ai-agent-skills 4.0.0 → 4.2.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -0,0 +1,219 @@
1
+ # For Your Agent
2
+
3
+ Use this when you want an agent to build and share a managed skills library for you, not just make a local folder of `SKILL.md` files.
4
+
5
+ For detailed workflow guidance, install the skill: `npx ai-agent-skills install curate-a-team-library`.
6
+
7
+ The companion workflow skills are:
8
+
9
+ - `npx ai-agent-skills install install-from-remote-library`
10
+ - `npx ai-agent-skills install curate-a-team-library`
11
+ - `npx ai-agent-skills install share-a-library`
12
+ - `npx ai-agent-skills install browse-and-evaluate`
13
+ - `npx ai-agent-skills install update-installed-skills`
14
+ - `npx ai-agent-skills install build-workspace-docs`
15
+ - `npx ai-agent-skills install review-a-skill`
16
+ - `npx ai-agent-skills install audit-library-health`
17
+ - `npx ai-agent-skills install migrate-skills-between-libraries`
18
+
19
+ ## Paste this into your agent
20
+
21
+ ```text
22
+ Set up a managed team skills library for me with `ai-agent-skills`.
23
+
24
+ Use this repo for reference if you need docs or examples:
25
+ https://github.com/MoizIbnYousaf/Ai-Agent-Skills
26
+ https://github.com/MoizIbnYousaf/Ai-Agent-Skills/blob/main/FOR_YOUR_AGENT.md
27
+
28
+ Use the CLI with `npx`. Do not ask me to open the repo or link you to anything else.
29
+ Do not hand-edit `skills.json`, `README.md`, or `WORK_AREAS.md` if the command already exists.
30
+
31
+ Follow this curator decision protocol:
32
+
33
+ 1. Create a new workspace with `npx ai-agent-skills init-library <name>`, unless I already gave you a library name.
34
+ 2. Move into that workspace and keep working there.
35
+ 3. Ask me at most 3 short questions before acting:
36
+ - what kinds of work the library needs to support
37
+ - whether the first pass should stay small and opinionated or aim broader
38
+ - whether this should end as a local draft only or a shareable GitHub repo
39
+ 4. Use these 5 work areas as the shelf system:
40
+ - `frontend` for web UI, browser work, design systems, visual polish
41
+ - `backend` for APIs, databases, security, infrastructure, runtime systems
42
+ - `mobile` for iOS, Android, React Native, Expo, device testing, app delivery
43
+ - `workflow` for docs, testing, release work, files, research, planning
44
+ - `agent-engineering` for prompts, evals, tools, orchestration, agent runtime design
45
+ 5. Map the user's stack to shelves before adding anything.
46
+ - Example: "I build mobile apps with React Native and a Node backend" maps to `mobile` + `backend`.
47
+ - Add `workflow` only when testing, release, docs, or research are clearly part of the job.
48
+ - Add `agent-engineering` only when the user is building AI features, agents, prompts, evals, or toolchains.
49
+ - Make sure the first pass covers every primary shelf the user explicitly named. Do not let `mobile` crowd out `backend` if they asked for both.
50
+ 6. Run a discovery loop before curating:
51
+ - use `npx ai-agent-skills list --area <work-area>` to browse a shelf
52
+ - use `npx ai-agent-skills search <query>` when the user names a stack, tool, or capability
53
+ - use `npx ai-agent-skills collections` to inspect starter packs that may already exist
54
+ - keep machine-readable reads tight with `--fields name,tier,workArea`
55
+ - use `--limit 10` on larger result sets before asking for more
56
+ - if the user named multiple primary shelves, browse each of them before deciding what to add
57
+ 7. Keep the first pass small, around 3 to 8 skills.
58
+ 8. Choose the right mutation path:
59
+ - use `add` first for bundled picks and simple GitHub imports when the CLI can route it for you
60
+ - use `catalog` when you want an upstream entry without copying files into `skills/`
61
+ - use `vendor` only for true house copies you want to edit or own locally
62
+ 9. Keep branch names consistent and useful.
63
+ - Examples: `React Native / UI`, `React Native / QA`, `Node / APIs`, `Node / Data`, `Docs / Release`
64
+ - Use branches to group related picks inside a shelf, not as free-form notes
65
+ 10. Every mutation must include explicit curator metadata like `--area`, `--branch`, and `--why`.
