viepilot 2.50.1 → 3.7.2
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/CHANGELOG.md +204 -0
- package/README.md +1 -1
- package/bin/viepilot.cjs +1 -0
- package/bin/vp-tools.cjs +123 -1
- package/docs/brainstorm/session-2026-05-22.md +472 -0
- package/docs/dev/agents.md +51 -41
- package/lib/adapter-context.cjs +294 -0
- package/lib/adapters/antigravity.cjs +8 -2
- package/lib/adapters/claude-code.cjs +4 -0
- package/lib/audit/browser-runner.cjs +102 -0
- package/lib/intake/adapters/browser.cjs +58 -0
- package/lib/intake/adapters/excel-m365.cjs +54 -6
- package/lib/intake/auto-intake.cjs +194 -0
- package/lib/intake/classifier.cjs +22 -4
- package/lib/intake/manifest.cjs +81 -0
- package/lib/intake/triage-ux.cjs +10 -2
- package/lib/intake/validator.cjs +97 -0
- package/lib/intake/writeback.cjs +169 -3
- package/lib/request/url-enricher.cjs +69 -0
- package/lib/viepilot-install.cjs +15 -0
- package/package.json +1 -1
- package/skills/vp-audit/SKILL.md +99 -3
- package/skills/vp-auto/SKILL.md +54 -4
- package/skills/vp-brainstorm/SKILL.md +69 -3
- package/skills/vp-crystallize/SKILL.md +52 -3
- package/skills/vp-debug/SKILL.md +52 -3
- package/skills/vp-design/SKILL.md +52 -3
- package/skills/vp-docs/SKILL.md +52 -3
- package/skills/vp-evolve/SKILL.md +52 -3
- package/skills/vp-info/SKILL.md +52 -3
- package/skills/vp-intake/SKILL.md +306 -7
- package/skills/vp-pause/SKILL.md +52 -3
- package/skills/vp-persona/SKILL.md +52 -3
- package/skills/vp-proposal/SKILL.md +52 -3
- package/skills/vp-request/SKILL.md +72 -3
- package/skills/vp-resume/SKILL.md +52 -3
- package/skills/vp-rollback/SKILL.md +52 -3
- package/skills/vp-skills/SKILL.md +52 -3
- package/skills/vp-status/SKILL.md +52 -3
- package/skills/vp-task/SKILL.md +52 -3
- package/skills/vp-ui-components/SKILL.md +52 -3
- package/skills/vp-update/SKILL.md +52 -3
- package/workflows/autonomous.md +268 -18
- package/workflows/brainstorm.md +222 -7
- package/workflows/crystallize.md +124 -6
- package/workflows/design.md +62 -1
- package/workflows/request.md +54 -8
|
@@ -9,7 +9,7 @@ Output this banner as the **first** thing on every invocation — before questio
|
|
|
9
9
|
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
|
10
10
|
```
|
|
11
11
|
</greeting>
|
|
12
|
-
<
|
|
12
|
+
<adapter id="claude-code">
|
|
13
13
|
## A. Skill Invocation
|
|
14
14
|
- Skill được gọi khi user mention `vp-persona`, `/vp-persona`, "persona", "profile", "customize workflow"
|
|
15
15
|
- Treat all user text after the skill mention as `{{VP_ARGS}}`
|
|
@@ -18,8 +18,57 @@ Output this banner as the **first** thing on every invocation — before questio
|
|
|
18
18
|
Prompt user conversationally with numbered list options.
|
|
19
19
|
|
|
20
20
|
## C. Tool Usage
|
|
21
|
-
Use
|
|
22
|
-
|
|
21
|
+
Use Claude Code tools: `Bash` (shell), `Read` (file), `Edit` + `Write` (file write/patch),
|
|
22
|
+
`Grep` (search), `Glob` (file patterns), `LS`, `WebSearch`, `WebFetch`,
|
|
23
|
+
`Agent` (spawn subagent — multi-level nesting supported)
|
|
24
|
+
Interactive: `AskUserQuestion` (deferred — preload via ToolSearch before first call)
|
|
25
|
+
</adapter>
|
|
26
|
+
|
|
27
|
+
<adapter id="cursor-agent">
|
|
28
|
+
## A. Skill Invocation
|
|
29
|
+
Same trigger keywords as claude-code adapter.
|
|
30
|
+
|
|
31
|
+
## C. Tool Usage
|
|
32
|
+
Use Cursor tools: `run_terminal_cmd` (shell), `read_file` (read), `edit_file` (write/edit),
|
|
33
|
+
`grep_search` (search), `web_search`, `codebase_search`, `list_dir`, `file_search`
|
|
34
|
+
Interactive: text list fallback (AskQuestion available in Plan Mode only; Agent Mode = text)
|
|
35
|
+
Subagent: `/multitask` (user command, single-level only — not a callable tool)
|
|
36
|
+
MCP limit: 40 tools
|
|
37
|
+
</adapter>
|
|
38
|
+
|
|
39
|
+
<adapter id="antigravity">
|
|
40
|
+
## A. Skill Invocation
|
|
41
|
+
Same trigger keywords as claude-code adapter.
|
|
42
|
+
Skill discovery: LLM-driven (automatic, no slash command needed).
|
|
43
|
+
|
|
44
|
+
## C. Tool Usage
|
|
45
|
+
Use Antigravity tools: `shell` (cmd), `file_read`, `file_write`, MCP plugins
|
|
46
|
+
Interactive: text fallback (TUI-based; no formal AskUserQuestion)
|
|
47
|
+
Skill path: `.agents/skills/<skill>/SKILL.md` (project) or `~/.gemini/antigravity/skills/` (global)
|
|
48
|
+
Note: Gemini CLI deprecated June 18, 2026 — use Antigravity CLI.
