ai-ops-cli 0.2.6 → 1.0.1

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.
Files changed (62) hide show
  1. package/README.ko.md +170 -0
  2. package/README.md +109 -163
  3. package/data/context-layer/AGENTS.md +29 -0
  4. package/data/context-layer/CLAUDE.md +14 -0
  5. package/data/context-layer/GEMINI.md +14 -0
  6. package/data/context-layer/docs/agent/checks/impact-checklist.md +16 -0
  7. package/data/context-layer/docs/agent/checks/review-checklist.md +17 -0
  8. package/data/context-layer/docs/agent/maps/codebase-map.md +16 -0
  9. package/data/context-layer/docs/agent/rules/doc-update-rules.md +22 -0
  10. package/data/context-layer/docs/agent/rules/routing-rules.md +22 -0
  11. package/data/context-layer/docs/agent/rules/stop-rules.md +20 -0
  12. package/data/context-layer/docs/agent/workflow.md +25 -0
  13. package/data/context-layer/docs/business/business-rules.md +16 -0
  14. package/data/context-layer/docs/docs-status.md +14 -0
  15. package/data/packs/pack-registry.json +8 -0
  16. package/data/packs/spec-lifecycle/docs/specs/README.ko.md +26 -0
  17. package/data/packs/spec-lifecycle/docs/specs/README.md +26 -0
  18. package/data/packs/spec-lifecycle/docs/specs/baseline/.gitkeep +1 -0
  19. package/data/packs/spec-lifecycle/docs/specs/initial-build/.gitkeep +1 -0
  20. package/data/skills/README.ko.md +182 -0
  21. package/data/skills/README.md +27 -2
  22. package/data/skills/skill-registry.json +64 -16
  23. package/data/skills/task-skills/doc-impact-reviewer/SKILL.md +101 -0
  24. package/data/skills/task-skills/doc-impact-reviewer/agents/openai.yaml +6 -0
  25. package/data/skills/task-skills/spec-baseline-sync/SKILL.md +134 -0
  26. package/data/skills/task-skills/spec-baseline-sync/agents/openai.yaml +6 -0
  27. package/data/skills/task-skills/spec-baseline-sync/references/template.md +14 -0
  28. package/data/skills/task-skills/spec-product-01-idea-to-brief/SKILL.md +78 -0
  29. package/data/skills/task-skills/spec-product-01-idea-to-brief/agents/openai.yaml +6 -0
  30. package/data/skills/task-skills/spec-product-01-idea-to-brief/references/template.md +36 -0
  31. package/data/skills/task-skills/spec-product-02-brief-to-technical-context/SKILL.md +91 -0
  32. package/data/skills/task-skills/spec-product-02-brief-to-technical-context/agents/openai.yaml +6 -0
  33. package/data/skills/task-skills/spec-product-02-brief-to-technical-context/references/template.md +58 -0
  34. package/data/skills/task-skills/spec-product-03-brief-to-product-spec/SKILL.md +85 -0
  35. package/data/skills/task-skills/spec-product-03-brief-to-product-spec/agents/openai.yaml +6 -0
  36. package/data/skills/task-skills/spec-product-03-brief-to-product-spec/references/template.md +41 -0
  37. package/data/skills/task-skills/spec-product-04-product-spec-to-ui-spec/SKILL.md +93 -0
  38. package/data/skills/task-skills/spec-product-04-product-spec-to-ui-spec/agents/openai.yaml +6 -0
  39. package/data/skills/task-skills/spec-product-04-product-spec-to-ui-spec/references/stitch-prompt-template.md +41 -0
