Skills.",
       "labels": [
@@ -1463,7 +1463,7 @@
       "trust": "reviewed",
       "syncMode": "live",
       "sourceUrl": "https://github.com/Erikote04/Swift-API-Design-Guidelines-Agent-Skill/tree/main/swift-api-design-guidelines-skill",
-      "whyHere": "Curated because API and language discipline shape the whole Swift codebase, so the mobile shelf should expose a real skill here.",
+      "whyHere": "API design leaks across a whole Swift codebase. This earns a place.",
       "lastVerified": "",
       "notes": "Curated via twostraws/Swift-Agent-Skills.",
       "labels": [
@@ -1502,7 +1502,7 @@
       "trust": "reviewed",
       "syncMode": "live",
       "sourceUrl": "https://github.com/dadederk/iOS-Accessibility-Agent-Skill/tree/main/ios-accessibility",
-      "whyHere": "Curated because accessibility deserves first-class mobile coverage with concrete Apple-platform audits and remediation guidance.",
+      "whyHere": "Mobile needed real accessibility coverage.",
       "lastVerified": "",
       "notes": "Curated via twostraws/Swift-Agent-Skills.",
       "labels": [
@@ -1516,7 +1516,7 @@
     },
     {
       "name": "swift-accessibility-skill",
-      "description": "Apply platform accessibility best practices to SwiftUI, UIKit, and AppKit code. Essential companion to any SwiftUI, UIKit, or AppKit skill — always use together. Use whenever writing, editing, or reviewing ANY SwiftUI views, UIKit view controllers, AppKit views/window controllers, or platform UI — even when the user doesn't mention accessibility. Also use when the user mentions VoiceOver, Voice Control, Dynamic Type, Reduce Motion, screen reader, a11y, WCAG, accessibility audit, Nutrition Labels, accessibilityLabel, UIAccessibility, NSAccessibility, assistive technologies, or Switch Control. Not for server-side Swift, non-UI packages, or CLI tools.",
+      "description": "Apply platform accessibility best practices to SwiftUI, UIKit, and AppKit code. Use it alongside any SwiftUI, UIKit, or AppKit skill. Use it whenever writing, editing, or reviewing platform UI, even when the user does not mention accessibility. Also use it when the user mentions VoiceOver, Voice Control, Dynamic Type, Reduce Motion, screen readers, a11y, WCAG, accessibility audits, accessibilityLabel, UIAccessibility, NSAccessibility, assistive technologies, or Switch Control. Not for server-side Swift, non-UI packages, or CLI tools.",
       "category": "development",
       "workArea": "mobile",
       "branch": "Swift / Accessibility",
@@ -1541,7 +1541,7 @@
       "trust": "reviewed",
       "syncMode": "live",
       "sourceUrl": "https://github.com/PasqualeVittoriosi/swift-accessibility-skill/tree/main/swift-accessibility-skill",
-      "whyHere": "Curated because accessibility deserves first-class mobile coverage with concrete Apple-platform audits and remediation guidance.",
+      "whyHere": "Keeps accessibility work visible when the code is Swift-first.",
       "lastVerified": "",
       "notes": "Curated via twostraws/Swift-Agent-Skills.",
       "labels": [
@@ -1580,7 +1580,7 @@
       "trust": "reviewed",
       "syncMode": "live",
       "sourceUrl": "https://github.com/rgmez/apple-accessibility-skills/tree/main/skills/appkit-accessibility-auditor",
-      "whyHere": "Curated because accessibility deserves first-class mobile coverage with concrete Apple-platform audits and remediation guidance.",
+      "whyHere": "AppKit needs its own accessibility pass.",
       "lastVerified": "",
       "notes": "Curated via twostraws/Swift-Agent-Skills.",
       "labels": [
@@ -1619,7 +1619,7 @@
       "trust": "reviewed",
       "syncMode": "live",
       "sourceUrl": "https://github.com/rgmez/apple-accessibility-skills/tree/main/skills/swiftui-accessibility-auditor",
-      "whyHere": "Curated because accessibility deserves first-class mobile coverage with concrete Apple-platform audits and remediation guidance.",
+      "whyHere": "SwiftUI needs its own accessibility pass.",
       "lastVerified": "",
       "notes": "Curated via twostraws/Swift-Agent-Skills.",
       "labels": [
@@ -1658,7 +1658,7 @@
       "trust": "reviewed",
       "syncMode": "live",
       "sourceUrl": "https://github.com/rgmez/apple-accessibility-skills/tree/main/skills/uikit-accessibility-auditor",
-      "whyHere": "Curated because accessibility deserves first-class mobile coverage with concrete Apple-platform audits and remediation guidance.",
+      "whyHere": "UIKit needs its own accessibility pass.",
       "lastVerified": "",
       "notes": "Curated via twostraws/Swift-Agent-Skills.",
       "labels": [
@@ -1697,7 +1697,7 @@