66
+ 11. Write `whyHere` notes as concrete curation reasoning, not placeholders.
67
+ - good: "Covers React Native testing so the mobile shelf has a real device-validation option."
68
+ - bad: "I want this on my shelf."
69
+ 12. Use `--featured` sparingly.
70
+ - keep it to about 2 to 3 featured skills per shelf
71
+ - reserve it for skills you would tell a new teammate to install first
72
+ 13. After the library has about 5 to 8 solid picks, create a `starter-pack` collection.
73
+ - add new entries with `--collection starter-pack`
74
+ - or use `npx ai-agent-skills curate <skill> --collection starter-pack` for existing entries
75
+ 14. Sanity-check the library before finishing.
76
+ - run `npx ai-agent-skills list --area <work-area>` for each primary shelf you touched
77
+ - if you created `starter-pack`, run `npx ai-agent-skills collections` and confirm the install command looks right
78
+ 15. Run `npx ai-agent-skills build-docs` before finishing.
79
+ 16. If the user wants the library shared, turn it into a GitHub repo:
80
+ - `git init`
81
+ - `git add .`
82
+ - `git commit -m "Initialize skills library"`
83
+ - `gh repo create <owner>/<repo> --public --source=. --remote=origin --push`
84
+ 17. End by telling me:
85
+ - what you added
86
+ - which shelves you used and why
87
+ - which skills are featured
88
+ - what the `starter-pack` includes, if you created one
89
+ - the shareable install command
90
+ - use `npx ai-agent-skills install <owner>/<repo> --collection starter-pack -p` when a starter pack exists
91
+ - otherwise use `npx ai-agent-skills install <owner>/<repo> -p`
92
+ ```
93
+
94
+ ## Curator Decision Framework
95
+
96
+ Start with the workspace, not manual file edits. The job is to produce a library that another person or agent can actually browse, trust, and install.
97
+
98
+ ### Shelf Mapping Rules
99
+
100
+ - `frontend`: web interfaces, design systems, browser automation, UI polish, app-shell UX.
101
+ - `backend`: APIs, auth, databases, data pipelines, infra, services, runtime behavior.
102
+ - `mobile`: React Native, Expo, SwiftUI, Kotlin, simulators, device QA, store delivery.
103
+ - `workflow`: testing, release work, docs, research, content ops, file transforms, planning.
104
+ - `agent-engineering`: prompts, evals, tool use, orchestration, memory, agent runtime patterns.
105
+
106
+ If a user gives a mixed stack, map it to more than one shelf. Do not force every skill into one branch. If the stack is "React Native + Node backend", the first shelves are `mobile` and `backend`, and you only pull in `workflow` or `agent-engineering` when the actual work justifies it.
107
+
108
+ The first pass should include at least one strong anchor skill for each primary shelf the user explicitly named.
109
+
110
+ ### Discovery Loop
111
+
112
+ Before curating, inspect what already exists.
113
+
114
+ - Browse shelves with `npx ai-agent-skills list --area <work-area>`.
115
+ - Search by tools or capabilities with `npx ai-agent-skills search <query>`.
116
+ - Check `npx ai-agent-skills collections` when a ready-made pack may already cover part of the use case.
117
+ - In machine-readable flows, prefer `--fields name,tier,workArea` first so the response stays small.
118
+ - Add `--limit 10` when a shelf or search looks broad, then page further only if needed.
119
+ - If the user named multiple primary shelves, browse each one before you start curating.
120
+
121
+ Do not jump straight from `init-library` to a few guessed names unless the user already told you the exact skills they want.
122
+
123
+ ### Add vs Catalog vs Vendor
124
+
125
+ - Use `add` as the default front door inside a workspace.
126
+ - Use `catalog` when the right move is "track this upstream skill in our library, but do not copy its files into `skills/`."
127
+ - Use `vendor` when the right move is "we want our own editable house copy in this library."
128
+
129
+ If the user wants a repo they can share across a team, prefer upstream catalog entries for third-party skills and reserve house copies for true internal ownership.
130
+
131
+ ### Branch Naming
132
+
133
