prizmkit 1.0.142 → 1.0.143

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 (5) hide show
  1. package/bundled/VERSION.json +3 -3
  2. package/bundled/skills/_metadata.json +1 -1
  3. package/bundled/skills/bugfix-pipeline-launcher/SKILL.md +24 -25
  4. package/bundled/skills/dev-pipeline-launcher/SKILL.md +32 -30
  5. package/package.json +1 -1
package/bundled/VERSION.json CHANGED
@@ -1,5 +1,5 @@
1
1
  {
2
- "frameworkVersion": "1.0.142",
3
- "bundledAt": "2026-03-28T23:25:23.889Z",
4
- "bundledFrom": "6c6eed3"
2
+ "frameworkVersion": "1.0.143",
3
+ "bundledAt": "2026-03-28T23:59:01.821Z",
4
+ "bundledFrom": "ea51479"
5
5
  }
package/bundled/skills/_metadata.json CHANGED
@@ -1,5 +1,5 @@
1
1
  {
2
- "version": "1.0.141",
2
+ "version": "1.0.143",
3
3
  "skills": {
4
4
  "prizm-kit": {
5
5
  "description": "Full-lifecycle dev toolkit. Covers spec-driven development, Prizm context docs, code quality, debugging, deployment, and knowledge management.",
package/bundled/skills/bugfix-pipeline-launcher/SKILL.md CHANGED
@@ -113,38 +113,37 @@ Detect user intent from their message, then follow the corresponding workflow:
113
113
  - **(2) Background daemon** — pipeline runs fully detached via `launch-bugfix-daemon.sh`. Survives AI CLI session closure.
114
114
  - **(3) Manual** — display the final assembled commands only. Do not execute anything. User runs them on their own.
115
115
 
116
- 5. **Present configuration options**: After execution mode is chosen, show the remaining options with defaults. Ask the user to confirm or override.
116
+ 5. **Ask configuration options** ⚠️ MANDATORY INTERACTIVE STEP — applies to ALL execution modes (Foreground, Background, AND Manual). You MUST ask the user to configure options and WAIT for their response BEFORE proceeding to step 6. Do NOT skip this step or merge it with step 6.
117
117
 
118
- **Configuration Options:**
118
+ Use `AskUserQuestion` to present the following configuration choices. Each question is a separate selectable option:
119
119
 
120
- | Option | Default | Description |
121
- |--------|---------|-------------|
122
- | **Verbose logging** | On | Detailed AI session logs including tool calls and subagent activity |
123
- | **Max retries** | 3 | Max retry attempts per failed bug |
124
- | **Session timeout** | None | Per-bug timeout in seconds (e.g. `3600` = 1 hour) |
125
- | **Bug filter** | All | Run specific bugs: `B-001:B-005` (range), `B-001,B-003` (list), or mixed `B-001,B-005:B-010` |
120
+ **Question 1 — Verbose logging** (multiSelect: false):
121
+ - On (default) — Detailed AI session logs including tool calls and subagent activity
122
+ - Off — Minimal logging
126
123
 
127
- Default Verbose On.
124
+ **Question 2 — Max retries** (multiSelect: false):
125
+ - 3 (default)
126
+ - 1
127
+ - 5
128
128
 
129
- **Environment variable mapping** (for natural language → env var translation):
129
+ **Question 3 — Session timeout** (multiSelect: false):
130
+ - None (default) — No timeout
131
+ - 30 min — `SESSION_TIMEOUT=1800`
132
+ - 1 hour — `SESSION_TIMEOUT=3600`
133
+ - 2 hours — `SESSION_TIMEOUT=7200`
130
134
 
131
- | User says | Environment variable |
132
- |-----------|---------------------|
133
- | "timeout 2 hours" | `SESSION_TIMEOUT=7200` |
134
- | "max 5 retries" | `MAX_RETRIES=5` |
135
- | "no verbose" / "quiet" | `VERBOSE=0` |
136
- | "heartbeat every 60s" | `HEARTBEAT_INTERVAL=60` |
135
+ Note: Bug filter defaults to all bugs (by severity order). If the user selects "Other" on any option, handle their custom input.
137
136
 
138
- Example presentation to user:
139
- ```
140
- Bugfix pipeline will process N bugs in Foreground mode:
141
- - Verbose: On (subagent detection enabled)
142
- - Max retries: 3
143
- - Timeout: none
144
- - Bugs: all (by severity order)
137
+ **Environment variable mapping** (for translating user responses → env vars):
145
138
 
146
- Want to change any options, or proceed with these defaults?
147
- ```
139
+ | Config choice | Environment variable |
140
+ |-----------|---------------------|
141
+ | Verbose: Off | `VERBOSE=0` |
142
+ | Verbose: On | `VERBOSE=1` |
143
+ | Max retries: N | `MAX_RETRIES=N` |
144
+ | Timeout: value | `SESSION_TIMEOUT=<seconds>` |
145
+
146
+ ⚠️ STOP HERE and wait for user response before continuing to step 6.
148
147
 