|
|
49
|
+
</adapter>
|
|
50
|
+
|
|
51
|
+
<adapter id="codex">
|
|
52
|
+
## A. Skill Invocation
|
|
53
|
+
Same trigger keywords as claude-code adapter.
|
|
54
|
+
|
|
55
|
+
## C. Tool Usage
|
|
56
|
+
Use Codex tools: `container.exec` (sandboxed shell), `apply_patch` (file write), `web_search`
|
|
57
|
+
Interactive: text fallback (TUI Tab/Enter injection)
|
|
58
|
+
Config: `~/.codex/config.toml`
|
|
59
|
+
</adapter>
|
|
60
|
+
|
|
61
|
+
<adapter id="copilot">
|
|
62
|
+
## A. Skill Invocation
|
|
63
|
+
Same trigger keywords as claude-code adapter.
|
|
64
|
+
Discovery: User-driven (`@agent-name` in GitHub Copilot Chat).
|
|
65
|
+
|
|
66
|
+
## C. Tool Usage
|
|
67
|
+
Use Copilot tools: `runCommands` (shell), `read`/`readfile` (read), `edit`/`editFiles` (write),
|
|
68
|
+
`code_search`, `find_references`
|
|
69
|
+
Interactive: `askQuestions` (main agent only — NOT available in subagents; VS Code issue #293745)
|
|
70
|
+
Skill path: `.github/agents/<name>.agent.md`
|
|
71
|
+
</adapter>
|
|
23
72
|
<scope_policy>
|
|
24
73
|
## ViePilot Namespace Guard (BUG-004)
|
|
25
74
|
- Default mode: only use and reference `vp-*` skills in ViePilot workflows.
|
|
@@ -53,7 +53,7 @@ Silent if command unavailable or errors.
|
|
|
53
53
|
</persona_context>
|
|
54
54
|
|
|
55
55
|
|
|
56
|
-
<
|
|
56
|
+
<adapter id="claude-code">
|
|
57
57
|
## A. Skill Invocation
|
|
58
58
|
- Skill được gọi khi user mention `vp-proposal`, `/vp-proposal`, "proposal", "pitch deck", "presentation", "tài liệu đề xuất"
|
|
59
59
|
- Treat all user text after the skill mention as `{{VP_ARGS}}`
|
|
@@ -62,8 +62,57 @@ Silent if command unavailable or errors.
|
|
|
62
62
|
Prompt user conversationally with numbered list options.
|
|
63
63
|
|
|
64
64
|
## C. Tool Usage
|
|
65
|
-
Use
|
|
66
|
-
|
|
65
|
+
Use Claude Code tools: `Bash` (shell), `Read` (file), `Edit` + `Write` (file write/patch),
|
|
66
|
+
`Grep` (search), `Glob` (file patterns), `LS`, `WebSearch`, `WebFetch`,
|
|
67
|
+
`Agent` (spawn subagent — multi-level nesting supported)
|
|
68
|
+
Interactive: `AskUserQuestion` (deferred — preload via ToolSearch before first call)
|
|
69
|
+
</adapter>
|
|
70
|
+
|
|
71
|
+
<adapter id="cursor-agent">
|
|
72
|
+
## A. Skill Invocation
|
|
73
|
+
Same trigger keywords as claude-code adapter.
|
|
74
|
+
|
|
75
|
+
## C. Tool Usage
|
|
76
|
+
Use Cursor tools: `run_terminal_cmd` (shell), `read_file` (read), `edit_file` (write/edit),
|
|
77
|
+
`grep_search` (search), `web_search`, `codebase_search`, `list_dir`, `file_search`
|
|
78
|
+
Interactive: text list fallback (AskQuestion available in Plan Mode only; Agent Mode = text)
|
|
79
|
+
Subagent: `/multitask` (user command, single-level only — not a callable tool)
|
|
80
|
+
MCP limit: 40 tools
|
|
81
|
+
</adapter>
|
|
82
|
+
|
|
83
|
+
<adapter id="antigravity">
|
|
84
|
+
## A. Skill Invocation
|
|
85
|
+
Same trigger keywords as claude-code adapter.
|
|
86
|
+
Skill discovery: LLM-driven (automatic, no slash command needed).
|
|
87
|
+
|
|
88
|
+
## C. Tool Usage
|
|
89
|
+
Use Antigravity tools: `shell` (cmd), `file_read`, `file_write`, MCP plugins
|
|
90
|
+
Interactive: text fallback (TUI-based; no formal AskUserQuestion)
|
|
91
|
+
Skill path: `.agents/skills/<skill>/SKILL.md` (project) or `~/.gemini/antigravity/skills/` (global)
|
|
92
|
+
Note: Gemini CLI deprecated June 18, 2026 — use Antigravity CLI.
|
|
93
|
+
</adapter>
|
|
94
|
+
|
|
95
|
+
<adapter id="codex">
|
|
96
|
+
## A. Skill Invocation
|
|
97
|
+
Same trigger keywords as claude-code adapter.
|
|
98
|
+
|
|
99
|
+
## C. Tool Usage
|
|
100
|
+
Use Codex tools: `container.exec` (sandboxed shell), `apply_patch` (file write), `web_search`
|
|
101
|
+
Interactive: text fallback (TUI Tab/Enter injection)
|
|
102
|
+
Config: `~/.codex/config.toml`
|
|
103
|
+
</adapter>
|
|
104
|
+
|
|
105
|
+
<adapter id="copilot">
|
|
106
|
+
## A. Skill Invocation
|
|
107
|
+
Same trigger keywords as claude-code adapter.
|
|
108
|
+
Discovery: User-driven (`@agent-name` in GitHub Copilot Chat).
