opencode-skills-collection 4.1.11 → 4.1.12
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/bundled-skills/.antigravity-install-manifest.json +5 -1
- package/bundled-skills/agent-reels/SKILL.md +15 -4
- package/bundled-skills/datacircle/SKILL.md +128 -0
- package/bundled-skills/qrx/SKILL.md +131 -0
- package/bundled-skills/qrx/references/prompt-guide.md +30 -0
- package/bundled-skills/qrx/references/rest-api.md +40 -0
- package/bundled-skills/reverse-engineer-anything/SKILL.md +239 -0
- package/bundled-skills/reverse-engineer-anything/references/android-applications.md +34 -0
- package/bundled-skills/reverse-engineer-anything/references/evidence-workflows.md +40 -0
- package/bundled-skills/reverse-engineer-anything/references/javascript-applications.md +70 -0
- package/bundled-skills/reverse-engineer-anything/references/native-and-artifacts.md +146 -0
- package/bundled-skills/reverse-engineer-anything/references/runtime-observation.md +28 -0
- package/bundled-skills/uxkin-research/SKILL.md +127 -0
- package/package.json +1 -1
- package/skills_index.json +124 -0
|
@@ -0,0 +1,127 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: uxkin-research
|
|
3
|
+
description: "Research how real products handle a screen, flow or visual style before designing it: search UXKIN's real iOS screens, user journeys and website design systems, compare several and report what they share."
|
|
4
|
+
category: frontend
|
|
5
|
+
risk: safe
|
|
6
|
+
source: https://github.com/uxkin/agent/tree/main/skills/uxkin-research
|
|
7
|
+
source_repo: uxkin/agent
|
|
8
|
+
source_type: official
|
|
9
|
+
date_added: "2026-10-09"
|
|
10
|
+
author: UXKIN
|
|
11
|
+
tags: [ui, ux, design, research, mcp, design-system]
|
|
12
|
+
tools: [claude, codex, cursor, copilot, gemini]
|
|
13
|
+
license: MIT
|
|
14
|
+
license_source: https://github.com/uxkin/agent/blob/main/LICENSE
|
|
15
|
+
---
|
|
16
|
+
|
|
17
|
+
# UXKIN research
|
|
18
|
+
|
|
19
|
+
When a design decision depends on how real products do it, look at
|
|
20
|
+
several real examples, compare them properly and report what they show,
|
|
21
|
+
before anyone writes code. This skill uses the UXKIN MCP tools:
|
|
22
|
+
|
|
23
|
+
- `find_ui_references`: real apps, screens, journeys and websites
|
|
24
|
+
- `get_journey`: every screen of one journey, in order
|
|
25
|
+
- `find_ui_materials`: colors with their roles, typography, components
|
|
26
|
+
and the DESIGN.md of real website design systems
|
|
27
|
+
- `list_collections` / `get_collection`: references the person saved on
|
|
28
|
+
UXKIN; when they mention their saved picks or a collection, start there
|
|
29
|
+
|
|
30
|
+
## When to Use
|
|
31
|
+
|
|
32
|
+
- Use when the person asks how other apps handle a screen or flow ("how do other apps do onboarding?").
|
|
33
|
+
- Use when they want UI inspiration or comparable apps before designing.
|
|
34
|
+
- Use when they need examples of a flow: onboarding, sign-up, checkout, paywall, cancellation, account deletion, empty states.
|
|
35
|
+
- Use when they need a real website design system to start from.
|
|
36
|
+
|
|
37
|
+
## If the tools aren't connected
|
|
38
|
+
|
|
39
|
+
Don't present examples from memory as if they were real research, and
|
|
40
|
+
don't describe screens you haven't seen. Answer from the project itself
|
|
41
|
+
and general principles, say clearly that it isn't based on real
|
|
42
|
+
references, and mention once, in one short sentence, that connecting
|
|
43
|
+
UXKIN (https://uxkin.com) lets you compare real apps and flows for this.
|
|
44
|
+
Don't repeat it.
|
|
45
|
+
|
|
46
|
+
If a search says the account needs a plan, tell the person once and
|
|
47
|
+
carry on without references.
|
|
48
|
+
|
|
49
|
+
## 1. Frame the question
|
|
50
|
+
|
|
51
|
+
Turn the request into one or two concrete questions, for example: "Where
|
|
52
|
+
do subscription apps put cancelling, and how many steps does it take?"