  40. package/data/skills/task-skills/spec-product-04-product-spec-to-ui-spec/references/ui-spec-template.md +39 -0
  41. package/data/skills/task-skills/spec-product-05-spec-to-work-packets/SKILL.md +157 -0
  42. package/data/skills/task-skills/spec-product-05-spec-to-work-packets/agents/openai.yaml +6 -0
  43. package/data/skills/task-skills/spec-product-05-spec-to-work-packets/references/stitch-html-review.md +25 -0
  44. package/data/skills/task-skills/spec-product-05-spec-to-work-packets/references/work-packet-template.md +67 -0
  45. package/data/skills/task-skills/spec-shared-glossary-sync/SKILL.md +102 -0
  46. package/data/skills/task-skills/spec-shared-glossary-sync/agents/openai.yaml +6 -0
  47. package/data/skills/task-skills/spec-shared-glossary-sync/references/checklist.md +36 -0
  48. package/data/skills/task-skills/spec-shared-glossary-sync/references/template.md +58 -0
  49. package/data/subagents/README.ko.md +47 -0
  50. package/data/subagents/README.md +47 -0
  51. package/data/subagents/security-gate/PROMPT.md +18 -0
  52. package/data/subagents/security-gate/claude.frontmatter.yaml +8 -0
  53. package/data/subagents/security-gate/codex.frontmatter.toml +6 -0
  54. package/data/subagents/security-gate/gemini.frontmatter.yaml +6 -0
  55. package/data/subagents/security-reviewer/PROMPT.md +17 -0
  56. package/data/subagents/security-reviewer/claude.frontmatter.yaml +9 -0
  57. package/data/subagents/security-reviewer/codex.frontmatter.toml +6 -0
  58. package/data/subagents/security-reviewer/gemini.frontmatter.yaml +6 -0
  59. package/data/subagents/subagent-registry.json +14 -0
  60. package/dist/bin/index.js +2101 -1712
  61. package/dist/bin/index.js.map +1 -1
  62. package/package.json +2 -2
@@ -0,0 +1,20 @@
1
+ ---
2
+ status: Active
3
+ layer: agent
4
+ owner: ai-ops
5
+ read_when:
6
+ - before_destructive_action
7
+ - before_external_side_effect
8
+ update_when:
9
+ - safety_policy_changes
10
+ ---
11
+ # Stop Rules
12
+
13
+ ## 멈추고 확인할 때
14
+
15
+ - 삭제, reset, 강제 overwrite처럼 복구가 어려운 작업이 필요한 경우
16
+ - credential, 개인 정보, 운영 데이터가 노출될 수 있는 경우
17
+ - 계획 문서와 실제 코드 구조가 충돌해 임의 판단이 위험한 경우
18
+ - 검증 실패 원인이 환경 문제인지 구현 문제인지 구분되지 않는 경우
19
+
20
+ 확인이 필요한 지점은 짧게 설명하고, 안전한 대안이 있으면 함께 제시한다.
@@ -0,0 +1,25 @@
1
+ ---
2
+ status: Active
3
+ layer: agent
4
+ owner: ai-ops
5
+ read_when:
6
+ - before_task
7
+ update_when:
8
+ - workflow_changes
9
+ ---
10
+ # Workflow
11
+
12
+ ## 기본 흐름
13
+
14
+ 1. 요청 범위와 현재 작업 디렉터리를 확인한다.
15
+ 2. 관련 문서의 `status`를 확인하고 `Active` 문서만 판단 근거로 사용한다.
16
+ 3. 코드 변경 전 현재 diff를 확인한다.
17
+ 4. 변경은 가능한 작은 단위로 적용한다.
18
+ 5. 변경 범위에 맞는 검증을 실행한다.
19
+ 6. 결과, 검증, 남은 리스크를 짧게 보고한다.
20
+
21
+ ## 보존 원칙
22
+
23
+ - 사용자 변경으로 보이는 diff는 되돌리지 않는다.
24
+ - project-owned 문서는 CLI update가 덮어쓰지 않는다.
25
+ - global skills와 subagents는 project operating layer uninstall 대상이 아니다.
@@ -0,0 +1,16 @@
1
+ ---
2
+ status: Reserved
3
+ layer: business
4
+ owner: project
5
+ read_when:
6
+ - business_rule_check
7
+ update_when:
8
+ - business_rule_changes
9
+ ---
10
+ # Business Rules
11
+
12
+ 이 문서는 Reserved 상태입니다. 프로젝트가 실제 규칙을 보강하기 전까지 현재 판단 근거로 사용하지 마세요.