149
148
  6. **Show final command**: Assemble the complete command from execution mode + confirmed configuration, and present it to the user.
150
149
 
package/bundled/skills/dev-pipeline-launcher/SKILL.md CHANGED
@@ -133,46 +133,48 @@ Detect user intent from their message, then follow the corresponding workflow:
133
133
  - **(2) Background daemon** — pipeline runs fully detached via `launch-daemon.sh`. Survives AI CLI session closure.
134
134
  - **(3) Manual** — display the final assembled commands only. Do not execute anything. User runs them on their own.
135
135
 
136
- 6. **Present configuration options**: After execution mode is chosen, show the remaining options with defaults. Ask the user to confirm or override.
136
+ 6. **Ask configuration options** ⚠️ MANDATORY INTERACTIVE STEP — applies to ALL execution modes (Foreground, Background, AND Manual). You MUST ask the user to configure options and WAIT for their response BEFORE proceeding to step 7. Do NOT skip this step or merge it with step 7.
137
137
 
138
- **Configuration Options:**
138
+ Use `AskUserQuestion` to present the following configuration choices. Each question is a separate selectable option:
139
139
 
140
- | Option | Default | Description |
141
- |--------|---------|-------------|
142
- | **Critic review** | Off | Adversarial review after planning & implementation. Increases time ~5-10 min/feature |
143
- | **Verbose logging** | On | Detailed AI session logs including tool calls and subagent activity |
144
- | **Max retries** | 3 | Max retry attempts per failed feature |
145
- | **Session timeout** | None | Per-feature timeout in seconds (e.g. `3600` = 1 hour) |
146
- | **Feature filter** | All | Run specific features: `F-001:F-005` (range), `F-001,F-003` (list), or mixed `F-001,F-005:F-010` |
147
- | **Browser verify** | Auto | Run playwright-cli verification for features with `browser_interaction`. Auto = run if playwright-cli installed and features have the field |
140
+ **Question 1 — Critic review** (multiSelect: false):
141
+ - Off (default) — Skip adversarial review
142
+ - On — Enable critic review after planning & implementation (+5-10 min/feature)
148
143
 
149
- Default Verbose On. Default Critic to Off unless features have `estimated_complexity: "high"` or above.
144
+ **Question 2 — Verbose logging** (multiSelect: false):
145
+ - On (default) — Detailed AI session logs including tool calls and subagent activity
146
+ - Off — Minimal logging
150
147
 
151
- **Environment variable mapping** (for natural language → env var translation):
148
+ **Question 3 — Max retries** (multiSelect: false):
149
+ - 3 (default)
150
+ - 1
151
+ - 5
152
152
 
153
- | User says | Environment variable |
153
+ **Question 4 — Session timeout** (multiSelect: false):
154
+ - None (default) — No timeout
155
+ - 30 min — `SESSION_TIMEOUT=1800`
156
+ - 1 hour — `SESSION_TIMEOUT=3600`
157
+ - 2 hours — `SESSION_TIMEOUT=7200`
158
+
159
+ Note: Due to the 4-question limit per `AskUserQuestion` call, Feature filter and Browser verify use their defaults (all features, auto-detect playwright-cli). If the user selects "Other" on any option, handle their custom input.
160
+
161
+ Default Critic to Off unless features have `estimated_complexity: "high"` or above (in which case default to On).
162
+
163
+ **Environment variable mapping** (for translating user responses → env vars):
164
+
165
+ | Config choice | Environment variable |
154
166
  |-----------|---------------------|
155
- | "timeout 2 hours" | `SESSION_TIMEOUT=7200` |
156
- | "max 5 retries" | `MAX_RETRIES=5` |
157
- | "no verbose" / "quiet" | `VERBOSE=0` |
158
- | "heartbeat every 60s" | `HEARTBEAT_INTERVAL=60` |
159
- | "enable critic review" | `ENABLE_CRITIC=true` |
167
+ | Critic: On | `ENABLE_CRITIC=true` |
168
+ | Verbose: Off | `VERBOSE=0` |
169
+ | Verbose: On | `VERBOSE=1` |
170
+ | Max retries: N | `MAX_RETRIES=N` |
171
+ | Timeout: value | `SESSION_TIMEOUT=<seconds>` |
160
172
  | "skip browser verify" | `BROWSER_VERIFY=false` |
161
173
  | "enable browser verify" | `BROWSER_VERIFY=true` |
162
174
 
163
- Example presentation to user:
164
- ```
165
- Pipeline will process N features in Foreground mode:
166
- - Critic: Off
167
- - Verbose: On (subagent detection enabled)
168
- - Max retries: 3
169
- - Timeout: none
170
- - Features: all
171
-
172
- Want to change any options, or proceed with these defaults?
173
- ```
175
+ ⚠️ STOP HERE and wait for user response before continuing to step 7.
174
176
 
175
- 7. **Show final command**: Assemble the complete command from execution mode + confirmed configuration, and present it to the user.
177
+ 7. **Show final command**: After user confirms configuration in step 6, assemble the complete command from execution mode + user-confirmed configuration, and present it to the user.
176
178
 
177
179
  **Foreground command:**
178
180
  ```bash
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "prizmkit",
3
- "version": "1.0.142",
3
+ "version": "1.0.143",
4
4
  "description": "Create a new PrizmKit-powered project with clean initialization — no framework dev files, just what you need.",
5
5
  "type": "module",
6
6
  "bin": {