+ Keep branch labels consistent so the shelves stay readable.
134
+
135
+ - Good: `React Native / UI`, `React Native / QA`, `Node / APIs`, `Node / Data`, `Docs / Release`
136
+ - Bad: `stuff`, `misc`, `my notes`
137
+
138
+ ### Writing Good `whyHere` Notes
139
+
140
+ `whyHere` is curator judgment. It should explain why this skill belongs in this library, on this shelf, for this team.
141
+
142
+ - Mention the actual gap it fills.
143
+ - Mention the stack or workflow it supports.
144
+ - Be honest about why it is here instead of a nearby alternative.
145
+ - Never use placeholders like "I want this" or "looks useful."
146
+
147
+ ### Featured Skills
148
+
149
+ Featured picks are the shelf anchors.
150
+
151
+ - Keep featured picks to about 2 to 3 per shelf.
152
+ - Feature the skills a new teammate should notice first.
153
+ - Do not feature everything.
154
+
155
+ ### Collections
156
+
157
+ Once the library has a meaningful first pass, create a `starter-pack` collection.
158
+
159
+ - Put the first recommended 3 to 5 skills in it.
160
+ - Make it cross-shelf when that helps onboarding.
161
+ - Use `curate --collection starter-pack` to retrofit membership onto skills that are already in the catalog.
162
+
163
+ ### Final Sanity Check
164
+
165
+ Before you hand the library back:
166
+
167
+ - Run `npx ai-agent-skills list --area <work-area>` for each primary shelf you touched.
168
+ - Run `npx ai-agent-skills collections` if you created `starter-pack`.
169
+ - Make sure the resulting library still reflects the user’s actual stack and does not over-index on one shelf.
170
+
171
+ ### Sharing Step
172
+
173
+ A library is not really shared until it is in Git and has an install command you can hand to someone else.
174
+
175
+ After `build-docs`, if the user wants sharing:
176
+
177
+ ```bash
178
+ git init
179
+ git add .
180
+ git commit -m "Initialize skills library"
181
+ gh repo create <owner>/<repo> --public --source=. --remote=origin --push
182
+ ```
183
+
184
+ Then give them the actual install command to share, for example:
185
+
186
+ ```bash
187
+ npx ai-agent-skills install <owner>/<repo> --collection starter-pack -p
188
+ ```
189
+
190
+ If you did not create a `starter-pack` yet, share the whole library instead:
191
+
192
+ ```bash
193
+ npx ai-agent-skills install <owner>/<repo> -p
194
+ ```
195
+
196
+ ## Direct Shell Fallback
197
+
198
+ ```bash
199
+ npx ai-agent-skills init-library my-library
200
+ cd my-library
201
+
202
+ npx ai-agent-skills list --area mobile
203
+ npx ai-agent-skills search react-native
204
+ npx ai-agent-skills search testing
205
+
206
+ npx ai-agent-skills add frontend-design --area frontend --branch Implementation --why "Anchors the frontend shelf with stronger UI craft and production-ready interface direction."
207
+ npx ai-agent-skills add anthropics/skills --skill webapp-testing --area workflow --branch Testing --why "Adds browser-level validation so the workflow shelf covers end-to-end checks." --collection starter-pack
208
+ npx ai-agent-skills catalog conorluddy/ios-simulator-skill --skill ios-simulator-skill --area mobile --branch "React Native / QA" --why "Gives the mobile shelf a concrete simulator workflow for app-level testing." --collection starter-pack --featured
209
+
210
+ npx ai-agent-skills build-docs
211
+
212
+ git init
213
+ git add .
214
+ git commit -m "Initialize skills library"
215
+ gh repo create <owner>/my-library --public --source=. --remote=origin --push
216
+
217
+ # Share this with teammates:
218
+ npx ai-agent-skills install <owner>/my-library --collection starter-pack -p
219
+ ```
package/README.md CHANGED
@@ -13,20 +13,26 @@
13
13
  <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>
14
14
  <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>
15
15
  <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>
16
- <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>
16
+ <a href="https://github.com/MoizIbnYousaf/Ai-Agent-Skills#shelves"><img alt="Library structure" src="https://img.shields.io/badge/library-64%20skills%20%C2%B7%205%20shelves-cba6f7?style=for-the-badge&labelColor=313244&logo=bookstack&logoColor=cdd6f4" /></a>
17
17
  </p>
18
18
 