13
+
14
+ ## 규칙
15
+
16
+ - TBD
@@ -0,0 +1,14 @@
1
+ ---
2
+ status: Active
3
+ layer: status
4
+ owner: project
5
+ read_when:
6
+ - before_task
7
+ update_when:
8
+ - document_status_changes
9
+ ---
10
+ # Docs Status
11
+
12
+ | path | status | owner |
13
+ | --- | --- | --- |
14
+ {{documents_table}}
@@ -0,0 +1,8 @@
1
+ {
2
+ "packs": [
3
+ {
4
+ "id": "spec-lifecycle",
5
+ "source_path": "spec-lifecycle"
6
+ }
7
+ ]
8
+ }
@@ -0,0 +1,26 @@
1
+ ---
2
+ status: Reserved
3
+ layer: spec
4
+ owner: project
5
+ read_when:
6
+ - spec_lifecycle
7
+ update_when:
8
+ - spec_lifecycle_changes
9
+ ---
10
+ # Specs
11
+
12
+ 이 문서는 Reserved 상태입니다. 프로젝트가 실제 spec lifecycle 문서를 보강하기 전까지 현재 판단 근거로 사용하지 마세요.
13
+
14
+ ## 디렉토리 구조
15
+
16
+ ```text
17
+ docs/specs/
18
+ ├── baseline/
19
+ └── initial-build/
20
+ ```
21
+
22
+ ## 기준
23
+
24
+ - `baseline/`은 승인된 제품/기술/UI 기준 문서를 둡니다.
25
+ - `initial-build/`는 초기 구현 work packet과 관련 산출물을 둡니다.
26
+ - 실제 판단 근거로 쓰기 전에 각 문서의 frontmatter와 `docs/docs-status.md` 상태를 갱신합니다.
@@ -0,0 +1,26 @@
1
+ ---
2
+ status: Reserved
3
+ layer: spec
4
+ owner: project
5
+ read_when:
6
+ - spec_lifecycle
7
+ update_when:
8
+ - spec_lifecycle_changes
9
+ ---
10
+ # Specs
11
+
12
+ This document is Reserved. Do not use this document as current decision-making evidence until the project fills in real spec lifecycle documents.
13
+
14
+ ## Directory Structure
15
+
16
+ ```text
17
+ docs/specs/
18
+ ├── baseline/
19
+ └── initial-build/
20
+ ```
21
+
22
+ ## Rules
23
+
24
+ - `baseline/` contains approved product, technical, and UI baseline documents.
25
+ - `initial-build/` contains initial implementation work packets and related artifacts.
26
+ - Before using any document as decision-making evidence, update its frontmatter and its status in `docs/docs-status.md`.
@@ -0,0 +1,182 @@
1
+ # Skill 작성 가이드
2
+
3
+ 이 디렉터리는 설치 가능한 agent skill의 source of truth입니다.
4
+
5
+ ## 용어
6
+
7
+ ### Reference Skill
8
+
9
+ `reference skill`은 lazy-load되는 지식 pack입니다.
10
+
11
+ - 정식 상세 내용은 `references/reference.md`에 둡니다.
12
+ - `SKILL.md`는 얇게 유지하고, agent가 언제 skill을 써야 하는지와 무엇을 먼저 읽어야 하는지만 안내합니다.
13
+ - 표준, stack 가이드, 큰 도메인 reference에 사용합니다.
14
+
15
+ ### Task Skill
16
+
17
+ `task skill`은 절차형 workflow입니다.
18
+
19
+ - 정식 절차는 `SKILL.md`에 둡니다.
20
+ - `references/`는 선택적인 보조 자료입니다.
21
+ - 반복 가능한 점검, 작업, guided workflow에 사용합니다.
22
+
23
+ ### Task Skill 사용
24
+
25
+ 반복되는 운영 절차는 task skill로 둡니다. 예를 들어 `doc-impact-reviewer`는 변경 완료 또는 커밋 직전에 diff를 확인하고, 갱신 후보 문서를 `required / recommended / not needed`로 제안한 뒤 사용자 승인 후 승인된 문서만 수정합니다.
26
+
27
+ 승인이 필요한 task skill은 자동 호출을 막습니다.
28
+
29
+ - Codex: `agents/openai.yaml`에 `policy.allow_implicit_invocation: false`를 둡니다.
