ai-agent-skills 4.0.0 → 4.3.0
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.
- package/FOR_YOUR_AGENT.md +227 -0
- package/README.md +110 -35
- package/cli.js +3589 -309
- package/docs/workflows/add-an-upstream-skill.md +4 -4
- package/docs/workflows/make-a-house-copy.md +1 -1
- package/docs/workflows/start-a-library.md +41 -10
- package/lib/catalog-data.cjs +23 -2
- package/lib/catalog-mutations.cjs +4 -2
- package/lib/catalog-paths.cjs +35 -0
- package/lib/workspace-import.cjs +396 -0
- package/package.json +2 -1
- package/skills/ask-questions-if-underspecified/SKILL.md +1 -0
- package/skills/audit-library-health/SKILL.md +74 -0
- package/skills/backend-development/SKILL.md +1 -0
- package/skills/best-practices/SKILL.md +1 -0
- package/skills/browse-and-evaluate/SKILL.md +58 -0
- package/skills/build-workspace-docs/SKILL.md +52 -0
- package/skills/changelog-generator/SKILL.md +1 -0
- package/skills/code-documentation/SKILL.md +1 -0
- package/skills/content-research-writer/SKILL.md +1 -0
- package/skills/curate-a-team-library/SKILL.md +137 -0
- package/skills/database-design/SKILL.md +1 -0
- package/skills/install-from-remote-library/SKILL.md +67 -0
- package/skills/llm-application-dev/SKILL.md +1 -0
- package/skills/migrate-skills-between-libraries/SKILL.md +70 -0
- package/skills/review-a-skill/SKILL.md +67 -0
- package/skills/share-a-library/SKILL.md +64 -0
- package/skills/update-installed-skills/SKILL.md +57 -0
- package/skills.json +1701 -3
- package/tui/catalog.cjs +9 -5
- package/tui/index.mjs +59 -41
|
@@ -0,0 +1,227 @@
|
|
|
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
|
+
- If I already have a flat repo of local skills, run `npx ai-agent-skills init-library . --import` from that repo root instead of creating a new directory.
|
|
35
|
+
- Invalid private-only names such as colon or underscore variants should be skipped and reported, not allowed to kill the whole batch.
|
|
36
|
+
2. Move into that workspace and keep working there.
|
|
37
|
+
3. Ask me at most 3 short questions before acting:
|
|
38
|
+
- what kinds of work the library needs to support
|
|
39
|
+
- whether the first pass should stay small and opinionated or aim broader
|
|
40
|
+
- whether this should end as a local draft only or a shareable GitHub repo
|
|
41
|
+
4. Use these 5 work areas as the shelf system:
|
|
42
|
+
- `frontend` for web UI, browser work, design systems, visual polish
|
|
43
|
+
- `backend` for APIs, databases, security, infrastructure, runtime systems
|
|
44
|
+
- `mobile` for iOS, Android, React Native, Expo, device testing, app delivery
|
|
45
|
+
- `workflow` for docs, testing, release work, files, research, planning
|
|
46
|
+
- `agent-engineering` for prompts, evals, tools, orchestration, agent runtime design
|
|
47
|
+
5. Map the user's stack to shelves before adding anything.
|
|
48
|
+
- Example: "I build mobile apps with React Native and a Node backend" maps to `mobile` + `backend`.
|
|
49
|
+
- Add `workflow` only when testing, release, docs, or research are clearly part of the job.
|
|
50
|
+
- Add `agent-engineering` only when the user is building AI features, agents, prompts, evals, or toolchains.
|
|
51
|
+
- 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.