19
- <p align="center"><sub>8 house copies · 47 cataloged upstream</sub></p>
19
+ <p align="center"><sub>17 house copies · 47 cataloged upstream</sub></p>
20
20
  <!-- GENERATED:library-stats:end -->
21
21
 
22
22
  <p align="center"><em>Picked, shelved, and maintained by hand.</em></p>
23
23
 
24
+ <p align="center">
25
+ <a href="./docs/workflows/start-a-library.md"><strong>Build your own library</strong></a>
26
+ ·
27
+ <a href="./FOR_YOUR_AGENT.md"><strong>For your agent</strong></a>
28
+ </p>
29
+
24
30
  ## Library
25
31
 
26
- `ai-agent-skills` now does two jobs.
32
+ `ai-agent-skills` does two things.
27
33
 
28
- It ships my curated bundled library, and it gives you the CLI and TUI to build a managed library of your own.
29
- It works with Claude Code, Codex, Cursor, and other SKILL.md-compatible agents.
34
+ It ships my curated library, and it gives you the CLI and TUI to build and manage your own.
35
+ It works with any Agent Skills-compatible agent.
30
36
 
31
37
  The bundled library is organized the way I work:
32
38
 
@@ -35,24 +41,24 @@ The bundled library is organized the way I work:
35
41
  - Keep provenance visible
36
42
  - Keep notes that explain why a skill is here
37
43
 
38
- Use `skills.sh` when you want the broad ecosystem.
39
- Use `ai-agent-skills` when you want a kept set, shelves, provenance, and a library you can manage yourself.
44
+ Use `skills.sh` for the broad ecosystem.
45
+ Use `ai-agent-skills` when you want a smaller library with shelves, provenance, and notes.
40
46
 
41
47
  ## What's New in 4.0.0
42
48
 
43
49
  - Managed library workspaces with `init-library`
44
50
  - `add <source>` for bringing bundled picks, upstream repo skills, or house copies into your own library
45
- - `sync [name]` as the main refresh command, with `update` kept as an alias
51
+ - `sync [name]` as the main refresh command; `update` stays as an alias
46
52
  - Dependency-aware installs with `requires` and `--no-deps`
47
- - Installed-state visibility across the CLI and the TUI
53
+ - Installed status in both the CLI and TUI
48
54
 
49
- ## Why Keep It
55
+ ## What It Is Now
50
56
 
51
57
  I launched this on December 17, 2025, before `skills.sh` existed and before the ecosystem had a clear default universal installer.
52
58
 
53
- Originally this repo was that installer. That part still matters.
59
+ Originally this repo was that installer. It still does that.
54
60
 
55
- I keep it because the library itself has become useful: shelves, provenance, and notes that make the curation legible.
61
+ What started as an installer is now a place to build and manage your own library of skills.
56
62
 
57
63
  ## How It Works
58
64
 
@@ -64,13 +70,54 @@ Each skill here is either a house copy or a cataloged upstream pick.
64
70
 
65
71
  - `Cataloged upstream`
66
72
  Metadata in `skills.json` with no local folder.
67
- These stay upstream and install live from the source repo when you ask for them.
73
+ These stay upstream and install from the source repo when you ask for them.
68
74
 
69
75
  Upstream work stays upstream. That keeps the library lean.
70
76
 
77
+ ## For Your Agent
78
+
79
+ Tell your agent to build you a library. Paste this, or just point it at this repo — the protocol below has everything it needs.
80
+
81
+ Full protocol with curator decision framework: [FOR_YOUR_AGENT.md](./FOR_YOUR_AGENT.md)
82
+
83
+ ### Paste this into your agent
84
+
85
+ ```text
86
+ Set up a managed team skills library for me with `ai-agent-skills`.
87
+
88
+ Read the full agent protocol here before starting:
89
+ https://raw.githubusercontent.com/MoizIbnYousaf/Ai-Agent-Skills/main/FOR_YOUR_AGENT.md
90
+
91
+ Use the CLI with `npx`. Do not hand-edit `skills.json`, `README.md`, or `WORK_AREAS.md` if the command already exists.
92
+
93
+ 1. Fetch and read FOR_YOUR_AGENT.md above — it has the full curator decision protocol.
94
+ 2. Create a workspace with `npx ai-agent-skills init-library <name>`.
95
+ 3. Ask me at most 3 short questions: what kinds of work, small or broad, local draft or shared repo.
96
+ 4. Map my stack to shelves: frontend, backend, mobile, workflow, agent-engineering.
97
+ 5. Run a discovery loop: `list --area <shelf>`, `search <query>`, `collections`.
98
+ 6. Add 3-8 skills with explicit `--area`, `--branch`, and `--why` on every mutation.
99
+ 7. Run `npx ai-agent-skills build-docs` before finishing.
100
+ 8. If I want it shared: `git init && git add . && git commit -m "Initialize skills library" && gh repo create`.
101
+ 9. Tell me what you added, which shelves, and the install command for teammates.
102
+ ```
103
+
104
+ The companion workflow skills (installed automatically when you use the library):
105
+
106
+ ```
107
+ npx ai-agent-skills install install-from-remote-library
108
+ npx ai-agent-skills install curate-a-team-library
109
+ npx ai-agent-skills install share-a-library
110
+ npx ai-agent-skills install browse-and-evaluate
111
+ npx ai-agent-skills install update-installed-skills
112
+ npx ai-agent-skills install build-workspace-docs
113
+ npx ai-agent-skills install review-a-skill
114
+ npx ai-agent-skills install audit-library-health
115
+ npx ai-agent-skills install migrate-skills-between-libraries
116
+ ```
117
+
71
118
  ## Quick Start
72
119
 