30
+ - Claude Code: `SKILL.md` frontmatter에 `disable-model-invocation: true`를 둡니다.
31
+ - Gemini CLI: skill-level explicit-only flag가 없으므로 본문에 명시 호출 전용 규칙을 적습니다.
32
+
33
+ 설치 예시:
34
+
35
+ ```bash
36
+ ai-ops skill install doc-impact-reviewer --tool codex
37
+ ```
38
+
39
+ ## 디렉터리 구조
40
+
41
+ ```text
42
+ apps/cli/data/skills/
43
+ README.md
44
+ README.ko.md
45
+ skill-registry.json
46
+ reference-skills/
47
+ <skill-name>/
48
+ SKILL.md
49
+ agents/ # optional
50
+ references/ # required for reference skills
51
+ assets/ # optional
52
+ scripts/ # optional
53
+ task-skills/
54
+ <skill-name>/
55
+ SKILL.md
56
+ references/ # optional
57
+ assets/ # optional
58
+ scripts/ # optional
59
+ ```
60
+
61
+ ## 작성 규칙
62
+
63
+ 1. 디렉터리 이름은 frontmatter `name`과 정확히 일치해야 합니다.
64
+ 2. `SKILL.md`는 YAML frontmatter로 시작해야 합니다.
65
+ 3. `kind`, `supported_tools`, preset grouping, `source_path`는 `skill-registry.json`에 둡니다.
66
+ 4. `reference` skill은 `reference-skills/` 아래에 두고 `references/reference.md`를 포함해야 합니다.
67
+ 5. `task` skill은 `task-skills/` 아래에 두고 실행 절차를 `SKILL.md`에 둡니다.
68
+ 6. 같은 상세 내용을 `SKILL.md`와 `references/`에 중복하지 않습니다.
69
+ 7. 도구별 metadata는 skill source 안에 직접 작성하고 CLI가 그대로 복사합니다.
70
+ 8. Codex와 Gemini는 `.agents/skills/<skill-name>`에 설치합니다. Claude는 `.claude/skills/<skill-name>`에 설치합니다.
71
+ 9. CLI는 skill 디렉터리 트리 전체를 그대로 복사하므로 `agents/`, `references/`, `assets/`, `scripts/` 아래 파일은 변경 없이 설치됩니다.
72
+
73
+ ## Frontmatter 필드
74
+
75
+ `SKILL.md` frontmatter는 이제 agent-facing 용도입니다. CLI는 아래 필수 필드를 검증하고, 추가 도구별 frontmatter 필드는 무시합니다.
76
+
77
+ | 필드 | 필수 | 예시 | 의미 |
78
+ | --- | --- | --- | --- |
79
+ | `name` | 예 | `graphql-contract` | 고유 skill 이름과 설치 디렉터리 key |
80
+ | `description` | 예 | `Use when changing GraphQL schema contracts.` | discovery/autotrigger 요약 |
81
+
82
+ ## Registry 필드
83
+
84
+ `skill-registry.json`은 install/catalog SSOT입니다.
85
+
86
+ | 필드 | 필수 | 예시 | 의미 |
87
+ | --- | --- | --- | --- |
88
+ | `id` | 예 | `graphql-contract` | canonical skill id |
89
+ | `kind` | 예 | `reference` / `task` | skill category |
90
+ | `supported_tools` | 예 | `["claude-code", "codex", "gemini"]` | 설치 가능한 도구 |
91
+ | `groups` | 예 | `["frontend-web"]` | 표시/discovery grouping |
92
+ | `included_in_presets` | 예 | `["frontend-web", "backend-ts"]` | `ai-ops init`에서 이 skill을 노출하는 preset |
93
+ | `source_path` | 예 | `reference-skills/graphql-contract` | skill source가 있는 상대 디렉터리 |
94
+
95
+ ## Content 배치
96
+
97
+ ### Reference Skill
98
+
99
+ - `SKILL.md`: 짧은 routing note
100
+ - `references/reference.md`: 전체 상세 내용
101
+
102
+ ### Task Skill
103
+
104
+ - `SKILL.md`: 실행 가능한 전체 절차
105
+ - `references/`: 선택적인 배경 자료
106
+ - `scripts/`: 선택적인 실행 helper
107
+
108
+ ## 도구별 호출 제어
109
+
110
+ skill을 explicit-only로 만들어야 하면 skill 작성자가 도구별 metadata를 직접 추가해야 합니다.