|
|
109
|
+
|
|
110
|
+
## C. Tool Usage
|
|
111
|
+
Use Copilot tools: `runCommands` (shell), `read`/`readfile` (read), `edit`/`editFiles` (write),
|
|
112
|
+
`code_search`, `find_references`
|
|
113
|
+
Interactive: `askQuestions` (main agent only — NOT available in subagents; VS Code issue #293745)
|
|
114
|
+
Skill path: `.github/agents/<name>.agent.md`
|
|
115
|
+
</adapter>
|
|
67
116
|
<scope_policy>
|
|
68
117
|
## ViePilot Namespace Guard (BUG-004)
|
|
69
118
|
- Default mode: only use and reference `vp-*` skills in ViePilot workflows.
|
|
@@ -53,7 +53,7 @@ Silent if command unavailable or errors.
|
|
|
53
53
|
</persona_context>
|
|
54
54
|
|
|
55
55
|
|
|
56
|
-
<
|
|
56
|
+
<adapter id="claude-code">
|
|
57
57
|
## A. Skill Invocation
|
|
58
58
|
- Skill được gọi khi user mention `vp-request`, `/vp-request`, "request", "yêu cầu", "bug", "lỗi", "feature mới", "nâng cấp"
|
|
59
59
|
- Treat all user text after the skill mention as `{{VP_ARGS}}`
|
|
@@ -62,8 +62,57 @@ Silent if command unavailable or errors.
|
|
|
62
62
|
Prompt user conversationally with numbered list options.
|
|
63
63
|
|
|
64
64
|
## C. Tool Usage
|
|
65
|
-
Use
|
|
66
|
-
|
|
65
|
+
Use Claude Code tools: `Bash` (shell), `Read` (file), `Edit` + `Write` (file write/patch),
|
|
66
|
+
`Grep` (search), `Glob` (file patterns), `LS`, `WebSearch`, `WebFetch`,
|
|
67
|
+
`Agent` (spawn subagent — multi-level nesting supported)
|
|
68
|
+
Interactive: `AskUserQuestion` (deferred — preload via ToolSearch before first call)
|
|
69
|
+
</adapter>
|
|
70
|
+
|
|
71
|
+
<adapter id="cursor-agent">
|
|
72
|
+
## A. Skill Invocation
|
|
73
|
+
Same trigger keywords as claude-code adapter.
|
|
74
|
+
|
|
75
|
+
## C. Tool Usage
|
|
76
|
+
Use Cursor tools: `run_terminal_cmd` (shell), `read_file` (read), `edit_file` (write/edit),
|
|
77
|
+
`grep_search` (search), `web_search`, `codebase_search`, `list_dir`, `file_search`
|
|
78
|
+
Interactive: text list fallback (AskQuestion available in Plan Mode only; Agent Mode = text)
|
|
79
|
+
Subagent: `/multitask` (user command, single-level only — not a callable tool)
|
|
80
|
+
MCP limit: 40 tools
|
|
81
|
+
</adapter>
|
|
82
|
+
|
|
83
|
+
<adapter id="antigravity">
|
|
84
|
+
## A. Skill Invocation
|
|
85
|
+
Same trigger keywords as claude-code adapter.
|
|
86
|
+
Skill discovery: LLM-driven (automatic, no slash command needed).
|
|
87
|
+
|
|
88
|
+
## C. Tool Usage
|
|
89
|
+
Use Antigravity tools: `shell` (cmd), `file_read`, `file_write`, MCP plugins
|
|
90
|
+
Interactive: text fallback (TUI-based; no formal AskUserQuestion)
|
|
91
|
+
Skill path: `.agents/skills/<skill>/SKILL.md` (project) or `~/.gemini/antigravity/skills/` (global)
|
|
92
|
+
Note: Gemini CLI deprecated June 18, 2026 — use Antigravity CLI.
|
|
93
|
+
</adapter>
|
|
94
|
+
|
|
95
|
+
<adapter id="codex">
|
|
96
|
+
## A. Skill Invocation
|
|
97
|
+
Same trigger keywords as claude-code adapter.
|
|
98
|
+
|
|
99
|
+
## C. Tool Usage
|
|
100
|
+
Use Codex tools: `container.exec` (sandboxed shell), `apply_patch` (file write), `web_search`
|
|
101
|
+
Interactive: text fallback (TUI Tab/Enter injection)
|
|
102
|
+
Config: `~/.codex/config.toml`
|
|
103
|
+
</adapter>
|
|
104
|
+
|
|
105
|
+
<adapter id="copilot">
|
|
106
|
+
## A. Skill Invocation
|
|
107
|
+
Same trigger keywords as claude-code adapter.
|
|
108
|
+
Discovery: User-driven (`@agent-name` in GitHub Copilot Chat).
|
|
109
|
+
|
|
110
|
+
## C. Tool Usage
|
|
111
|
+
Use Copilot tools: `runCommands` (shell), `read`/`readfile` (read), `edit`/`editFiles` (write),
|
|
112
|
+
`code_search`, `find_references`
|
|
113
|
+
Interactive: `askQuestions` (main agent only — NOT available in subagents; VS Code issue #293745)
|
|
114
|
+
Skill path: `.github/agents/<name>.agent.md`
|
|
115
|
+
</adapter>
|
|
67
116
|
<scope_policy>
|
|
68
117
|
## ViePilot Namespace Guard (BUG-004)
|
|
69
118
|
- Default mode: only use and reference `vp-*` skills in ViePilot workflows.