|
|
53
|
+
or "What does a dark fintech site use for surfaces and accents?". Note
|
|
54
|
+
the product type and platform, since they decide which examples are
|
|
55
|
+
relevant.
|
|
56
|
+
|
|
57
|
+
## 2. Search in plain words
|
|
58
|
+
|
|
59
|
+
Call `find_ui_references` with the product type, the screen or flow and,
|
|
60
|
+
if it matters, the platform: "meditation app onboarding", "delete
|
|
61
|
+
account", "empty state search results". Leave out filler such as
|
|
62
|
+
"screen", "design" or "UI".
|
|
63
|
+
|
|
64
|
+
Apps name flows in their own words, so try a second wording when results
|
|
65
|
+
are thin: "cancel subscription" and "manage subscription", "sign up" and
|
|
66
|
+
"create an account", "paywall" and "choose a plan".
|
|
67
|
+
|
|
68
|
+
For a visual style or a starting design system, call `find_ui_materials`
|
|
69
|
+
with the product type and mood: "developer tools dark", "wellness light
|
|
70
|
+
warm".
|
|
71
|
+
|
|
72
|
+
## 3. Open journeys, don't stop at thumbnails
|
|
73
|
+
|
|
74
|
+
For anything with more than one step, open 3 to 5 journey results with
|
|
75
|
+
`get_journey` and compare them end to end:
|
|
76
|
+
|
|
77
|
+
- **Start:** which screen leads into the flow, and what else lives there.
|
|
78
|
+
- **Steps:** how many, and what each one is for. Mark steps that only
|
|
79
|
+
persuade, upsell or survey.
|
|
80
|
+
- **End:** a confirmation, the home screen, the next task, a paywall.
|
|
81
|
+
- **Spread:** the shortest and longest versions, and what explains the
|
|
82
|
+
difference.
|
|
83
|
+
|
|
84
|
+
For design systems, compare color roles (background, surface, text,
|
|
85
|
+
accent), type and the components each one names.
|
|
86
|
+
|
|
87
|
+
## 4. Report
|
|
88
|
+
|
|
89
|
+
Keep it short and concrete:
|
|
90
|
+
|
|
91
|
+
1. What most of the examples do (the pattern), naming the apps or sites
|
|
92
|
+
and journeys so the person can look at them on uxkin.com.
|
|
93
|
+
2. Where they differ, and which option fits this product and why.
|
|
94
|
+
3. A recommendation, or two options with the trade-off.
|
|
95
|
+
|
|
96
|
+
Report only what you saw in the results. Don't guess at screens you
|
|
97
|
+
didn't open.
|
|
98
|
+
|
|
99
|
+
## Use patterns, not products
|
|
100
|
+
|
|
101
|
+
References guide decisions; they are not templates. Never copy another
|
|
102
|
+
product's branding, logos, illustrations or text. The product's own
|
|
103
|
+
requirements, accessibility and platform conventions always win over a
|
|
104
|
+
reference.
|
|
105
|
+
|
|
106
|
+
When the person moves on to building, follow the `no-ui-slop` skill if
|
|
107
|
+
it's installed.
|
|
108
|
+
|
|
109
|
+
## Examples
|
|
110
|
+
|
|
111
|
+
The person asks: "How do other meditation apps onboard new users?"
|
|
112
|
+
|
|
113
|
+
```text
|
|
114
|
+
1. Frame it: what starts the flow, how many steps, and what ends it?
|
|
115
|
+
2. find_ui_references("meditation app onboarding")
|
|
116
|
+
3. get_journey on 3 to 5 results; note the start, each step's purpose and the end.
|
|
117
|
+
4. Report the shared pattern, where the flows differ and one recommendation.
|
|
118
|
+
```
|
|
119
|
+
|
|
120
|
+
For a starting design system, call `find_ui_materials("wellness light warm")`, compare the named color roles, type and components, then say which one fits the product and why.
|
|
121
|
+
|
|
122
|
+
## Limitations
|
|
123
|
+
|
|
124
|
+
- Needs the UXKIN MCP tools connected. Without them the skill answers from the project and general principles, and says so.
|
|
125
|
+
- Real references depend on the UXKIN account; a plan-limited search returns no examples and the skill carries on without them.
