@uzysjung/agent-harness 26.87.0 → 26.88.1
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/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@uzysjung/agent-harness",
|
|
3
|
-
"version": "26.
|
|
3
|
+
"version": "26.88.1",
|
|
4
4
|
"description": "Curate vetted AI-coding skills & plugins by your tech stack — install only what you need, across Claude Code, Codex, OpenCode & Antigravity",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"publishConfig": {
|
|
@@ -10,7 +10,9 @@ description: >-
|
|
|
10
10
|
어떻게 해결했는지", "갭분석", "레퍼런스 서비스랑 비교해서 부족한 점 찾아줘" — or the
|
|
11
11
|
English equivalents: "gap analysis", "what are we missing vs the
|
|
12
12
|
ideal/north-star", "benchmark against reference services". Fires for both
|
|
13
|
-
Korean and English phrasing.
|
|
13
|
+
Korean and English phrasing. NOT for a whole-codebase multi-dimension audit
|
|
14
|
+
(use ultracode-service-audit) or single-artifact prose review (use
|
|
15
|
+
multi-persona-review) — this is the narrower gap-vs-benchmark loop.
|
|
14
16
|
---
|
|
15
17
|
|
|
16
18
|
# Gap Analysis E2E (reverse + competitive)
|
|
@@ -7,7 +7,9 @@ description: >-
|
|
|
7
7
|
페르소나를 여러명 만들어서 (손넷 모델정도로) 피드백 받아바", "다면 리뷰 해볼까", "페르소나로 리뷰",
|
|
8
8
|
"여러 관점으로 피드백", or in English "multi-persona review", "review this from different user
|
|
9
9
|
perspectives", "get persona feedback on this post/README/doc", "panel review this artifact".
|
|
10
|
-
Lighter than a full service audit — point it at ONE artifact, not a whole codebase.
|
|
10
|
+
Lighter than a full service audit — point it at ONE artifact, not a whole codebase. NOT for a
|
|
11
|
+
whole-codebase multi-dimension audit (use ultracode-service-audit) or a single-axis
|
|
12
|
+
gap-vs-benchmark loop (use gap-analysis-e2e).
|
|
11
13
|
---
|
|
12
14
|
|
|
13
15
|
# Multi-Persona Review (다면페르소나 워크플로우 리뷰)
|
|
@@ -10,6 +10,8 @@ description: >-
|
|
|
10
10
|
"다차원 서비스 감사", or in English "audit the whole service / full multi-dimensional service audit /
|
|
11
11
|
find code, UX, scalability, planning, security, and marketing problems and prioritize fixes".
|
|
12
12
|
The heavyweight superset audit — orchestrate it as a Workflow with fan-out finders and an adversarial verify pass.
|
|
13
|
+
NOT for a single-artifact prose/README review (use multi-persona-review) or a single-axis
|
|
14
|
+
gap-vs-benchmark loop (use gap-analysis-e2e) — those are the lighter siblings.
|
|
13
15
|
---
|
|
14
16
|
|
|
15
17
|
# Ultracode Service Audit
|