111
+
112
+ ### Codex
113
+
114
+ `agents/openai.yaml`을 직접 만듭니다.
115
+
116
+ ```yaml
117
+ allow_implicit_invocation: false
118
+ ```
119
+
120
+ - Codex가 description만 보고 skill을 자동 호출하면 안 될 때 사용합니다.
121
+ - CLI가 전체 디렉터리 트리를 복사하므로 `agents/openai.yaml`은 그대로 설치됩니다.
122
+
123
+ ### Claude Code
124
+
125
+ `SKILL.md` frontmatter에 `disable-model-invocation: true`를 직접 추가합니다.
126
+
127
+ ```yaml
128
+ ---
129
+ name: deploy-script
130
+ description: Runs the deployment workflow.
131
+ disable-model-invocation: true
132
+ ---
133
+ ```
134
+
135
+ - Claude가 명시적인 `/skill-name` 호출로만 skill을 로드해야 할 때 사용합니다.
136
+ - CLI는 이 추가 frontmatter 필드를 보존하고 자동 생성하지 않습니다.
137
+
138
+ ### Gemini CLI
139
+
140
+ Gemini CLI는 현재 implicit invocation 비활성화를 위한 skill-level frontmatter flag를 제공하지 않습니다.
141
+
142
+ - Gemini에서 explicit-only 동작이 필요하면 custom command를 사용합니다.
143
+ - 가짜 Gemini 전용 필드를 `SKILL.md`에 추가하지 마세요. Gemini가 해석하지 않습니다.
144
+
145
+ ## 예시
146
+
147
+ ### Reference Skill Skeleton
148
+
149
+ ```text
150
+ reference-skills/graphql-contract/
151
+ SKILL.md
152
+ agents/
153
+ openai.yaml # optional
154
+ references/
155
+ reference.md
156
+ ```
157
+
158
+ ### Task Skill Skeleton
159
+
160
+ ```text
161
+ task-skills/skill-load-check/
162
+ SKILL.md
163
+ scripts/
164
+ loaded.js
165
+ ```
166
+
167
+ ## 임시 검증 Skill
168
+
169
+ `skill-load-check`는 임시 검증 skill 예시입니다.
170
+
171
+ - description은 좁고 test-focused하게 유지합니다.
172
+ - 본문은 짧고 절차형으로 유지합니다.
173
+ - install/load workflow가 검증된 뒤에는 나중에 삭제해도 됩니다.
174
+
175
+ ## 운영 Task Skill
176
+
177
+ `doc-impact-reviewer`는 운영 문서 영향도를 수동으로 검토하는 task skill입니다.
178
+
179
+ - git status, diff, 변경 파일, 관련 operating-layer 문서를 읽습니다.
180
+ - 편집 전에 문서 후보와 리스크를 보고합니다.
181
+ - 사용자 확인 전에는 편집하지 않습니다.
182
+ - staging, commit, hook 설치를 직접 수행하지 않습니다.
@@ -20,11 +20,28 @@ A `task skill` is a procedural workflow.
20
20
  - `references/` is optional supporting material only
21
21
  - Use it for repeatable checks, actions, and guided workflows
22
22
 
23
+ ### Task Skill Usage
24
+
25
+ Keep repeatable operating procedures as task skills. For example, `doc-impact-reviewer` checks the diff when work is finished or just before commit, classifies document update candidates as `required / recommended / not needed`, and edits only the documents the user approves.
26
+
27
+ Disable automatic invocation for task skills that require explicit approval.
28
+
29
+ - Codex: add `policy.allow_implicit_invocation: false` to `agents/openai.yaml`.
30
+ - Claude Code: add `disable-model-invocation: true` to the `SKILL.md` frontmatter.
31
+ - Gemini CLI: there is no skill-level explicit-only flag, so write the explicit-invocation rule in the skill body.