|
|
126
|
+
- Covers iOS app screens, user journeys and website design systems. Other platforms may have no references.
|
|
127
|
+
- References inform decisions; they are not templates and never override the product's own requirements, accessibility or platform conventions.
|
package/package.json
CHANGED
package/skills_index.json
CHANGED
|
@@ -18916,6 +18916,36 @@
|
|
|
18916
18916
|
"license": "MIT",
|
|
18917
18917
|
"license_source": "https://github.com/zhaoxuya520/reverse-skill/blob/main/LICENSE"
|
|
18918
18918
|
},
|
|
18919
|
+
{
|
|
18920
|
+
"id": "datacircle",
|
|
18921
|
+
"path": "skills/datacircle",
|
|
18922
|
+
"category": "data",
|
|
18923
|
+
"name": "datacircle",
|
|
18924
|
+
"description": "Look up LinkedIn profiles by URL through Datacircle (Up2Data or HarvestAPI, no markup), over its hosted MCP server or REST API, with the user's yes before each paid call.",
|
|
18925
|
+
"risk": "critical",
|
|
18926
|
+
"source": "self",
|
|
18927
|
+
"date_added": "2026-10-10",
|
|
18928
|
+
"plugin": {
|
|
18929
|
+
"targets": {
|
|
18930
|
+
"codex": "supported",
|
|
18931
|
+
"claude": "supported"
|
|
18932
|
+
},
|
|
18933
|
+
"setup": {
|
|
18934
|
+
"type": "none",
|
|
18935
|
+
"summary": "",
|
|
18936
|
+
"docs": null
|
|
18937
|
+
},
|
|
18938
|
+
"reasons": []
|
|
18939
|
+
},
|
|
18940
|
+
"source_type": "self",
|
|
18941
|
+
"tags": [
|
|
18942
|
+
"b2b-data",
|
|
18943
|
+
"linkedin",
|
|
18944
|
+
"enrichment",
|
|
18945
|
+
"rest-api",
|
|
18946
|
+
"mcp"
|
|
18947
|
+
]
|
|
18948
|
+
},
|
|
18919
18949
|
{
|
|
18920
18950
|
"id": "datadog",
|
|
18921
18951
|
"path": "skills/datadog",
|
|
@@ -49937,6 +49967,40 @@
|
|
|
49937
49967
|
"license": "MIT",
|
|
49938
49968
|
"license_source": "https://github.com/amElnagdy/delegate-skills/blob/master/LICENSE"
|
|
49939
49969
|
},
|
|
49970
|
+
{
|
|
49971
|
+
"id": "qrx",
|
|
49972
|
+
"path": "skills/qrx",
|
|
49973
|
+
"category": "design",
|
|
49974
|
+
"name": "qrx",
|
|
49975
|
+
"description": "Make branded, print-ready art QR codes that always scan with QRX (qrx.codes). Use when a link needs a QR code that looks like artwork or matches a brand for print, packaging, signs, slides or event badges, and to list or re-point QRX codes. Not for plain QR codes the agent makes locally.",
|
|
49976
|
+
"risk": "critical",
|
|
49977
|
+
"source": "https://github.com/qrxcodes/qrx-mcp/tree/main/skills/qrx",
|
|
49978
|
+
"date_added": "2026-10-10",
|
|
49979
|
+
"plugin": {
|
|
49980
|
+
"targets": {
|
|
49981
|
+
"codex": "supported",
|
|
49982
|
+
"claude": "supported"
|
|
49983
|
+
},
|
|
49984
|
+
"setup": {
|
|
49985
|
+
"type": "none",
|
|
49986
|
+
"summary": "",
|
|
49987
|
+
"docs": null
|
|
49988
|
+
},
|
|
49989
|
+
"reasons": []
|
|
49990
|
+
},
|
|
49991
|
+
"source_type": "official",
|
|
49992
|
+
"source_repo": "qrxcodes/qrx-mcp",
|
|
49993
|
+
"license": "MIT",
|
|
49994
|
+
"license_source": "https://github.com/qrxcodes/qrx-mcp/blob/main/LICENSE",
|
|
49995
|
+
"tags": [
|
|
49996
|
+
"qr-code",
|
|
49997
|
+
"design",
|
|
49998
|
+
"branding",
|
|
49999
|
+