|
|
52
|
+
6. Run a discovery loop before curating:
|
|
53
|
+
- use `npx ai-agent-skills list --area <work-area>` to browse a shelf
|
|
54
|
+
- use `npx ai-agent-skills search <query>` when the user names a stack, tool, or capability
|
|
55
|
+
- use `npx ai-agent-skills collections` to inspect starter packs that may already exist
|
|
56
|
+
- keep machine-readable reads tight with `--fields name,tier,workArea`
|
|
57
|
+
- use `--limit 10` on larger result sets before asking for more
|
|
58
|
+
- if the user named multiple primary shelves, browse each of them before deciding what to add
|
|
59
|
+
7. Keep the first pass small, around 3 to 8 skills.
|
|
60
|
+
8. Choose the right mutation path:
|
|
61
|
+
- use `add` first for bundled picks and simple GitHub imports when the CLI can route it for you
|
|
62
|
+
- use `catalog` when you want an upstream entry without copying files into `skills/`
|
|
63
|
+
- use `vendor` only for true house copies you want to edit or own locally
|
|
64
|
+
9. Keep branch names consistent and useful.
|
|
65
|
+
- Examples: `React Native / UI`, `React Native / QA`, `Node / APIs`, `Node / Data`, `Docs / Release`
|
|
66
|
+
- Use branches to group related picks inside a shelf, not as free-form notes
|
|
67
|
+
10. Every mutation must include explicit curator metadata like `--area`, `--branch`, and `--why`.
|
|
68
|
+
11. Write `whyHere` notes as concrete curation reasoning, not placeholders.
|
|
69
|
+
- good: "Covers React Native testing so the mobile shelf has a real device-validation option."
|
|
70
|
+
- bad: "I want this on my shelf."
|
|
71
|
+
12. Use `--featured` sparingly.
|
|
72
|
+
- keep it to about 2 to 3 featured skills per shelf
|
|
73
|
+
- reserve it for skills you would tell a new teammate to install first
|
|
74
|
+
13. After the library has about 5 to 8 solid picks, create a `starter-pack` collection.
|
|
75
|
+
- add new entries with `--collection starter-pack`
|
|
76
|
+
- or use `npx ai-agent-skills curate <skill> --collection starter-pack` for existing entries
|
|
77
|
+
14. Sanity-check the library before finishing.
|
|
78
|
+
- run `npx ai-agent-skills list --area <work-area>` for each primary shelf you touched
|
|
79
|
+
- if you created `starter-pack`, run `npx ai-agent-skills collections` and confirm the install command looks right
|
|
80
|
+
15. Run `npx ai-agent-skills build-docs` before finishing.
|
|
81
|
+
16. If the user wants the library shared, turn it into a GitHub repo:
|
|
82
|
+
- `git init`
|
|
83
|
+
- `git add .`
|
|
84
|
+
- `git commit -m "Initialize skills library"`
|
|
85
|
+
- `gh repo create <owner>/<repo> --public --source=. --remote=origin --push`
|
|
86
|
+
17. End by telling me:
|
|
87
|
+
- what you added
|
|
88
|
+
- which shelves you used and why
|
|
89
|
+
- which skills are featured
|
|
90
|
+
- what the `starter-pack` includes, if you created one
|
|
91
|
+
- the shareable install command
|
|
92
|
+
- use `npx ai-agent-skills install <owner>/<repo> --collection starter-pack -p` when a starter pack exists
|
|
93
|
+
- otherwise use `npx ai-agent-skills install <owner>/<repo> -p`
|
|
94
|
+
```
|
|
95
|
+
|
|
96
|
+
## Curator Decision Framework
|
|
97
|
+
|
|
98
|
+
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.
|
|
99
|
+
|
|
100
|
+
### Shelf Mapping Rules
|
|
101
|
+
|
|
102
|
+
- `frontend`: web interfaces, design systems, browser automation, UI polish, app-shell UX.
|
|
103
|
+
- `backend`: APIs, auth, databases, data pipelines, infra, services, runtime behavior.
|
|
104
|
+
- `mobile`: React Native, Expo, SwiftUI, Kotlin, simulators, device QA, store delivery.
|
|
105
|
+
- `workflow`: testing, release work, docs, research, content ops, file transforms, planning.
|
|
106
|
+
- `agent-engineering`: prompts, evals, tool use, orchestration, memory, agent runtime patterns.
|
|
107
|
+
|
|
108
|
+
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.