|
|
@@ -110,6 +159,26 @@ Optional flags:
|
|
|
110
159
|
- `--brainstorm` : Brainstorm continuation mode
|
|
111
160
|
- `--list` : List pending requests
|
|
112
161
|
- `--quick` : Quick mode (minimal questions)
|
|
162
|
+
|
|
163
|
+
### URL Auto-Enrichment (ENH-093)
|
|
164
|
+
|
|
165
|
+
If your request originates from an existing issue tracker, pass the URL directly:
|
|
166
|
+
|
|
167
|
+
```
|
|
168
|
+
/vp-request https://github.com/org/repo/issues/123
|
|
169
|
+
/vp-request https://company.atlassian.net/browse/PROJ-456
|
|
170
|
+
/vp-request https://trello.com/c/cardId/card-title
|
|
171
|
+
/vp-request https://linear.app/team/issue/ENG-789
|
|
172
|
+
/vp-request https://notion.so/page-slug-abc123
|
|
173
|
+
```
|
|
174
|
+
|
|
175
|
+
ViePilot automatically extracts: title, type, description, priority — you confirm or edit.
|
|
176
|
+
Requires: `browser-intake-agent` + `vercel-labs/agent-browser` (`npx skills add vercel-labs/agent-browser`).
|
|
177
|
+
|
|
178
|
+
**Supported sources**: GitHub Issues, Linear, Jira (Atlassian), Trello, Notion.
|
|
179
|
+
|
|
180
|
+
When extraction is unavailable (non-CC adapter or agent-browser not installed), the URL is stored
|
|
181
|
+
as a `related_url` field in the request file and the normal question flow proceeds.
|
|
113
182
|
</context>
|
|
114
183
|
|
|
115
184
|
<process>
|
|
@@ -53,7 +53,7 @@ Silent if command unavailable or errors.
|
|
|
53
53
|
</persona_context>
|
|
54
54
|
|
|
55
55
|
|
|
56
|
-
<
|
|
56
|
+
<adapter id="claude-code">
|
|
57
57
|
## A. Skill Invocation
|
|
58
58
|
- Skill được gọi khi user mention `vp-resume`, `/vp-resume`, "resume", "tiếp tục", "where was i"
|
|
59
59
|
- Treat all user text after the skill mention as `{{VP_ARGS}}`
|
|
@@ -62,8 +62,57 @@ Silent if command unavailable or errors.
|
|
|
62
62
|
Prompt user conversationally with options.
|
|
63
63
|
|
|
64
64
|
## C. Tool Usage
|
|
65
|
-
Use
|
|
66
|
-
|
|
65
|
+
Use Claude Code tools: `Bash` (shell), `Read` (file), `Edit` + `Write` (file write/patch),
|
|
66
|
+
`Grep` (search), `Glob` (file patterns), `LS`, `WebSearch`, `WebFetch`,
|
|
67
|
+
`Agent` (spawn subagent — multi-level nesting supported)
|
|
68
|
+
Interactive: `AskUserQuestion` (deferred — preload via ToolSearch before first call)
|
|
69
|
+
</adapter>
|
|
70
|
+
|
|
71
|
+
<adapter id="cursor-agent">
|
|
72
|
+
## A. Skill Invocation
|
|
73
|
+
Same trigger keywords as claude-code adapter.
|
|
74
|
+
|
|
75
|
+
## C. Tool Usage
|
|
76
|
+
Use Cursor tools: `run_terminal_cmd` (shell), `read_file` (read), `edit_file` (write/edit),
|
|
77
|
+
`grep_search` (search), `web_search`, `codebase_search`, `list_dir`, `file_search`
|
|
78
|
+
Interactive: text list fallback (AskQuestion available in Plan Mode only; Agent Mode = text)
|
|
79
|
+
Subagent: `/multitask` (user command, single-level only — not a callable tool)
|
|
80
|
+
MCP limit: 40 tools
|
|
81
|
+
</adapter>
|
|
82
|
+
|
|
83
|
+
<adapter id="antigravity">
|
|
84
|
+
## A. Skill Invocation
|
|
85
|
+
Same trigger keywords as claude-code adapter.
|
|
86
|
+
Skill discovery: LLM-driven (automatic, no slash command needed).
|
|
87
|
+
|
|
88
|
+
## C. Tool Usage
|
|
89
|
+
Use Antigravity tools: `shell` (cmd), `file_read`, `file_write`, MCP plugins
|
|
90
|
+
Interactive: text fallback (TUI-based; no formal AskUserQuestion)
|
|
91
|
+
Skill path: `.agents/skills/<skill>/SKILL.md` (project) or `~/.gemini/antigravity/skills/` (global)
|
|
92
|
+
Note: Gemini CLI deprecated June 18, 2026 — use Antigravity CLI.
|
|
93
|
+
</adapter>
|
|
94
|
+
|
|
95
|
+
<adapter id="codex">
|
|
96
|
+
## A. Skill Invocation
|
|
97
|
+
Same trigger keywords as claude-code adapter.
|
|
98
|
+
|
|
99
|
+
## C. Tool Usage
|
|
100
|
+
Use Codex tools: `container.exec` (sandboxed shell), `apply_patch` (file write), `web_search`
|
|
101
|
+
Interactive: text fallback (TUI Tab/Enter injection)
|
|
102
|
+
Config: `~/.codex/config.toml`
|
|
103
|
+
</adapter>
|
|
104
|
+
|
|
105
|
+
<adapter id="copilot">
|
|
106
|
+
## A. Skill Invocation
|
|
107
|
+
Same trigger keywords as claude-code adapter.
|
|
108
|
+
Discovery: User-driven (`@agent-name` in GitHub Copilot Chat).
|
|
109
|
+
|
|
110
|
+
## C. Tool Usage
|
|
111
|
+
Use Copilot tools: `runCommands` (shell), `read`/`readfile` (read), `edit`/`editFiles` (write),
|
|
112
|
+
`code_search`, `find_references`
|
|
113
|
+
Interactive: `askQuestions` (main agent only — NOT available in subagents; VS Code issue #293745)
|
|
114
|
+
Skill path: `.github/agents/<name>.agent.md`
|
|
115
|
+
</adapter>
|
|
67
116
|
<scope_policy>
|
|
68
117
|
## ViePilot Namespace Guard (BUG-004)
|
|
69
118
|
- Default mode: only use and reference `vp-*` skills in ViePilot workflows.