       "trust": "reviewed",
       "syncMode": "live",
       "sourceUrl": "https://github.com/efremidze/swift-architecture-skill/tree/main/swift-architecture-skill",
-      "whyHere": "Curated because Swift architecture choices compound quickly, and this branch benefits from a dedicated upstream opinionated skill.",
+      "whyHere": "Architecture choices compound fast in Swift codebases. A dedicated skill helps.",
       "lastVerified": "",
       "notes": "Curated via twostraws/Swift-Agent-Skills.",
       "labels": [
@@ -1736,7 +1736,7 @@
       "trust": "reviewed",
       "syncMode": "live",
       "sourceUrl": "https://github.com/AvdLee/Core-Data-Agent-Skill/tree/main/core-data-expert",
-      "whyHere": "Curated because legacy Apple persistence still matters in real apps, and the mobile shelf needs a direct Core Data specialist.",
+      "whyHere": "Core Data still shows up often enough to keep a specialist.",
       "lastVerified": "",
       "notes": "Curated via twostraws/Swift-Agent-Skills.",
       "labels": [
@@ -1776,7 +1776,7 @@
       "trust": "reviewed",
       "syncMode": "live",
       "sourceUrl": "https://github.com/Dimillian/Skills/tree/main/swiftui-performance-audit",
-      "whyHere": "Curated because SwiftUI performance problems are subtle, and this branch needs a focused audit skill with real implementation guidance.",
+      "whyHere": "SwiftUI performance needs its own audit skill.",
       "lastVerified": "",
       "notes": "Curated via twostraws/Swift-Agent-Skills.",
       "labels": [
@@ -1815,7 +1815,7 @@
       "trust": "reviewed",
       "syncMode": "live",
       "sourceUrl": "https://github.com/ivan-magda/swift-security-skill/tree/main/swift-security-expert",
-      "whyHere": "Curated because security work should be native to the mobile shelf, with a real Swift-focused specialist instead of generic advice.",
+      "whyHere": "The mobile shelf should have a Swift-specific security voice.",
       "lastVerified": "",
       "notes": "Curated via twostraws/Swift-Agent-Skills.",
       "labels": [
@@ -1854,7 +1854,7 @@
       "trust": "reviewed",
       "syncMode": "live",
       "sourceUrl": "https://github.com/conorluddy/ios-simulator-skill/tree/main/ios-simulator-skill",
-      "whyHere": "Curated because practical simulator and device workflows belong in the mobile shelf when agents need to operate Swift apps end to end.",
+      "whyHere": "Agents working on Swift apps need simulator workflows.",
       "lastVerified": "",
       "notes": "Curated via twostraws/Swift-Agent-Skills.",
       "labels": [
@@ -1868,7 +1868,7 @@
     },
     {
       "name": "writing-for-interfaces",
-      "description": "Use when someone asks to write, rewrite, review, or improve text that appears inside a product or interface. Examples: \"review the UX copy\", \"is there a better way to phrase this\", \"rewrite this error message\", \"write copy for this screen/flow/page\", reviewing button labels, improving CLI output messages, writing onboarding copy, settings descriptions, or confirmation dialogs. Trigger whenever the request involves wording shown to end users inside software — apps, web, CLI, email notifications, modals, tooltips, empty states, or alerts. Also trigger for vague requests like \"review the UX\" where interface copy review is implied. Do NOT trigger for content marketing, blog posts, app store listings, API docs, brand guides, cover letters, or interview questions — this is a technical writing skill for interface language.",
+      "description": "Use when someone asks to write, rewrite, review, or improve text that appears inside a product or interface. Examples: \"review the UX copy\", \"is there a better way to phrase this\", \"rewrite this error message\", \"write copy for this screen/flow/page\", reviewing button labels, improving CLI output messages, writing onboarding copy, settings descriptions, or confirmation dialogs. Trigger whenever the request involves wording shown to end users inside software, including apps, web, CLI, email notifications, modals, tooltips, empty states, or alerts. Also trigger for vague requests like \"review the UX\" when interface copy review is implied. Do not trigger for content marketing, blog posts, app store listings, API docs, brand guides, cover letters, or interview questions. This skill is for interface language.",
       "category": "document",
       "workArea": "mobile",
       "branch": "Swift / User Interface",
@@ -1894,7 +1894,7 @@
       "trust": "reviewed",
       "syncMode": "live",
       "sourceUrl": "https://github.com/andrewgleave/skills/tree/main/writing-for-interfaces",