32
+
33
+ Install example:
34
+
35
+ ```bash
36
+ ai-ops skill install doc-impact-reviewer --tool codex
37
+ ```
38
+
23
39
  ## Directory Shape
24
40
 
25
41
  ```text
26
42
  apps/cli/data/skills/
27
43
  README.md
44
+ README.ko.md
28
45
  skill-registry.json
29
46
  reference-skills/
30
47
  <skill-name>/
@@ -45,7 +62,7 @@ apps/cli/data/skills/
45
62
 
46
63
  1. Directory name must exactly match frontmatter `name`.
47
64
  2. `SKILL.md` must start with YAML frontmatter.
48
- 3. `kind`, `supported_tools`, `install_scopes`, preset grouping, and `source_path` live in `skill-registry.json`.
65
+ 3. `kind`, `supported_tools`, preset grouping, and `source_path` live in `skill-registry.json`.
49
66
  4. A `reference` skill must live under `reference-skills/` and include `references/reference.md`.
50
67
  5. A `task` skill must live under `task-skills/` and keep its executable procedure in `SKILL.md`.
51
68
  6. Do not duplicate the same detailed content across `SKILL.md` and `references/`.
@@ -71,7 +88,6 @@ apps/cli/data/skills/
71
88
  | `id` | Yes | `graphql-contract` | Canonical skill id |
72
89
  | `kind` | Yes | `reference` / `task` | Skill category |
73
90
  | `supported_tools` | Yes | `["claude-code", "codex", "gemini"]` | Where the skill may be installed |
74
- | `install_scopes` | Yes | `["project", "user"]` | Allowed install scopes |
75
91
  | `groups` | Yes | `["frontend-web"]` | Display/discovery grouping |
76
92
  | `included_in_presets` | Yes | `["frontend-web", "backend-ts"]` | Presets that surface this skill in `ai-ops init` |
77
93
  | `source_path` | Yes | `reference-skills/graphql-contract` | Relative directory that contains the skill source |
@@ -155,3 +171,12 @@ task-skills/skill-load-check/
155
171
  - Keep the description narrow and test-focused
156
172
  - Keep the body short and procedural
157
173
  - It is acceptable to delete this skill later once the install/load workflow is proven
174
+
175
+ ## Operating Task Skills
176
+
177
+ `doc-impact-reviewer` is a task skill for manually reviewing operating-document impact.
178
+
179
+ - It reads git status, diffs, changed files, and related operating-layer documents.
180
+ - It reports document candidates and risk before editing.
181
+ - It does not edit before user confirmation.
182
+ - It does not stage, commit, or install hooks by itself.
@@ -4,7 +4,6 @@
4
4
  "id": "ai-llm-python-runtime",
5
5
  "kind": "reference",
6
6
  "supported_tools": ["claude-code", "codex", "gemini"],
7
- "install_scopes": ["project", "user"],
8
7
  "groups": ["backend-python"],
9
8
  "included_in_presets": [],
10
9
  "source_path": "reference-skills/ai-llm-python-runtime"
@@ -13,7 +12,6 @@
13
12
  "id": "backend-python-fastapi-runtime",
14
13
  "kind": "reference",
15
14
  "supported_tools": ["claude-code", "codex", "gemini"],
16
- "install_scopes": ["project", "user"],
17
15
  "groups": ["backend-python"],
18
16
  "included_in_presets": ["backend-python"],
19
17
  "source_path": "reference-skills/backend-python-fastapi-runtime"
@@ -22,7 +20,6 @@
22
20
  "id": "backend-service-standards",
23
21
  "kind": "reference",
24
22
  "supported_tools": ["claude-code", "codex", "gemini"],
25
- "install_scopes": ["project", "user"],
26
23
  "groups": ["backend-ts", "backend-python"],
27
24
  "included_in_presets": ["backend-ts", "backend-python"],
28
25
  "source_path": "reference-skills/backend-service-standards"
@@ -31,7 +28,6 @@
31
28