|
|
@@ -53,7 +53,7 @@ Silent if command unavailable or errors.
|
|
|
53
53
|
</persona_context>
|
|
54
54
|
|
|
55
55
|
|
|
56
|
-
<
|
|
56
|
+
<adapter id="claude-code">
|
|
57
57
|
## A. Skill Invocation
|
|
58
58
|
- Skill được gọi khi user mention `vp-rollback`, `/vp-rollback`, "rollback", "quay lại"
|
|
59
59
|
- Treat all user text after the skill mention as `{{VP_ARGS}}`
|
|
@@ -62,8 +62,57 @@ Silent if command unavailable or errors.
|
|
|
62
62
|
Show available checkpoints and confirm before rollback.
|
|
63
63
|
|
|
64
64
|
## C. Tool Usage
|
|
65
|
-
Use
|
|
66
|
-
|
|
65
|
+
Use Claude Code tools: `Bash` (shell), `Read` (file), `Edit` + `Write` (file write/patch),
|
|
66
|
+
`Grep` (search), `Glob` (file patterns), `LS`, `WebSearch`, `WebFetch`,
|
|
67
|
+
`Agent` (spawn subagent — multi-level nesting supported)
|
|
68
|
+
Interactive: `AskUserQuestion` (deferred — preload via ToolSearch before first call)
|
|
69
|
+
</adapter>
|
|
70
|
+
|
|
71
|
+
<adapter id="cursor-agent">
|
|
72
|
+
## A. Skill Invocation
|
|
73
|
+
Same trigger keywords as claude-code adapter.
|
|
74
|
+
|
|
75
|
+
## C. Tool Usage
|
|
76
|
+
Use Cursor tools: `run_terminal_cmd` (shell), `read_file` (read), `edit_file` (write/edit),
|
|
77
|
+
`grep_search` (search), `web_search`, `codebase_search`, `list_dir`, `file_search`
|
|
78
|
+
Interactive: text list fallback (AskQuestion available in Plan Mode only; Agent Mode = text)
|
|
79
|
+
Subagent: `/multitask` (user command, single-level only — not a callable tool)
|
|
80
|
+
MCP limit: 40 tools
|
|
81
|
+
</adapter>
|
|
82
|
+
|
|
83
|
+
<adapter id="antigravity">
|
|
84
|
+
## A. Skill Invocation
|
|
85
|
+
Same trigger keywords as claude-code adapter.
|
|
86
|
+
Skill discovery: LLM-driven (automatic, no slash command needed).
|
|
87
|
+
|
|
88
|
+
## C. Tool Usage
|
|
89
|
+
Use Antigravity tools: `shell` (cmd), `file_read`, `file_write`, MCP plugins
|
|
90
|
+
Interactive: text fallback (TUI-based; no formal AskUserQuestion)
|
|
91
|
+
Skill path: `.agents/skills/<skill>/SKILL.md` (project) or `~/.gemini/antigravity/skills/` (global)
|
|
92
|
+
Note: Gemini CLI deprecated June 18, 2026 — use Antigravity CLI.
|
|
93
|
+
</adapter>
|
|
94
|
+
|
|
95
|
+
<adapter id="codex">
|
|
96
|
+
## A. Skill Invocation
|
|
97
|
+
Same trigger keywords as claude-code adapter.
|
|
98
|
+
|
|
99
|
+
## C. Tool Usage
|
|
100
|
+
Use Codex tools: `container.exec` (sandboxed shell), `apply_patch` (file write), `web_search`
|
|
101
|
+
Interactive: text fallback (TUI Tab/Enter injection)
|
|
102
|
+
Config: `~/.codex/config.toml`
|
|
103
|
+
</adapter>
|
|
104
|
+
|
|
105
|
+
<adapter id="copilot">
|
|
106
|
+
## A. Skill Invocation
|
|
107
|
+
Same trigger keywords as claude-code adapter.
|
|
108
|
+
Discovery: User-driven (`@agent-name` in GitHub Copilot Chat).
|
|
109
|
+
|
|
110
|
+
## C. Tool Usage
|
|
111
|
+
Use Copilot tools: `runCommands` (shell), `read`/`readfile` (read), `edit`/`editFiles` (write),
|
|
112
|
+
`code_search`, `find_references`
|
|
113
|
+
Interactive: `askQuestions` (main agent only — NOT available in subagents; VS Code issue #293745)
|
|
114
|
+
Skill path: `.github/agents/<name>.agent.md`
|
|
115
|
+
</adapter>
|
|
67
116
|
<scope_policy>
|
|
68
117
|
## ViePilot Namespace Guard (BUG-004)
|
|
69
118
|
- Default mode: only use and reference `vp-*` skills in ViePilot workflows.
|
|
@@ -49,7 +49,7 @@ Silent if command unavailable or errors.
|
|
|
49
49
|
</persona_context>
|
|
50
50
|
|
|
51
51
|
|
|
52
|
-
<
|
|
52
|
+
<adapter id="claude-code">
|
|
53
53
|
## A. Skill Invocation
|
|
54
54
|
- Skill được gọi khi user mention `vp-skills`, `/vp-skills`, "scan skills", "list skills", "install skill", "global registry"
|
|
55
55
|
- Treat all user text after the skill mention as `{{VP_ARGS}}`
|
|
@@ -58,8 +58,57 @@ Silent if command unavailable or errors.
|
|
|
58
58
|
Prompt user conversationally with numbered list options at control points.