-      "whyHere": "Curated because interface writing is part of product craft on Apple platforms, and the mobile shelf should include that discipline too.",
+      "whyHere": "Interface writing belongs next to UI work, not in a distant docs shelf.",
       "lastVerified": "",
       "notes": "Curated via twostraws/Swift-Agent-Skills.",
       "labels": [

package/tui/index.mjs

@@ -105,8 +105,8 @@ const SOURCE_NOTES = {
 
 const CREATOR_HANDLE = '@moizibnyousaf';
 const LIBRARY_SIGNATURE = "Moiz's Curated Agent Skills Library";
-const LIBRARY_THESIS = 'Shelves, not search results.';
-const LIBRARY_SUPPORT = 'Small enough to scan. Opinionated enough to trust.';
+const LIBRARY_THESIS = 'Start with a shelf.';
+const LIBRARY_SUPPORT = 'A smaller library, kept by hand.';
 
 function clamp(value, min, max) {
   return Math.max(min, Math.min(max, value));
@@ -1138,7 +1138,7 @@ function SkillScreen({skill, previewMode, scope, agent, columns, viewport = null
         title="Why it belongs"
         eyebrow="Editorial note"
         lines=${editorialLines}
-        footer="The first screen should explain why this earned a place on the shelf before it asks you to install anything."
+        footer="The first screen should tell you why a pick is here before it asks you to install it."
       />
       ${previewMode
         ? html`
@@ -1158,7 +1158,7 @@ function SkillScreen({skill, previewMode, scope, agent, columns, viewport = null
         title="Provenance"
         eyebrow="Shelf and source"
         lines=${provenanceLines}
-        footer="The library keeps placement and provenance visible so installs still feel trustworthy."
+        footer="Shelf placement and provenance stay visible here."
         variant="rail"
       />
       <${Inspector}
@@ -1193,7 +1193,7 @@ function SkillScreen({skill, previewMode, scope, agent, columns, viewport = null
                 'Use the open skills CLI to install this skill directly from its upstream repository.',
               ]}
               command=${skillsSpec.command}
-              footer="This path follows the external skills ecosystem instead of the vendored library copy."
+              footer="This path installs from the upstream repo."
               variant="rail"
             />
           `
@@ -1246,7 +1246,7 @@ function SkillScreen({skill, previewMode, scope, agent, columns, viewport = null
                       eyebrow="skills.sh"
                       lines=${['Use the open skills CLI to install this skill directly from its upstream repository.']}
                       command=${skillsSpec.command}
-                      footer="This path follows the external skills ecosystem instead of the vendored library copy."
+                      footer="This path follows the external skills ecosystem."
                     />
                   `
                 : null}
@@ -1254,7 +1254,7 @@ function SkillScreen({skill, previewMode, scope, agent, columns, viewport = null
                 title="Provenance"
                 eyebrow="Shelf and source"
                 lines=${provenanceLines}
-                footer="The library keeps placement and provenance visible on purpose."
+                footer="Shelf placement and provenance stay visible here."
               />
               <${Inspector}
                 title="Neighboring shelf picks"
@@ -2511,7 +2511,7 @@ function App({catalog: initialCatalog, scope, agent, onExit}) {
           breadcrumbs=${breadcrumbs}
           title=${rootMode === 'areas' ? LIBRARY_THESIS : 'Trusted publishers'}
           subtitle=${rootMode === 'areas'
-            ? 'Start with the work. Each shelf stays small enough to scan and opinionated enough to trust.'
+            ? 'Start with the work. Each shelf stays small enough to browse quickly.'
             : 'See where the picks come from and which lanes each publisher feeds into the library.'}
           metaItems=${[`${catalog.total} skills`, `${catalog.areas.length} shelves`, `${catalog.sources.length} sources`, activeTheme.label]}
           hint="Arrow keys move · Enter drills in · / searches · : command palette"
@@ -2913,7 +2913,7 @@ function App({catalog: initialCatalog, scope, agent, onExit}) {
       ${overlay?.type === 'repo-why'
         ? html`<${TextEntryOverlay}
             title="Why it belongs"
-            subtitle="The library only saves fully placed upstream picks."
+            subtitle="Only fully placed upstream picks get saved."
             value=${overlay.value}
             setValue=${(value) => setOverlay((currentOverlay) => ({...currentOverlay, value}))}
             viewport=${viewport}