@codename_inc/spectre 4.0.0 → 5.1.0

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.
@@ -0,0 +1,121 @@
1
+ ---
2
+ name: "ux"
3
+ description: "👻 | Define user flows, components, and UX behavior — generates the UX spec for a feature - primary agent"
4
+ user-invocable: true
5
+ ---
6
+
7
+ # ux
8
+
9
+ ## Input Handling
10
+
11
+ Treat the current command arguments as this workflow's input. When invoked from a slash command, use the forwarded `$ARGUMENTS` value.
12
+
13
+ # ux: Define Exactly How the Feature Works
14
+
15
+ Transform product requirements into a definitive behavioral specification. Two stages: align on user flows, then generate detailed spec. Output: `ux.md` ready for implementation.
16
+
17
+ <ARGUMENTS> $ARGUMENTS </ARGUMENTS>
18
+
19
+ ---
20
+
21
+ # STAGE 1: Flow Discovery & Alignment
22
+
23
+ **Goal**: Align on HOW the feature works before specifying details.
24
+
25
+ ## Step 1 — Understand the Feature
26
+
27
+ 1. **Read scope and requirements** in this precedence (read whichever exist FULLY, no offset/limit):
28
+ - `docs/tasks/{branch}/concepts/scope.md` — the canonical scope doc (preferred)
29
+ - `docs/tasks/{branch}/specs/prd.md` — if a PRD was generated separately
30
+ - `docs/tasks/{branch}/task_summary.md` — if present
31
+ - **If none exist** → ask the user for scope context (or recommend `scope` first) before proceeding.
32
+ 2. **Research patterns**: Dispatch `@patterns` to find existing screens/components similar to what we're building. Note conventions, reusable elements, and any design tokens.
33
+ 3. **Identify user segments**: List the user segments this feature serves — first-time vs returning, anonymous vs signed-in, free vs paid, role-based variants. UX often diverges across segments and missing this is a common cause of rework.
34
+ 4. **Identify journeys**: List user goals, entry points, and completion states.
35
+
36
+ ## Step 2 — Present User Flows
37
+
38
+ Write each flow as a narrative walkthrough.
39
+
40
+ **Per flow include**: Goal, Entry point, Journey steps (User sees → User does → System responds), Decision points with branches, Success state, Questions where ambiguity exists.
41
+
42
+ **Per user segment**: Call out where flows diverge (e.g., "First-time users see X tour; returning users skip directly to Y").
43
+
44
+ After writing all flows, propose a specific take rather than asking open-ended:
45
+
46
+ > **User Flows — Proposed**
47
+ >
48
+ > I've mapped {N} flows across {M} user segments: {list with one-line summaries}
49
+ >
50
+ > **Key segmentation calls**: [where flows diverge by user state and why]
51
+ >
52
+ > Push back on anything wrong, missing, or over-/under-segmented. Reply with feedback or **"Flows approved"** to proceed.
53
+
54
+ **Wait for approval. If feedback → revise and re-present. If approved → Stage 2.**
55
+
56
+ ---
57
+
58
+ # STAGE 2: Detailed Specification
59
+
60
+ **Gate**: Only proceed after explicit flow approval.
61
+
62
+ ## Step 3 — Clarify Remaining Details
63
+
64
+ Review approved flows for gaps: component behaviors, edge cases, state definitions, segment variants.
65
+
66
+ If significant gaps, ask 3–5 targeted questions (empty states, error handling, loading, limits, segment differences). Save to `clarifications/ux_clarifications_{timestamp}.md`, prompt user to read, incorporate answers.
67
+
68
+ ## Step 4 — Write the Specification
69
+
70
+ Generate complete spec with these sections:
71
+
72
+ ### Required Sections
73
+
74
+ 1. **Overview** — What this feature is, problem it solves, primary user goal (1 paragraph)
75
+ 2. **User Segments** — Each segment served, what's different about their UX (e.g., first-time onboarding, role-based permissions, free vs paid limits, anon vs signed-in)
76
+ 3. **Screens** — Every screen: name, purpose (1 line), navigation relationships
77
+ 4. **Flows** — Formalized from Stage 1 with alternate paths (validation fail, cancel, network error). Include per-segment branches where they diverge.