"mcp",
|
|
50000
|
+
"rest-api",
|
|
50001
|
+
"print"
|
|
50002
|
+
]
|
|
50003
|
+
},
|
|
49940
50004
|
{
|
|
49941
50005
|
"id": "quality-nonconformance",
|
|
49942
50006
|
"path": "skills/quality-nonconformance",
|
|
@@ -51829,6 +51893,32 @@
|
|
|
51829
51893
|
"reasons": []
|
|
51830
51894
|
}
|
|
51831
51895
|
},
|
|
51896
|
+
{
|
|
51897
|
+
"id": "reverse-engineer-anything",
|
|
51898
|
+
"path": "skills/reverse-engineer-anything",
|
|
51899
|
+
"category": "uncategorized",
|
|
51900
|
+
"name": "reverse-engineer-anything",
|
|
51901
|
+
"description": "Use REA to investigate shipped apps, binaries, packages, and runtimes; trace features with evidence, compare versions, or guide reconstruction. Skip ordinary source-code analysis.",
|
|
51902
|
+
"risk": "safe",
|
|
51903
|
+
"source": "https://github.com/morluto/rea/tree/main/skill-src/reverse-engineer-anything",
|
|
51904
|
+
"date_added": "2026-10-10",
|
|
51905
|
+
"plugin": {
|
|
51906
|
+
"targets": {
|
|
51907
|
+
"codex": "supported",
|
|
51908
|
+
"claude": "supported"
|
|
51909
|
+
},
|
|
51910
|
+
"setup": {
|
|
51911
|
+
"type": "none",
|
|
51912
|
+
"summary": "",
|
|
51913
|
+
"docs": null
|
|
51914
|
+
},
|
|
51915
|
+
"reasons": []
|
|
51916
|
+
},
|
|
51917
|
+
"source_type": "community",
|
|
51918
|
+
"source_repo": "morluto/rea",
|
|
51919
|
+
"license": "MIT",
|
|
51920
|
+
"license_source": "https://github.com/morluto/rea/blob/main/LICENSE"
|
|
51921
|
+
},
|
|
51832
51922
|
{
|
|
51833
51923
|
"id": "reverse-engineering",
|
|
51834
51924
|
"path": "skills/reverse-engineering",
|
|
@@ -63830,6 +63920,40 @@
|
|
|
63830
63920
|
"reasons": []
|
|
63831
63921
|
}
|
|
63832
63922
|
},
|
|
63923
|
+
{
|
|
63924
|
+
"id": "uxkin-research",
|
|
63925
|
+
"path": "skills/uxkin-research",
|
|
63926
|
+
"category": "frontend",
|
|
63927
|
+
"name": "uxkin-research",
|
|
63928
|
+
"description": "Research how real products handle a screen, flow or visual style before designing it: search UXKIN's real iOS screens, user journeys and website design systems, compare several and report what they share.",
|
|
63929
|
+
"risk": "safe",
|
|
63930
|
+
"source": "https://github.com/uxkin/agent/tree/main/skills/uxkin-research",
|
|
63931
|
+
"date_added": "2026-10-09",
|
|
63932
|
+
"plugin": {
|
|
63933
|
+
"targets": {
|
|
63934
|
+
"codex": "supported",
|
|
63935
|
+
"claude": "supported"
|
|
63936
|
+
},
|
|
63937
|
+
"setup": {
|
|
63938
|
+
"type": "none",
|
|
63939
|
+
"summary": "",
|
|
63940
|
+
"docs": null
|
|
63941
|
+
},
|
|
63942
|
+
"reasons": []
|
|
63943
|
+
},
|
|
63944
|
+
"source_type": "official",
|
|
63945
|
+
"source_repo": "uxkin/agent",
|
|
63946
|
+
"license": "MIT",
|
|
63947
|
+
"license_source": "https://github.com/uxkin/agent/blob/main/LICENSE",
|
|
63948
|
+
"tags": [
|
|
63949
|
+
"ui",
|
|
63950
|
+
"ux",
|
|
63951
|
+
"design",
|
|
63952
|
+
"research",
|
|
63953
|
+
"mcp",
|
|
63954
|
+
"design-system"
|
|
63955
|
+
]
|
|
63956
|
+
},
|
|
63833
63957
|
{
|
|
63834
63958
|
"id": "uxui-principles",
|
|
63835
63959
|
"path": "skills/uxui-principles",
|