|
|
59
59
|
|
|
60
60
|
## C. Tool Usage
|
|
61
|
-
Use
|
|
62
|
-
|
|
61
|
+
Use Claude Code tools: `Bash` (shell), `Read` (file), `Edit` + `Write` (file write/patch),
|
|
62
|
+
`Grep` (search), `Glob` (file patterns), `LS`, `WebSearch`, `WebFetch`,
|
|
63
|
+
`Agent` (spawn subagent — multi-level nesting supported)
|
|
64
|
+
Interactive: `AskUserQuestion` (deferred — preload via ToolSearch before first call)
|
|
65
|
+
</adapter>
|
|
66
|
+
|
|
67
|
+
<adapter id="cursor-agent">
|
|
68
|
+
## A. Skill Invocation
|
|
69
|
+
Same trigger keywords as claude-code adapter.
|
|
70
|
+
|
|
71
|
+
## C. Tool Usage
|
|
72
|
+
Use Cursor tools: `run_terminal_cmd` (shell), `read_file` (read), `edit_file` (write/edit),
|
|
73
|
+
`grep_search` (search), `web_search`, `codebase_search`, `list_dir`, `file_search`
|
|
74
|
+
Interactive: text list fallback (AskQuestion available in Plan Mode only; Agent Mode = text)
|
|
75
|
+
Subagent: `/multitask` (user command, single-level only — not a callable tool)
|
|
76
|
+
MCP limit: 40 tools
|
|
77
|
+
</adapter>
|
|
78
|
+
|
|
79
|
+
<adapter id="antigravity">
|
|
80
|
+
## A. Skill Invocation
|
|
81
|
+
Same trigger keywords as claude-code adapter.
|
|
82
|
+
Skill discovery: LLM-driven (automatic, no slash command needed).
|
|
83
|
+
|
|
84
|
+
## C. Tool Usage
|
|
85
|
+
Use Antigravity tools: `shell` (cmd), `file_read`, `file_write`, MCP plugins
|
|
86
|
+
Interactive: text fallback (TUI-based; no formal AskUserQuestion)
|
|
87
|
+
Skill path: `.agents/skills/<skill>/SKILL.md` (project) or `~/.gemini/antigravity/skills/` (global)
|
|
88
|
+
Note: Gemini CLI deprecated June 18, 2026 — use Antigravity CLI.
|
|
89
|
+
</adapter>
|
|
90
|
+
|
|
91
|
+
<adapter id="codex">
|
|
92
|
+
## A. Skill Invocation
|
|
93
|
+
Same trigger keywords as claude-code adapter.
|
|
94
|
+
|
|
95
|
+
## C. Tool Usage
|
|
96
|
+
Use Codex tools: `container.exec` (sandboxed shell), `apply_patch` (file write), `web_search`
|
|
97
|
+
Interactive: text fallback (TUI Tab/Enter injection)
|
|
98
|
+
Config: `~/.codex/config.toml`
|
|
99
|
+
</adapter>
|
|
100
|
+
|
|
101
|
+
<adapter id="copilot">
|
|
102
|
+
## A. Skill Invocation
|
|
103
|
+
Same trigger keywords as claude-code adapter.
|
|
104
|
+
Discovery: User-driven (`@agent-name` in GitHub Copilot Chat).
|
|
105
|
+
|
|
106
|
+
## C. Tool Usage
|
|
107
|
+
Use Copilot tools: `runCommands` (shell), `read`/`readfile` (read), `edit`/`editFiles` (write),
|
|
108
|
+
`code_search`, `find_references`
|
|
109
|
+
Interactive: `askQuestions` (main agent only — NOT available in subagents; VS Code issue #293745)
|
|
110
|
+
Skill path: `.github/agents/<name>.agent.md`
|
|
111
|
+
</adapter>
|
|
63
112
|
|
|
64
113
|
<scope_policy>
|
|
65
114
|
## ViePilot Namespace Guard (BUG-004)
|
|
@@ -53,14 +53,63 @@ Silent if command unavailable or errors.
|
|
|
53
53
|
</persona_context>
|
|
54
54
|
|
|
55
55
|
|
|
56
|
-
<
|
|
56
|
+
<adapter id="claude-code">
|
|
57
57
|
## A. Skill Invocation
|
|
58
58
|
- Skill được gọi khi user mention `vp-status`, `/vp-status`, "status", "tiến độ", "đang ở đâu"
|
|
59
59
|
- Treat all user text after the skill mention as `{{VP_ARGS}}`
|
|
60
60
|
|
|
61
61
|
## B. Tool Usage
|
|
62
|
-
Use
|
|
63
|
-
|
|
62
|
+
Use Claude Code tools: `Bash` (shell), `Read` (file), `Edit` + `Write` (file write/patch),
|
|
63
|
+
`Grep` (search), `Glob` (file patterns), `LS`, `WebSearch`, `WebFetch`,
|
|
64
|
+
`Agent` (spawn subagent — multi-level nesting supported)
|
|
65
|
+
Interactive: `AskUserQuestion` (deferred — preload via ToolSearch before first call)
|
|
66
|
+
</adapter>
|
|
67
|
+
|
|
68
|
+
<adapter id="cursor-agent">
|
|
69
|
+
## A. Skill Invocation
|
|
70
|
+
Same trigger keywords as claude-code adapter.
|
|
71
|
+
|
|
72
|
+
## C. Tool Usage
|
|
73
|
+
Use Cursor tools: `run_terminal_cmd` (shell), `read_file` (read), `edit_file` (write/edit),
|
|
74
|
+
`grep_search` (search), `web_search`, `codebase_search`, `list_dir`, `file_search`
|
|
75
|
+
Interactive: text list fallback (AskQuestion available in Plan Mode only; Agent Mode = text)
|
|
76
|
+
Subagent: `/multitask` (user command, single-level only — not a callable tool)
|
|
77
|
+
MCP limit: 40 tools
|
|
78
|
+
</adapter>
|
|
79
|
+
|
|
80
|
+
<adapter id="antigravity">
|
|
81
|
+
## A. Skill Invocation
|
|
82
|
+
Same trigger keywords as claude-code adapter.