  "id": "backend-ts-nestjs-runtime",
32
29
  "kind": "reference",
33
30
  "supported_tools": ["claude-code", "codex", "gemini"],
34
- "install_scopes": ["project", "user"],
35
31
  "groups": ["backend-ts"],
36
32
  "included_in_presets": ["backend-ts"],
37
33
  "source_path": "reference-skills/backend-ts-nestjs-runtime"
@@ -40,7 +36,6 @@
40
36
  "id": "data-pipeline-python-performance",
41
37
  "kind": "reference",
42
38
  "supported_tools": ["claude-code", "codex", "gemini"],
43
- "install_scopes": ["project", "user"],
44
39
  "groups": ["backend-python"],
45
40
  "included_in_presets": [],
46
41
  "source_path": "reference-skills/data-pipeline-python-performance"
@@ -49,7 +44,6 @@
49
44
  "id": "db-prisma-postgresql",
50
45
  "kind": "reference",
51
46
  "supported_tools": ["claude-code", "codex", "gemini"],
52
- "install_scopes": ["project", "user"],
53
47
  "groups": ["backend-ts"],
54
48
  "included_in_presets": ["backend-ts"],
55
49
  "source_path": "reference-skills/db-prisma-postgresql"
@@ -58,7 +52,6 @@
58
52
  "id": "db-sqlalchemy-postgresql",
59
53
  "kind": "reference",
60
54
  "supported_tools": ["claude-code", "codex", "gemini"],
61
- "install_scopes": ["project", "user"],
62
55
  "groups": ["backend-python"],
63
56
  "included_in_presets": ["backend-python"],
64
57
  "source_path": "reference-skills/db-sqlalchemy-postgresql"
@@ -67,7 +60,6 @@
67
60
  "id": "frontend-app-flutter-runtime",
68
61
  "kind": "reference",
69
62
  "supported_tools": ["claude-code", "codex", "gemini"],
70
- "install_scopes": ["project", "user"],
71
63
  "groups": ["frontend-app"],
72
64
  "included_in_presets": ["frontend-app"],
73
65
  "source_path": "reference-skills/frontend-app-flutter-runtime"
@@ -76,7 +68,6 @@
76
68
  "id": "frontend-web-react-next-runtime",
77
69
  "kind": "reference",
78
70
  "supported_tools": ["claude-code", "codex", "gemini"],
79
- "install_scopes": ["project", "user"],
80
71
  "groups": ["frontend-web"],
81
72
  "included_in_presets": ["frontend-web"],
82
73
  "source_path": "reference-skills/frontend-web-react-next-runtime"
@@ -85,7 +76,6 @@
85
76
  "id": "frontend-web-shadcn-ui",
86
77
  "kind": "reference",
87
78
  "supported_tools": ["claude-code", "codex", "gemini"],
88
- "install_scopes": ["project", "user"],
89
79
  "groups": ["frontend-web"],
90
80
  "included_in_presets": ["frontend-web"],
91
81
  "source_path": "reference-skills/frontend-web-shadcn-ui"
@@ -94,7 +84,6 @@
94
84
  "id": "graphql-client-integration",
95
85
  "kind": "reference",
96
86
  "supported_tools": ["claude-code", "codex", "gemini"],
97
- "install_scopes": ["project", "user"],
98
87
  "groups": ["frontend-web", "frontend-app"],
99
88
  "included_in_presets": ["frontend-web", "frontend-app"],
100
89
  "source_path": "reference-skills/graphql-client-integration"
@@ -103,7 +92,6 @@
103
92
  "id": "graphql-contract",
104
93
  "kind": "reference",
105
94
  "supported_tools": ["claude-code", "codex", "gemini"],
106
- "install_scopes": ["project", "user"],
107
95
  "groups": ["frontend-web", "frontend-app", "backend-ts"],
108
96
  "included_in_presets": ["frontend-web", "frontend-app", "backend-ts"],
109
97
  "source_path": "reference-skills/graphql-contract"
@@ -112,7 +100,6 @@
112
100
  "id": "graphql-server-runtime",
113
101
  "kind": "reference",
114
102
  "supported_tools": ["claude-code", "codex", "gemini"],
115
- "install_scopes": ["project", "user"],
116
103
  "groups": ["backend-ts"],