73
- ### Use The Bundled Library
120
+ ### Use the bundled library
74
121
 
75
122
  ```bash
76
123
  # Open the terminal browser
@@ -82,7 +129,7 @@ npx ai-agent-skills list
82
129
  # Install a skill from the library
83
130
  npx ai-agent-skills install frontend-design
84
131
 
85
- # Install the Swift hub straight to Claude + Codex
132
+ # Install the Swift hub to the default global targets
86
133
  npx ai-agent-skills swift
87
134
 
88
135
  # Install an entire curated pack
@@ -91,7 +138,7 @@ npx ai-agent-skills install --collection swift-agent-skills -p
91
138
  # Install to the project shelf
92
139
  npx ai-agent-skills install pdf -p
93
140
 
94
- # Install all skills from an upstream repo straight to Claude + Codex
141
+ # Install all skills from an upstream repo to the default global targets
95
142
  npx ai-agent-skills anthropics/skills
96
143
 
97
144
  # Browse a repo before adding or installing from it
@@ -105,15 +152,16 @@ Default install targets:
105
152
 
106
153
  Legacy agent-specific targets still work through `--agent <name>`.
107
154
 
108
- ### Start Your Own Library
155
+ ### Start your own library
109
156
 
110
157
  ```bash
111
158
  # Create a managed workspace
112
159
  npx ai-agent-skills init-library my-library
113
160
  cd my-library
114
161
 
115
- # Add a bundled pick, refresh it, and rebuild the docs
162
+ # Add a bundled pick, install it, refresh it, and rebuild the docs
116
163
  npx ai-agent-skills add frontend-design --area frontend --branch Implementation --why "I want this on my shelf."
164
+ npx ai-agent-skills install frontend-design -p
117
165
  npx ai-agent-skills sync frontend-design -p
118
166
  npx ai-agent-skills add anthropics/skills --skill webapp-testing --area workflow --branch Testing --why "I use this when I want browser-level checks in the workspace."
119
167
  npx ai-agent-skills build-docs
@@ -121,15 +169,16 @@ npx ai-agent-skills build-docs
121
169
 
122
170
  ## Workspace Mode
123
171
 
124
- Workspace mode is now part of the main product surface.
172
+ Workspace mode is part of the normal flow now.
125
173
 
126
- Start with a managed workspace, pull in a few skills, then keep your own shelves current with `add`, `catalog`, `vendor`, `sync`, and `build-docs`.
174
+ Start with a managed workspace, add a few skills, then keep your shelves current with `add`, `catalog`, `vendor`, `sync`, and `build-docs`.
127
175
 