|
|
83
|
+
Skill discovery: LLM-driven (automatic, no slash command needed).
|
|
84
|
+
|
|
85
|
+
## C. Tool Usage
|
|
86
|
+
Use Antigravity tools: `shell` (cmd), `file_read`, `file_write`, MCP plugins
|
|
87
|
+
Interactive: text fallback (TUI-based; no formal AskUserQuestion)
|
|
88
|
+
Skill path: `.agents/skills/<skill>/SKILL.md` (project) or `~/.gemini/antigravity/skills/` (global)
|
|
89
|
+
Note: Gemini CLI deprecated June 18, 2026 — use Antigravity CLI.
|
|
90
|
+
</adapter>
|
|
91
|
+
|
|
92
|
+
<adapter id="codex">
|
|
93
|
+
## A. Skill Invocation
|
|
94
|
+
Same trigger keywords as claude-code adapter.
|
|
95
|
+
|
|
96
|
+
## C. Tool Usage
|
|
97
|
+
Use Codex tools: `container.exec` (sandboxed shell), `apply_patch` (file write), `web_search`
|
|
98
|
+
Interactive: text fallback (TUI Tab/Enter injection)
|
|
99
|
+
Config: `~/.codex/config.toml`
|
|
100
|
+
</adapter>
|
|
101
|
+
|
|
102
|
+
<adapter id="copilot">
|
|
103
|
+
## A. Skill Invocation
|
|
104
|
+
Same trigger keywords as claude-code adapter.
|
|
105
|
+
Discovery: User-driven (`@agent-name` in GitHub Copilot Chat).
|
|
106
|
+
|
|
107
|
+
## C. Tool Usage
|
|
108
|
+
Use Copilot tools: `runCommands` (shell), `read`/`readfile` (read), `edit`/`editFiles` (write),
|
|
109
|
+
`code_search`, `find_references`
|
|
110
|
+
Interactive: `askQuestions` (main agent only — NOT available in subagents; VS Code issue #293745)
|
|
111
|
+
Skill path: `.github/agents/<name>.agent.md`
|
|
112
|
+
</adapter>
|
|
64
113
|
<scope_policy>
|
|
65
114
|
## ViePilot Namespace Guard (BUG-004)
|
|
66
115
|
- Default mode: only use and reference `vp-*` skills in ViePilot workflows.
|
package/skills/vp-task/SKILL.md
CHANGED
|
@@ -53,14 +53,63 @@ Silent if command unavailable or errors.
|
|
|
53
53
|
</persona_context>
|
|
54
54
|
|
|
55
55
|
|
|
56
|
-
<
|
|
56
|
+
<adapter id="claude-code">
|
|
57
57
|
## A. Skill Invocation
|
|
58
58
|
- Skill được gọi khi user mention `vp-task`, `/vp-task`
|
|
59
59
|
- Treat all user text after the skill mention as `{{VP_ARGS}}`
|
|
60
60
|
|
|
61
61
|
## B. Tool Usage
|
|
62
|
-
Use
|
|
63
|
-
|
|
62
|
+
Use Claude Code tools: `Bash` (shell), `Read` (file), `Edit` + `Write` (file write/patch),
|
|
63
|
+
`Grep` (search), `Glob` (file patterns), `LS`, `WebSearch`, `WebFetch`,
|
|
64
|
+
`Agent` (spawn subagent — multi-level nesting supported)
|
|
65
|
+
Interactive: `AskUserQuestion` (deferred — preload via ToolSearch before first call)
|
|
66
|
+
</adapter>
|
|
67
|
+
|
|
68
|
+
<adapter id="cursor-agent">
|
|
69
|
+
## A. Skill Invocation
|
|
70
|
+
Same trigger keywords as claude-code adapter.
|
|
71
|
+
|
|
72
|
+
## C. Tool Usage
|
|
73
|
+
Use Cursor tools: `run_terminal_cmd` (shell), `read_file` (read), `edit_file` (write/edit),
|
|
74
|
+
`grep_search` (search), `web_search`, `codebase_search`, `list_dir`, `file_search`
|
|
75
|
+
Interactive: text list fallback (AskQuestion available in Plan Mode only; Agent Mode = text)
|
|
76
|
+
Subagent: `/multitask` (user command, single-level only — not a callable tool)
|
|
77
|
+
MCP limit: 40 tools
|
|
78
|
+
</adapter>
|
|
79
|
+
|
|
80
|
+
<adapter id="antigravity">
|
|
81
|
+
## A. Skill Invocation
|
|
82
|
+
Same trigger keywords as claude-code adapter.
|
|
83
|
+
Skill discovery: LLM-driven (automatic, no slash command needed).
|
|
84
|
+
|
|
85
|
+
## C. Tool Usage
|
|
86
|
+
Use Antigravity tools: `shell` (cmd), `file_read`, `file_write`, MCP plugins
|
|
87
|
+
Interactive: text fallback (TUI-based; no formal AskUserQuestion)
|
|
88
|
+
Skill path: `.agents/skills/<skill>/SKILL.md` (project) or `~/.gemini/antigravity/skills/` (global)
|
|
89
|
+
Note: Gemini CLI deprecated June 18, 2026 — use Antigravity CLI.
|
|
90
|
+
</adapter>
|
|
91
|
+
|
|
92
|
+
<adapter id="codex">
|
|
93
|
+
## A. Skill Invocation
|
|
94
|
+
Same trigger keywords as claude-code adapter.
|
|
95
|
+
|
|
96
|
+
## C. Tool Usage
|
|
97
|
+
Use Codex tools: `container.exec` (sandboxed shell), `apply_patch` (file write), `web_search`
|
|
98
|
+
Interactive: text fallback (TUI Tab/Enter injection)
|
|
99
|
+
Config: `~/.codex/config.toml`
|
|
100
|
+
</adapter>
|
|
101
|
+
|
|
102
|
+
<adapter id="copilot">
|
|
103
|
+
## A. Skill Invocation
|
|
104
|
+
Same trigger keywords as claude-code adapter.