|
|
109
|
+
|
|
110
|
+
The first pass should include at least one strong anchor skill for each primary shelf the user explicitly named.
|
|
111
|
+
|
|
112
|
+
### Discovery Loop
|
|
113
|
+
|
|
114
|
+
Before curating, inspect what already exists.
|
|
115
|
+
|
|
116
|
+
- Browse shelves with `npx ai-agent-skills list --area <work-area>`.
|
|
117
|
+
- Search by tools or capabilities with `npx ai-agent-skills search <query>`.
|
|
118
|
+
- Check `npx ai-agent-skills collections` when a ready-made pack may already cover part of the use case.
|
|
119
|
+
- In machine-readable flows, prefer `--fields name,tier,workArea` first so the response stays small.
|
|
120
|
+
- Add `--limit 10` when a shelf or search looks broad, then page further only if needed.
|
|
121
|
+
- If the user named multiple primary shelves, browse each one before you start curating.
|
|
122
|
+
|
|
123
|
+
Do not jump straight from `init-library` to a few guessed names unless the user already told you the exact skills they want.
|
|
124
|
+
|
|
125
|
+
### Add vs Catalog vs Vendor
|
|
126
|
+
|
|
127
|
+
- Use `add` as the default front door inside a workspace.
|
|
128
|
+
- Use `catalog` when the right move is "track this upstream skill in our library, but do not copy its files into `skills/`."
|
|
129
|
+
- Use `vendor` when the right move is "we want our own editable house copy in this library."
|
|
130
|
+
|
|
131
|
+
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.
|
|
132
|
+
|
|
133
|
+
### Branch Naming
|
|
134
|
+
|
|
135
|
+
Keep branch labels consistent so the shelves stay readable.
|
|
136
|
+
|
|
137
|
+
- Good: `React Native / UI`, `React Native / QA`, `Node / APIs`, `Node / Data`, `Docs / Release`
|
|
138
|
+
- Bad: `stuff`, `misc`, `my notes`
|
|
139
|
+
|
|
140
|
+
### Writing Good `whyHere` Notes
|
|
141
|
+
|
|
142
|
+
`whyHere` is curator judgment. It should explain why this skill belongs in this library, on this shelf, for this team.
|
|
143
|
+
|
|
144
|
+
- Mention the actual gap it fills.
|
|
145
|
+
- Mention the stack or workflow it supports.
|
|
146
|
+
- Be honest about why it is here instead of a nearby alternative.
|
|
147
|
+
- Never use placeholders like "I want this" or "looks useful."
|
|
148
|
+
|
|
149
|
+
### Featured Skills
|
|
150
|
+
|
|
151
|
+
Featured picks are the shelf anchors.
|
|
152
|
+
|
|
153
|
+
- Keep featured picks to about 2 to 3 per shelf.
|
|
154
|
+
- Feature the skills a new teammate should notice first.
|
|
155
|
+
- Do not feature everything.
|
|
156
|
+
|
|
157
|
+
### Collections
|
|
158
|
+
|
|
159
|
+
Once the library has a meaningful first pass, create a `starter-pack` collection.
|
|
160
|
+
|
|
161
|
+
- Put the first recommended 3 to 5 skills in it.
|
|
162
|
+
- Make it cross-shelf when that helps onboarding.
|
|
163
|
+
- Use `curate --collection starter-pack` to retrofit membership onto skills that are already in the catalog.
|
|
164
|
+
|
|
165
|
+
### Final Sanity Check
|
|
166
|
+
|
|
167
|
+
Before you hand the library back:
|
|
168
|
+
|
|
169
|
+
- Run `npx ai-agent-skills list --area <work-area>` for each primary shelf you touched.
|
|
170
|
+
- Run `npx ai-agent-skills collections` if you created `starter-pack`.
|
|
171
|
+
- Make sure the resulting library still reflects the user’s actual stack and does not over-index on one shelf.
|
|
172
|
+
|
|
173
|
+
### Sharing Step
|
|
174
|
+
|
|
175
|
+
A library is not really shared until it is in Git and has an install command you can hand to someone else.