78
+ 5. **Layouts** — Per screen: header/main/footer structure + responsive behavior (desktop >1024, tablet 768–1024, mobile <768)
79
+ 6. **Components** — Each interactive element: purpose, location, applicable states (see State Vocabulary below)
80
+ 7. **Interactions** — Table format: Element | Action | Result (exhaustive)
81
+ 8. **States** — Table format: State | Trigger | Appearance | Available Actions
82
+ 9. **Content** — Exact copy: page titles, buttons, empty states, error messages, confirmation dialogs
83
+ 10. **Edge Cases** — Limits/boundaries, null/long data handling, permissions, offline/network failures, segment-specific edge cases
84
+ 11. **Accessibility** — Tab order, keyboard actions (Enter/Space/Escape), screen reader announcements, focus management
85
+
86
+ ### State Vocabulary
87
+
88
+ Use these state categories where applicable. Not every component needs every state — pick what's relevant for the feature.
89
+
90
+ - **Visual states** (per interactive element): default, hover, focus, active/pressed, disabled
91
+ - **Data states** (per data view): empty, loading, partial-loaded, loaded, error, stale/refreshing
92
+ - **Form states**: pristine, dirty, touched, submitting, submitted-success, submitted-error, validation-error per field
93
+ - **Selection states**: none, single, multi, partial-selection, all-selected
94
+ - **Sync states** (collaborative or async UI): optimistic, pending, conflict, resolved
95
+ - **Network states** (where relevant): online, offline, reconnecting
96
+
97
+ Save to `docs/tasks/{branch}/ux.md`
98
+
99
+ Prompt:
100
+
101
+ > **UX Specification Complete**
102
+ >
103
+ > Written to `{path}`. Please review: Any behaviors wrong or missing? Edge cases not covered? Segment differences captured?
104
+ >
105
+ > **Want a prototype to validate visually before approving?** `prototype` will render this spec (high-fi, no synthesis) and flag assumptions where I had to fill in details — catches issues prose review misses. Reply `prototype` to run it now.
106
+ >
107
+ > Otherwise, reply with feedback, or **"Approved"** to finalize.
108
+
109
+ **Wait for approval, feedback, or prototype request.** If user replies `prototype`, invoke `prototype` (the post-ux mode auto-detects the complete ux.md). Once prototype completes and any spec updates from filled assumptions are applied, return here for final approval.
110
+
111
+ ## Step 5 — Handoff
112
+
113
+ Confirm completion with summary: screens specified, segments addressed, flows documented, components with states, edge cases and accessibility covered.
114
+
115
+ Read `.spectre/next_steps_guide.md` and render Next Steps footer:
116
+
117
+ ```
118
+ Next Steps | Phase: Scope | Status: UX Complete
119
+ Recommendation: {contextual next action — if no prototype was generated, suggest prototype to validate the spec visually before /plan}
120
+ Options: prototype (validate spec visually), create_plan, create_tasks, tdd
121
+ ```
@@ -1,100 +0,0 @@
1
- ---
2
- name: ux_spec
3
- description: Define the User Flows and generate a UX Spec - primary agent
4
- user-invocable: true
5
- ---
6
-
7
- # ux_spec
8
-
9
- ## Input Handling
10
-
11
- Treat the current command arguments as this workflow's input. When invoked from a slash command, use the forwarded `$ARGUMENTS` value.
12
-
13
- # ux_spec: Define Exactly How the Feature Works
14
-
15
- Transform product requirements into a definitive behavioral specification. Two stages: align on user flows, then generate detailed spec. Output: `ux.md` ready for implementation.
16
-
17
- <ARGUMENTS> $ARGUMENTS </ARGUMENTS>
18
-
19
- ---
20
-
21
- # STAGE 1: Flow Discovery & Alignment
22
-
23
- **Goal**: Align on HOW the feature works before specifying details.