|
|
105
|
+
Discovery: User-driven (`@agent-name` in GitHub Copilot Chat).
|
|
106
|
+
|
|
107
|
+
## C. Tool Usage
|
|
108
|
+
Use Copilot tools: `runCommands` (shell), `read`/`readfile` (read), `edit`/`editFiles` (write),
|
|
109
|
+
`code_search`, `find_references`
|
|
110
|
+
Interactive: `askQuestions` (main agent only — NOT available in subagents; VS Code issue #293745)
|
|
111
|
+
Skill path: `.github/agents/<name>.agent.md`
|
|
112
|
+
</adapter>
|
|
64
113
|
<scope_policy>
|
|
65
114
|
## ViePilot Namespace Guard (BUG-004)
|
|
66
115
|
- Default mode: only use and reference `vp-*` skills in ViePilot workflows.
|
|
@@ -53,7 +53,7 @@ Silent if command unavailable or errors.
|
|
|
53
53
|
</persona_context>
|
|
54
54
|
|
|
55
55
|
|
|
56
|
-
<
|
|
56
|
+
<adapter id="claude-code">
|
|
57
57
|
## A. Skill Invocation
|
|
58
58
|
- Skill được gọi khi user mention `vp-ui-components`, `/vp-ui-components`, "ui components", "component library", "21st.dev component"
|
|
59
59
|
- Treat all user text after the skill mention as `{{VP_ARGS}}`
|
|
@@ -62,8 +62,57 @@ Silent if command unavailable or errors.
|
|
|
62
62
|
Prompt user conversationally with numbered list options.
|
|
63
63
|
|
|
64
64
|
## C. Tool Usage
|
|
65
|
-
Use
|
|
66
|
-
|
|
65
|
+
Use Claude Code tools: `Bash` (shell), `Read` (file), `Edit` + `Write` (file write/patch),
|
|
66
|
+
`Grep` (search), `Glob` (file patterns), `LS`, `WebSearch`, `WebFetch`,
|
|
67
|
+
`Agent` (spawn subagent — multi-level nesting supported)
|
|
68
|
+
Interactive: `AskUserQuestion` (deferred — preload via ToolSearch before first call)
|
|
69
|
+
</adapter>
|
|
70
|
+
|
|
71
|
+
<adapter id="cursor-agent">
|
|
72
|
+
## A. Skill Invocation
|
|
73
|
+
Same trigger keywords as claude-code adapter.
|
|
74
|
+
|
|
75
|
+
## C. Tool Usage
|
|
76
|
+
Use Cursor tools: `run_terminal_cmd` (shell), `read_file` (read), `edit_file` (write/edit),
|
|
77
|
+
`grep_search` (search), `web_search`, `codebase_search`, `list_dir`, `file_search`
|
|
78
|
+
Interactive: text list fallback (AskQuestion available in Plan Mode only; Agent Mode = text)
|
|
79
|
+
Subagent: `/multitask` (user command, single-level only — not a callable tool)
|
|
80
|
+
MCP limit: 40 tools
|
|
81
|
+
</adapter>
|
|
82
|
+
|
|
83
|
+
<adapter id="antigravity">
|
|
84
|
+
## A. Skill Invocation
|
|
85
|
+
Same trigger keywords as claude-code adapter.
|
|
86
|
+
Skill discovery: LLM-driven (automatic, no slash command needed).
|
|
87
|
+
|
|
88
|
+
## C. Tool Usage
|
|
89
|
+
Use Antigravity tools: `shell` (cmd), `file_read`, `file_write`, MCP plugins
|
|
90
|
+
Interactive: text fallback (TUI-based; no formal AskUserQuestion)
|
|
91
|
+
Skill path: `.agents/skills/<skill>/SKILL.md` (project) or `~/.gemini/antigravity/skills/` (global)
|
|
92
|
+
Note: Gemini CLI deprecated June 18, 2026 — use Antigravity CLI.
|
|
93
|
+
</adapter>
|
|
94
|
+
|
|
95
|
+
<adapter id="codex">
|
|
96
|
+
## A. Skill Invocation
|
|
97
|
+
Same trigger keywords as claude-code adapter.
|
|
98
|
+
|
|
99
|
+
## C. Tool Usage
|
|
100
|
+
Use Codex tools: `container.exec` (sandboxed shell), `apply_patch` (file write), `web_search`
|
|
101
|
+
Interactive: text fallback (TUI Tab/Enter injection)
|
|
102
|
+
Config: `~/.codex/config.toml`
|
|
103
|
+
</adapter>
|
|
104
|
+
|
|
105
|
+
<adapter id="copilot">
|
|
106
|
+
## A. Skill Invocation
|
|
107
|
+
Same trigger keywords as claude-code adapter.
|
|
108
|
+
Discovery: User-driven (`@agent-name` in GitHub Copilot Chat).
|
|
109
|
+
|
|
110
|
+
## C. Tool Usage
|
|
111
|
+
Use Copilot tools: `runCommands` (shell), `read`/`readfile` (read), `edit`/`editFiles` (write),
|
|
112
|
+
`code_search`, `find_references`
|
|
113
|
+
Interactive: `askQuestions` (main agent only — NOT available in subagents; VS Code issue #293745)
|
|
114
|
+
Skill path: `.github/agents/<name>.agent.md`
|
|
115
|
+
</adapter>
|
|
67
116
|
<scope_policy>
|
|
68
117
|
## ViePilot Namespace Guard (BUG-004)
|
|
69
118
|
- Default mode: only use and reference `vp-*` skills in ViePilot workflows.
|