|
|
176
|
+
|
|
177
|
+
After `build-docs`, if the user wants sharing:
|
|
178
|
+
|
|
179
|
+
```bash
|
|
180
|
+
git init
|
|
181
|
+
git add .
|
|
182
|
+
git commit -m "Initialize skills library"
|
|
183
|
+
gh repo create <owner>/<repo> --public --source=. --remote=origin --push
|
|
184
|
+
```
|
|
185
|
+
|
|
186
|
+
Then give them the actual install command to share, for example:
|
|
187
|
+
|
|
188
|
+
```bash
|
|
189
|
+
npx ai-agent-skills install <owner>/<repo> --collection starter-pack -p
|
|
190
|
+
```
|
|
191
|
+
|
|
192
|
+
If you did not create a `starter-pack` yet, share the whole library instead:
|
|
193
|
+
|
|
194
|
+
```bash
|
|
195
|
+
npx ai-agent-skills install <owner>/<repo> -p
|
|
196
|
+
```
|
|
197
|
+
|
|
198
|
+
## Direct Shell Fallback
|
|
199
|
+
|
|
200
|
+
```bash
|
|
201
|
+
npx ai-agent-skills init-library my-library
|
|
202
|
+
cd my-library
|
|
203
|
+
|
|
204
|
+
npx ai-agent-skills list --area mobile
|
|
205
|
+
npx ai-agent-skills search react-native
|
|
206
|
+
npx ai-agent-skills search testing
|
|
207
|
+
|
|
208
|
+
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."
|
|
209
|
+
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
|
|
210
|
+
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
|
|
211
|
+
|
|
212
|
+
npx ai-agent-skills build-docs
|
|
213
|
+
|
|
214
|
+
# Existing flat repo of skills
|
|
215
|
+
cd ~/projects/my-skills
|
|
216
|
+
npx ai-agent-skills init-library . --areas "mobile,workflow,agent-engineering" --import --auto-classify
|
|
217
|
+
npx ai-agent-skills list --area workflow
|
|
218
|
+
npx ai-agent-skills curate my-skill --area mobile --branch "Mobile / Imported" --why "Why it belongs."
|
|
219
|
+
|
|
220
|
+
git init
|
|
221
|
+
git add .
|
|
222
|
+
git commit -m "Initialize skills library"
|
|
223
|
+
gh repo create <owner>/my-library --public --source=. --remote=origin --push
|
|
224
|
+
|
|
225
|
+
# Share this with teammates:
|
|
226
|
+
npx ai-agent-skills install <owner>/my-library --collection starter-pack -p
|
|
227
|
+
```
|
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-
|
|
16
|
+
<a href="https://github.com/MoizIbnYousaf/Ai-Agent-Skills#shelves"><img alt="Library structure" src="https://img.shields.io/badge/library-110%20skills%20%C2%B7%206%20shelves-cba6f7?style=for-the-badge&labelColor=313244&logo=bookstack&logoColor=cdd6f4" /></a>
|
|
17
17
|
</p>
|
|
18
18
|
|
|
19
|
-
<p align="center"><sub>
|
|
19
|
+
<p align="center"><sub>17 house copies · 93 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`
|
|
32
|
+
`ai-agent-skills` does two things.
|
|
27
33
|
|
|
28
|
-
It ships my curated
|
|
29
|
-
It works with
|
|
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`
|
|
39
|
-
Use `ai-agent-skills` when you want a
|
|
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
|
-
## What's New in 4.
|
|
47
|
+
## What's New in 4.2.0
|
|
42
48
|
|
|
43
|
-
- Managed
|
|
44
|
-
-
|
|
45
|
-
-
|
|
46
|
-
- Dependency-aware installs
|
|
47
|
-
-
|
|
49
|
+
- Managed team libraries you can share over GitHub and install with `install <owner>/<repo>`
|
|
50
|
+
- Machine-readable CLI flows with `--format json`, `--fields`, pagination, and safer non-interactive output
|
|
51
|
+
- More authored workflow skills for curating, reviewing, syncing, and sharing libraries
|
|
52
|
+
- Dependency-aware installs, `sync` as the main refresh verb, and stronger installed-state visibility across the CLI and TUI
|
|
53
|
+
- A cleaner curator loop around shelves, provenance, trust, and shared starter packs
|
|
48
54
|
|
|
49
|
-
##
|
|
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.