24
-
25
- ## Step 1 — Understand the Feature
26
-
27
- 1. **Read requirements**: `docs/tasks/{branch}/task_summary.md` and `docs/tasks/{branch}/specs/prd.md`
28
- 2. **Research patterns**: Find existing screens/components similar to what we're building, note conventions
29
- 3. **Identify journeys**: List user goals, entry points, and completion states
30
-
31
- ## Step 2 — Present User Flows
32
-
33
- Write each flow as a narrative walkthrough:
34
-
35
- **Per flow include**: Goal, Entry point, Journey steps (User sees → User does → System responds), Decision points with branches, Success state, Questions where ambiguity exists
36
-
37
- After writing all flows, prompt:
38
-
39
- > **User Flows for Review**
40
- >
41
- > I've mapped {N} flows: {list with one-line summaries}
42
- >
43
- > Please review: Are these the right flows? Any missing? Do journeys feel right? Answer flagged questions.
44
- >
45
- > Reply with feedback, or **"Flows approved"** to proceed.
46
-
47
- **Wait for approval. If feedback → revise and re-present. If approved → Stage 2.**
48
-
49
- ---
50
-
51
- # STAGE 2: Detailed Specification
52
-
53
- **Gate**: Only proceed after explicit flow approval.
54
-
55
- ## Step 3 — Clarify Remaining Details
56
-
57
- Review approved flows for gaps: component behaviors, edge cases, state definitions.
58
-
59
- If significant gaps, ask 3-5 targeted questions (empty states, error handling, loading, limits). Save to `clarifications/ux_clarifications_{timestamp}.md`, prompt user to read, incorporate answers.
60
-
61
- ## Step 4 — Write the Specification
62
-
63
- Generate complete spec with these sections:
64
-
65
- ### Required Sections
66
-
67
- 1. **Overview** — What this feature is, problem it solves, primary user goal (1 paragraph)
68
- 2. **Screens** — Every screen: name, purpose (1 line), navigation relationships
69
- 3. **Flows** — Formalized from Stage 1 with alternate paths (validation fail, cancel, network error)
70
- 4. **Layouts** — Per screen: header/main/footer structure + responsive behavior (desktop >1024, tablet 768-1024, mobile <768)
71
- 5. **Components** — Each interactive element: purpose, location, states (default, hover, active, disabled, loading, error)
72
- 6. **Interactions** — Table format: Element | Action | Result (exhaustive)
73
- 7. **States** — Table format: State | Trigger | Appearance | Available Actions (empty, loading, loaded, error)
74
- 8. **Content** — Exact copy: page titles, buttons, empty states, error messages, confirmation dialogs
75
- 9. **Edge Cases** — Limits/boundaries, null/long data handling, permissions, offline/network failures
76
- 10. **Accessibility** — Tab order, keyboard actions (Enter/Space/Escape), screen reader announcements, focus management
77
-
78
- Save to `docs/tasks/{branch}/ux.md`
79
-
80
- Prompt:
81
-
82
- > **UX Specification Complete**
83
- >
84
- > Written to `{path}`. Please review: Any behaviors wrong or missing? Edge cases not covered?
85
- >
86
- > Reply with feedback, or **"Approved"** to finalize.
87
-
88
- **Wait for approval.**
89
-
90
- ## Step 5 — Handoff
91
-
92
- Confirm completion with summary: screens specified, flows documented, components with states, edge cases and accessibility covered.
93
-
94
- Read `.spectre/next_steps_guide.md` and render Next Steps footer:
95
-
96
- ```
97
- Next Steps | Phase: Scope | Status: UX Complete
98
- Recommendation: {contextual next action}
99
- Options: /create_plan, /create_tasks, /tdd
100
- ```
@@ -1,100 +0,0 @@
1
- ---
2
- name: "ux_spec"
3
- description: "Define the User Flows and generate a UX Spec - primary agent"
4
- user-invocable: true
5
- ---
6
-
7
- # ux_spec
8
-
9
- ## Input Handling
10
-
11
- Treat the current command arguments as this workflow's input. When invoked from a slash command, use the forwarded `$ARGUMENTS` value.