128
176
  ```bash
129
177
  npx ai-agent-skills init-library my-library
130
178
  cd my-library
131
179
 
132
180
  npx ai-agent-skills add frontend-design --area frontend --branch Implementation --why "I want this on my shelf."
181
+ npx ai-agent-skills install frontend-design -p
133
182
  npx ai-agent-skills add anthropics/skills --skill webapp-testing --area workflow --branch Testing --why "I use this when I want browser-level checks in the workspace."
134
183
  npx ai-agent-skills sync frontend-design -p
135
184
  npx ai-agent-skills build-docs
@@ -152,7 +201,7 @@ Most browsing starts in one of two places:
152
201
  | 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` |
153
202
  | Sources | The provenance view: see which publishers feed which shelves and branches. | `npx ai-agent-skills info frontend-design` |
154
203
 
155
- The other views are still there. They are just secondary:
204
+ The other views are still useful, just more situational:
156
205
 
157
206
  - `npx ai-agent-skills browse` for the TUI
158
207
  - `npx ai-agent-skills list --collection my-picks` for a cross-shelf starter stack
@@ -169,8 +218,8 @@ The shelves are the main structure.
169
218
  | Frontend | 10 | Interfaces, design systems, browser work, and product polish. |
170
219
  | Backend | 5 | Systems, data, security, and runtime operations. |
171
220
  | Mobile | 24 | Swift, SwiftUI, iOS, and Apple-platform development, with room for future React Native branches. |
172
- | Workflow | 10 | Files, docs, planning, release work, and research-to-output flows. |
173
- | Agent Engineering | 6 | MCP, skill-building, prompting discipline, and LLM application work. |
221
+ | Workflow | 11 | Files, docs, planning, release work, and research-to-output flows. |
222
+ | Agent Engineering | 14 | MCP, skill-building, prompting discipline, and LLM application work. |
174
223
  <!-- GENERATED:shelf-table:end -->
175
224
 
176
225
  The full map lives in [WORK_AREAS.md](./WORK_AREAS.md).
@@ -190,12 +239,12 @@ Collections are smaller sets. Useful, but secondary to the shelves.
190
239
  | `docs-and-research` | Docs, files, research, and writing work. | `pdf`, `doc-coauthoring`, `docx` |
191
240
  <!-- GENERATED:collection-table:end -->
192
241
 
193
- ## Curating The Catalog
242
+ ## Curating the catalog
194
243
 
195
244
  Use `catalog` when you want to add an upstream skill without vendoring it.
196
245
 
197
- In a managed workspace, `add` is the simpler front door.
198
- `catalog` and `vendor` are still the explicit power-user verbs.
246
+ In a managed workspace, start with `add`.
247
+ Use `catalog` and `vendor` when you want more control.
199
248
 
200
249
  ```bash
201
250
  npx ai-agent-skills catalog openai/skills --list
@@ -213,7 +262,7 @@ It adds metadata and placement in the active library:
213
262
  - why it earned a place
214
263
  - how it should install later
215
264
 
216
- For existing picks, `curate` is the quick loop:
265
+ For existing picks, use `curate` for quick edits:
217
266
 
218
267
  ```bash
219
268
  npx ai-agent-skills curate frontend-design --branch Implementation
@@ -238,12 +287,12 @@ Current upstream mix:
238
287
  | Source repo | Skills |
239
288
  | --- | --- |
240
289
  | `anthropics/skills` | 11 |
290
+ | `MoizIbnYousaf/Ai-Agent-Skills` | 11 |
241
291
  | `openai/skills` | 9 |
242
292
  | `Dimillian/Skills` | 4 |
243
293
  | `wshobson/agents` | 4 |
244
294
  | `rgmez/apple-accessibility-skills` | 3 |
245
295
  | `ComposioHQ/awesome-claude-skills` | 2 |
246
- | `MoizIbnYousaf/Ai-Agent-Skills` | 2 |
247
296
  | `andrewgleave/skills` | 1 |
248
297
  | `arjitj2/swiftui-design-principles` | 1 |
249
298
  | `AvdLee/Core-Data-Agent-Skill` | 1 |
@@ -317,7 +366,7 @@ npx ai-agent-skills vendor <repo-or-path> --skill <name> --area <shelf> --branch
317
366
  - `npm run test:live`
318
367
  No-mock live verification. Clones the real upstream repos, captures raw `SKILL.md` frontmatter and file manifests, runs real install/sync/uninstall flows in isolated temp homes and projects, drives the TUI through a real PTY, and writes a report to `tmp/live-test-report.json`.
319
368
  - `npm run test:live:quick`
320
- Smaller live matrix for faster iteration while keeping the same no-mock pipeline.
369
+ A smaller live matrix for faster iteration with the same no-mock pipeline.
321
370
 
322
371
  ## Legacy Agent Support
323
372
 
@@ -340,9 +389,9 @@ Still supported through `--agent <name>`:
340
389
 
341
390
  - Small shelves
342
391
  - Clear provenance
343
- - Notes that explain the keep
392
+ - Notes that explain why something stays
344
393
  - Upstream repos staying upstream
345
- - A library that looks maintained
394
+ - A library that looks cared for
346
395
 
347
396
  ## Contributing
348
397