|
|
59
|
+
Originally this repo was that installer. It still does that.
|
|
54
60
|
|
|
55
|
-
|
|
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
|
|
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
|
|
120
|
+
### Use the bundled library
|
|
74
121
|
|
|
75
122
|
```bash
|
|
76
123
|
# Open the terminal browser
|
|
@@ -82,16 +129,20 @@ 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
|
|
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
|
|
89
136
|
npx ai-agent-skills install --collection swift-agent-skills -p
|
|
90
137
|
|
|
138
|
+
# Install the mktg marketing pack
|
|
139
|
+
npx ai-agent-skills mktg
|
|
140
|
+
npx ai-agent-skills marketing-cli
|
|
141
|
+
|
|
91
142
|
# Install to the project shelf
|
|
92
143
|
npx ai-agent-skills install pdf -p
|
|
93
144
|
|
|
94
|
-
# Install all skills from an upstream repo
|
|
145
|
+
# Install all skills from an upstream repo to the default global targets
|
|
95
146
|
npx ai-agent-skills anthropics/skills
|
|
96
147
|
|
|
97
148
|
# Browse a repo before adding or installing from it
|
|
@@ -105,34 +156,51 @@ Default install targets:
|
|
|
105
156
|
|
|
106
157
|
Legacy agent-specific targets still work through `--agent <name>`.
|
|
107
158
|
|
|
108
|
-
### Start
|
|
159
|
+
### Start your own library
|
|
109
160
|
|
|
110
161
|
```bash
|
|
111
162
|
# Create a managed workspace
|
|
112
163
|
npx ai-agent-skills init-library my-library
|
|
113
164
|
cd my-library
|
|
114
165
|
|
|
115
|
-
# Add a bundled pick, refresh it, and rebuild the docs
|
|
166
|
+
# Add a bundled pick, install it, refresh it, and rebuild the docs
|
|
116
167
|
npx ai-agent-skills add frontend-design --area frontend --branch Implementation --why "I want this on my shelf."
|
|
168
|
+
npx ai-agent-skills install frontend-design -p
|
|
117
169
|
npx ai-agent-skills sync frontend-design -p
|
|
118
170
|
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
171
|
npx ai-agent-skills build-docs
|
|
172
|
+
|
|
173
|
+
# Or bootstrap an existing flat repo of skills in place
|
|
174
|
+
cd ~/projects/my-skills
|
|
175
|
+
npx ai-agent-skills init-library . --areas "mobile,workflow,agent-engineering" --import --auto-classify
|
|
176
|
+
npx ai-agent-skills browse
|
|
177
|
+
|
|
178
|
+
# Invalid private-only names are skipped and reported.
|
|
179
|
+
# Low-confidence imports fall back to workflow with a needs-curation label.
|
|
120
180
|
```
|
|
121
181
|
|
|
122
182
|
## Workspace Mode
|
|
123
183
|
|
|
124
|
-
Workspace mode is
|
|
184
|
+
Workspace mode is part of the normal flow now.
|
|
125
185
|
|
|
126
|
-
Start with a managed workspace,
|
|
186
|
+
Start with a managed workspace, add a few skills, then keep your shelves current with `add`, `catalog`, `vendor`, `sync`, and `build-docs`.
|
|
127
187
|
|
|
128
188
|
```bash
|
|
129
189
|
npx ai-agent-skills init-library my-library
|
|
130
190
|
cd my-library
|
|
131
191
|
|
|
132
192
|
npx ai-agent-skills add frontend-design --area frontend --branch Implementation --why "I want this on my shelf."