12
-
13
- # ux_spec: Define Exactly How the Feature Works
14
-
15
- Transform product requirements into a definitive behavioral specification. Two stages: align on user flows, then generate detailed spec. Output: `ux.md` ready for implementation.
16
-
17
- <ARGUMENTS> $ARGUMENTS </ARGUMENTS>
18
-
19
- ---
20
-
21
- # STAGE 1: Flow Discovery & Alignment
22
-
23
- **Goal**: Align on HOW the feature works before specifying details.
24
-
25
- ## Step 1 — Understand the Feature
26
-
27
- 1. **Read requirements**: `docs/tasks/{branch}/task_summary.md` and `docs/tasks/{branch}/specs/prd.md`
28
- 2. **Research patterns**: Find existing screens/components similar to what we're building, note conventions
29
- 3. **Identify journeys**: List user goals, entry points, and completion states
30
-
31
- ## Step 2 — Present User Flows
32
-
33
- Write each flow as a narrative walkthrough:
34
-
35
- **Per flow include**: Goal, Entry point, Journey steps (User sees → User does → System responds), Decision points with branches, Success state, Questions where ambiguity exists
36
-
37
- After writing all flows, prompt:
38
-
39
- > **User Flows for Review**
40
- >
41
- > I've mapped {N} flows: {list with one-line summaries}
42
- >
43
- > Please review: Are these the right flows? Any missing? Do journeys feel right? Answer flagged questions.
44
- >
45
- > Reply with feedback, or **"Flows approved"** to proceed.
46
-
47
- **Wait for approval. If feedback → revise and re-present. If approved → Stage 2.**
48
-
49
- ---
50
-
51
- # STAGE 2: Detailed Specification
52
-
53
- **Gate**: Only proceed after explicit flow approval.
54
-
55
- ## Step 3 — Clarify Remaining Details
56
-
57
- Review approved flows for gaps: component behaviors, edge cases, state definitions.
58
-
59
- If significant gaps, ask 3-5 targeted questions (empty states, error handling, loading, limits). Save to `clarifications/ux_clarifications_{timestamp}.md`, prompt user to read, incorporate answers.
60
-
61
- ## Step 4 — Write the Specification
62
-
63
- Generate complete spec with these sections:
64
-
65
- ### Required Sections
66
-
67
- 1. **Overview** — What this feature is, problem it solves, primary user goal (1 paragraph)
68
- 2. **Screens** — Every screen: name, purpose (1 line), navigation relationships
69
- 3. **Flows** — Formalized from Stage 1 with alternate paths (validation fail, cancel, network error)
70
- 4. **Layouts** — Per screen: header/main/footer structure + responsive behavior (desktop >1024, tablet 768-1024, mobile <768)
71
- 5. **Components** — Each interactive element: purpose, location, states (default, hover, active, disabled, loading, error)
72
- 6. **Interactions** — Table format: Element | Action | Result (exhaustive)
73
- 7. **States** — Table format: State | Trigger | Appearance | Available Actions (empty, loading, loaded, error)
74
- 8. **Content** — Exact copy: page titles, buttons, empty states, error messages, confirmation dialogs
75
- 9. **Edge Cases** — Limits/boundaries, null/long data handling, permissions, offline/network failures
76
- 10. **Accessibility** — Tab order, keyboard actions (Enter/Space/Escape), screen reader announcements, focus management
77
-
78
- Save to `docs/tasks/{branch}/ux.md`
79
-
80
- Prompt:
81
-
82
- > **UX Specification Complete**
83
- >
84
- > Written to `{path}`. Please review: Any behaviors wrong or missing? Edge cases not covered?
85
- >
86
- > Reply with feedback, or **"Approved"** to finalize.
87
-
88
- **Wait for approval.**
89
-
90
- ## Step 5 — Handoff
91
-
92
- Confirm completion with summary: screens specified, flows documented, components with states, edge cases and accessibility covered.
93
-
94
- Read `.spectre/next_steps_guide.md` and render Next Steps footer:
95
-
96
- ```
97
- Next Steps | Phase: Scope | Status: UX Complete
98
- Recommendation: {contextual next action}
99
- Options: /create_plan, /create_tasks, /tdd
100
- ```