117
104
  "included_in_presets": ["backend-ts"],
118
105
  "source_path": "reference-skills/graphql-server-runtime"
@@ -121,25 +108,86 @@
121
108
  "id": "python-language",
122
109
  "kind": "reference",
123
110
  "supported_tools": ["claude-code", "codex", "gemini"],
124
- "install_scopes": ["project", "user"],
125
111
  "groups": ["backend-python"],
126
112
  "included_in_presets": ["backend-python"],
127
113
  "source_path": "reference-skills/python-language"
128
114
  },
115
+ {
116
+ "id": "doc-impact-reviewer",
117
+ "kind": "task",
118
+ "supported_tools": ["claude-code", "codex", "gemini"],
119
+ "groups": ["agent-operating-layer"],
120
+ "included_in_presets": [],
121
+ "source_path": "task-skills/doc-impact-reviewer"
122
+ },
129
123
  {
130
124
  "id": "skill-load-check",
131
125
  "kind": "task",
132
126
  "supported_tools": ["claude-code", "codex", "gemini"],
133
- "install_scopes": ["project", "user"],
134
127
  "groups": [],
135
128
  "included_in_presets": [],
136
129
  "source_path": "task-skills/skill-load-check"
137
130
  },
131
+ {
132
+ "id": "spec-baseline-sync",
133
+ "kind": "task",
134
+ "supported_tools": ["claude-code", "codex", "gemini"],
135
+ "groups": ["spec-lifecycle"],
136
+ "included_in_presets": [],
137
+ "source_path": "task-skills/spec-baseline-sync"
138
+ },
139
+ {
140
+ "id": "spec-product-01-idea-to-brief",
141
+ "kind": "task",
142
+ "supported_tools": ["claude-code", "codex", "gemini"],
143
+ "groups": ["spec-lifecycle"],
144
+ "included_in_presets": [],
145
+ "source_path": "task-skills/spec-product-01-idea-to-brief"
146
+ },
147
+ {
148
+ "id": "spec-product-02-brief-to-technical-context",
149
+ "kind": "task",
150
+ "supported_tools": ["claude-code", "codex", "gemini"],
151
+ "groups": ["spec-lifecycle"],
152
+ "included_in_presets": [],
153
+ "source_path": "task-skills/spec-product-02-brief-to-technical-context"
154
+ },
155
+ {
156
+ "id": "spec-product-03-brief-to-product-spec",
157
+ "kind": "task",
158
+ "supported_tools": ["claude-code", "codex", "gemini"],
159
+ "groups": ["spec-lifecycle"],
160
+ "included_in_presets": [],
161
+ "source_path": "task-skills/spec-product-03-brief-to-product-spec"
162
+ },
163
+ {
164
+ "id": "spec-product-04-product-spec-to-ui-spec",
165
+ "kind": "task",
166
+ "supported_tools": ["claude-code", "codex", "gemini"],
167
+ "groups": ["spec-lifecycle"],
168
+ "included_in_presets": [],
169
+ "source_path": "task-skills/spec-product-04-product-spec-to-ui-spec"
170
+ },
171
+ {
172
+ "id": "spec-product-05-spec-to-work-packets",
173
+ "kind": "task",
174
+ "supported_tools": ["claude-code", "codex", "gemini"],
175
+ "groups": ["spec-lifecycle"],
176
+ "included_in_presets": [],
177
+ "source_path": "task-skills/spec-product-05-spec-to-work-packets"
178
+ },
179
+ {
180
+ "id": "spec-shared-glossary-sync",
181
+ "kind": "task",
182
+ "supported_tools": ["claude-code", "codex", "gemini"],
183
+ "groups": ["spec-lifecycle"],
184
+ "included_in_presets": [],
185
+ "source_path": "task-skills/spec-shared-glossary-sync"
186
+ },
138
187
  {
139
188
  "id": "typescript-language",
140
189
  "kind": "reference",
141
190
  "supported_tools": ["claude-code", "codex", "gemini"],
142
- "install_scopes": ["project", "user"],
143
191
  "groups": ["frontend-web", "backend-ts"],
144
192
  "included_in_presets": ["frontend-web", "backend-ts"],
145
193
  "source_path": "reference-skills/typescript-language"