|
|
193
|
+
npx ai-agent-skills install frontend-design -p
|
|
133
194
|
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
195
|
npx ai-agent-skills sync frontend-design -p
|
|
135
196
|
npx ai-agent-skills build-docs
|
|
197
|
+
|
|
198
|
+
# Bulk import an existing library after bootstrap
|
|
199
|
+
npx ai-agent-skills import --auto-classify
|
|
200
|
+
|
|
201
|
+
# Review the fallback bucket and fix shelf placement
|
|
202
|
+
npx ai-agent-skills list --area workflow
|
|
203
|
+
npx ai-agent-skills curate some-skill --area mobile --branch "Mobile / Testing" --why "Why it belongs."
|
|
136
204
|
```
|
|
137
205
|
|
|
138
206
|
Workflow guides:
|
|
@@ -152,7 +220,7 @@ Most browsing starts in one of two places:
|
|
|
152
220
|
| 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
221
|
| Sources | The provenance view: see which publishers feed which shelves and branches. | `npx ai-agent-skills info frontend-design` |
|
|
154
222
|
|
|
155
|
-
The other views are still
|
|
223
|
+
The other views are still useful, just more situational:
|
|
156
224
|
|
|
157
225
|
- `npx ai-agent-skills browse` for the TUI
|
|
158
226
|
- `npx ai-agent-skills list --collection my-picks` for a cross-shelf starter stack
|
|
@@ -169,8 +237,9 @@ The shelves are the main structure.
|
|
|
169
237
|
| Frontend | 10 | Interfaces, design systems, browser work, and product polish. |
|
|
170
238
|
| Backend | 5 | Systems, data, security, and runtime operations. |
|
|
171
239
|
| Mobile | 24 | Swift, SwiftUI, iOS, and Apple-platform development, with room for future React Native branches. |
|
|
172
|
-
| Workflow |
|
|
173
|
-
| Agent Engineering |
|
|
240
|
+
| Workflow | 11 | Files, docs, planning, release work, and research-to-output flows. |
|
|
241
|
+
| Agent Engineering | 14 | MCP, skill-building, prompting discipline, and LLM application work. |
|
|
242
|
+
| Marketing | 46 | Brand, strategy, copy, distribution, creative, SEO, conversion, and growth work. |
|
|
174
243
|
<!-- GENERATED:shelf-table:end -->
|
|
175
244
|
|
|
176
245
|
The full map lives in [WORK_AREAS.md](./WORK_AREAS.md).
|
|
@@ -188,14 +257,15 @@ Collections are smaller sets. Useful, but secondary to the shelves.
|
|
|
188
257
|
| `build-systems` | Backend, architecture, MCP, and security work. | `mcp-builder`, `backend-development`, `database-design` |
|
|
189
258
|
| `test-and-debug` | QA, debugging, CI cleanup, and observability. | `playwright`, `webapp-testing`, `gh-fix-ci` |
|
|
190
259
|
| `docs-and-research` | Docs, files, research, and writing work. | `pdf`, `doc-coauthoring`, `docx` |
|
|
260
|
+
| `mktg` | The full upstream mktg marketing playbook. Install the whole set at once or pick from it. | `cmo`, `brand-voice`, `positioning-angles` |
|
|
191
261
|
<!-- GENERATED:collection-table:end -->
|
|
192
262
|
|
|
193
|
-
## Curating
|
|
263
|
+
## Curating the catalog
|
|
194
264
|
|
|
195
265
|
Use `catalog` when you want to add an upstream skill without vendoring it.
|
|
196
266
|
|
|
197
|
-
In a managed workspace, `add
|
|
198
|
-
`catalog` and `vendor`
|
|
267
|
+
In a managed workspace, start with `add`.
|
|
268
|
+
Use `catalog` and `vendor` when you want more control.
|
|
199
269
|
|
|
200
270
|
```bash
|
|
201
271
|
npx ai-agent-skills catalog openai/skills --list
|
|
@@ -213,7 +283,7 @@ It adds metadata and placement in the active library:
|
|
|
213
283
|
- why it earned a place
|
|
214
284
|
- how it should install later
|
|
215
285
|
|
|
216
|
-
For existing picks, `curate`
|
|
286
|
+
For existing picks, use `curate` for quick edits:
|
|
217
287
|
|
|
218
288
|
```bash
|
|
219
289
|
npx ai-agent-skills curate frontend-design --branch Implementation
|
|
@@ -237,13 +307,14 @@ Current upstream mix:
|
|
|
237
307
|
<!-- GENERATED:source-table:start -->
|
|
238
308
|
| Source repo | Skills |
|
|
239
309
|
| --- | --- |
|
|
310
|
+
| `MoizIbnYousaf/mktg` | 46 |
|
|
240
311
|
| `anthropics/skills` | 11 |
|
|
312
|
+
| `MoizIbnYousaf/Ai-Agent-Skills` | 11 |
|
|
241
313
|
| `openai/skills` | 9 |
|
|
242
314
|
| `Dimillian/Skills` | 4 |
|
|
243
315
|
| `wshobson/agents` | 4 |
|
|
244
316
|
| `rgmez/apple-accessibility-skills` | 3 |
|
|
245
317
|
| `ComposioHQ/awesome-claude-skills` | 2 |
|
|
246
|
-
| `MoizIbnYousaf/Ai-Agent-Skills` | 2 |
|
|
247
318
|
| `andrewgleave/skills` | 1 |
|
|
248
319
|
| `arjitj2/swiftui-design-principles` | 1 |
|
|
249
320
|
| `AvdLee/Core-Data-Agent-Skill` | 1 |
|
|
@@ -285,8 +356,11 @@ npx ai-agent-skills preview pdf
|
|
|
285
356
|
# Install
|
|
286
357
|
npx ai-agent-skills install <skill-name>
|
|
287
358
|
npx ai-agent-skills swift
|
|
359
|
+
npx ai-agent-skills mktg
|
|
360
|
+
npx ai-agent-skills marketing-cli
|
|
288
361
|
npx ai-agent-skills install <skill-name> -p
|
|
289
362
|
npx ai-agent-skills install --collection swift-agent-skills -p
|
|
363
|
+
npx ai-agent-skills install --collection mktg -p
|
|
290
364
|
npx ai-agent-skills <owner/repo>
|
|
291
365
|
npx ai-agent-skills install <owner/repo>
|
|
292
366
|
npx ai-agent-skills install <owner/repo>@<skill-name>
|
|
@@ -308,6 +382,7 @@ npx ai-agent-skills catalog <owner/repo> --skill <name> --area <shelf> --branch
|
|
|
308
382
|
npx ai-agent-skills curate <skill-name> --branch "<branch>"
|
|
309
383
|
npx ai-agent-skills curate review
|
|
310
384
|
npx ai-agent-skills vendor <repo-or-path> --skill <name> --area <shelf> --branch <branch> --why "<editorial note>"
|
|
385
|
+
npx ai-agent-skills import [path] --auto-classify
|
|
311
386
|
```
|
|
312
387
|
|
|
313
388
|
## Testing
|
|
@@ -317,7 +392,7 @@ npx ai-agent-skills vendor <repo-or-path> --skill <name> --area <shelf> --branch
|
|
|
317
392
|
- `npm run test:live`
|
|
318
393
|
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
394
|
- `npm run test:live:quick`
|
|
320
|
-
|
|
395
|
+
A smaller live matrix for faster iteration with the same no-mock pipeline.
|
|
321
396
|
|
|
322
397
|
## Legacy Agent Support
|
|
323
398
|
|
|
@@ -340,9 +415,9 @@ Still supported through `--agent <name>`:
|
|
|
340
415
|
|
|
341
416
|
- Small shelves
|
|
342
417
|
- Clear provenance
|
|
343
|
-
- Notes that explain
|
|
418
|
+
- Notes that explain why something stays
|
|
344
419
|
- Upstream repos staying upstream
|
|
345
|
-
- A library that looks
|
|
420
|
+
- A library that looks cared for
|
|
346
421
|
|
|
347
422
|
## Contributing
|
|
348
423
|
|