prizmkit 1.1.41 → 1.1.42
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/bundled/VERSION.json +3 -3
- package/bundled/dev-pipeline/scripts/generate-bootstrap-prompt.py +1 -1
- package/bundled/dev-pipeline/scripts/generate-bugfix-prompt.py +1 -1
- package/bundled/dev-pipeline/scripts/generate-recovery-prompt.py +1 -1
- package/bundled/dev-pipeline/scripts/generate-refactor-prompt.py +1 -1
- package/bundled/dev-pipeline/templates/bootstrap-prompt.md +1 -1
- package/bundled/dev-pipeline/templates/bugfix-bootstrap-prompt.md +1 -1
- package/bundled/dev-pipeline/templates/refactor-bootstrap-prompt.md +1 -1
- package/bundled/skills/_metadata.json +1 -1
- package/bundled/skills/bugfix-pipeline-launcher/SKILL.md +7 -0
- package/bundled/skills/feature-pipeline-launcher/SKILL.md +7 -0
- package/bundled/skills/prizmkit-committer/SKILL.md +2 -0
- package/bundled/skills/refactor-pipeline-launcher/SKILL.md +7 -0
- package/package.json +1 -1
package/bundled/VERSION.json
CHANGED
|
@@ -450,7 +450,7 @@ BUGFIX_STEPS = [
|
|
|
450
450
|
".prizmkit/bugfix/{slug}/plan.md"]),
|
|
451
451
|
("prizmkit-implement", "Implement Fix", []),
|
|
452
452
|
("prizmkit-code-review", "Code Review", []),
|
|
453
|
-
("prizmkit-committer", "Commit", []),
|
|
453
|
+
("prizmkit-committer", "Commit", ["--headless"]),
|
|
454
454
|
("bug-report", "Generate Fix Report",
|
|
455
455
|
[".prizmkit/bugfix/{slug}/fix-report.md"]),
|
|
456
456
|
]
|
|
@@ -117,7 +117,7 @@ Commit the fix and finalize:
|
|
|
117
117
|
1. Run `/prizmkit-retrospective` (structural sync only — update file counts,
|
|
118
118
|
interfaces, dependencies in .prizm-docs/)
|
|
119
119
|
2. Stage all changed files explicitly (NEVER use `git add -A` or `git add .`)
|
|
120
|
-
3. Run `/prizmkit-committer` with commit prefix `fix(<scope>): <description>`
|
|
120
|
+
3. Run `/prizmkit-committer --headless` with commit prefix `fix(<scope>): <description>`
|
|
121
121
|
4. Verify working tree is clean: `git status --short`
|
|
122
122
|
5. Write `fix-report.md` to `.prizmkit/bugfix/{bug_id}/fix-report.md` with:
|
|
123
123
|
- Root cause summary
|
|
@@ -40,7 +40,7 @@ REFACTOR_STEPS = [
|
|
|
40
40
|
("prizmkit-code-review", "Review — Code Review & Behavior Verification",
|
|
41
41
|
[".prizmkit/refactor/{slug}/review-report.md"]),
|
|
42
42
|
("prizmkit-committer", "Commit",
|
|
43
|
-
[]),
|
|
43
|
+
["--headless"]),
|
|
44
44
|
("refactor-report", "Generate Refactor Report",
|
|
45
45
|
[".prizmkit/refactor/{slug}/refactor-report.md"]),
|
|
46
46
|
]
|
|
@@ -36,7 +36,7 @@ Infer what needs to be done from the feature context above and follow the standa
|
|
|
36
36
|
|
|
37
37
|
6. **Retrospective**: Run `/prizmkit-retrospective` to sync `.prizm-docs/` with code changes.
|
|
38
38
|
|
|
39
|
-
7. **Commit**: Run `/prizmkit-committer` to commit all changes. Do NOT push.
|
|
39
|
+
7. **Commit**: Run `/prizmkit-committer --headless` to commit all changes. Do NOT push.
|
|
40
40
|
|
|
41
41
|
### Critical Rules
|
|
42
42
|
|
|
@@ -240,7 +240,7 @@ git add <specific-files-modified>
|
|
|
240
240
|
git add .prizm-docs/
|
|
241
241
|
```
|
|
242
242
|
|
|
243
|
-
**d.** Run `/prizmkit-committer`:
|
|
243
|
+
**d.** Run `/prizmkit-committer --headless`:
|
|
244
244
|
- Commit message prefix: `fix({{FIX_SCOPE}}): {{BUG_TITLE}}`
|
|
245
245
|
- Include both fix code and reproduction test
|
|
246
246
|
- Do NOT push
|
|
@@ -235,7 +235,7 @@ Include browser verification approach in plan.md:
|
|
|
235
235
|
|
|
236
236
|
1. Run `/prizmkit-retrospective` (full sync — Job 1 + Job 2) to update `.prizm-docs/` with structural changes
|
|
237
237
|
|
|
238
|
-
2. Run `/prizmkit-committer` with:
|
|
238
|
+
2. Run `/prizmkit-committer --headless` with:
|
|
239
239
|
- Commit message: `refactor({{REFACTOR_ID}}): {{REFACTOR_TITLE}}`
|
|
240
240
|
- Include all refactored files and any new/updated tests
|
|
241
241
|
- Do NOT push (user will push manually)
|
|
@@ -121,6 +121,13 @@ Detect user intent from their message, then follow the corresponding workflow:
|
|
|
121
121
|
|
|
122
122
|
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.
|
|
123
123
|
|
|
124
|
+
⛔ **HARD STOP**: You MUST call `AskUserQuestion` with the questions below and WAIT for the user's response. You MUST NOT:
|
|
125
|
+
- Skip this step and jump to the next step
|
|
126
|
+
- Merge this step and the next step into one response
|
|
127
|
+
- Assume default values and show the command without asking
|
|
128
|
+
- Show the command as text and ask "ready?" without presenting the options
|
|
129
|
+
If you find yourself writing the final command before the user has answered these questions, STOP — you are violating this rule.
|
|
130
|
+
|
|
124
131
|
Use `AskUserQuestion` to present the following configuration choices. Each question is a separate selectable option:
|
|
125
132
|
|
|
126
133
|
**Question 1 — Verbose logging** (multiSelect: false):
|
|
@@ -138,6 +138,13 @@ Detect user intent from their message, then follow the corresponding workflow:
|
|
|
138
138
|
|
|
139
139
|
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.
|
|
140
140
|
|
|
141
|
+
⛔ **HARD STOP**: You MUST call `AskUserQuestion` with the 4 questions below and WAIT for the user's response. You MUST NOT:
|
|
142
|
+
- Skip this step and jump to step 7
|
|
143
|
+
- Merge step 6 and step 7 into one response
|
|
144
|
+
- Assume default values and show the command without asking
|
|
145
|
+
- Show the command as text and ask "ready?" without presenting the options
|
|
146
|
+
If you find yourself writing the final command before the user has answered these questions, STOP — you are violating this rule.
|
|
147
|
+
|
|
141
148
|
Use `AskUserQuestion` to present the following configuration choices. Each question is a separate selectable option:
|
|
142
149
|
|
|
143
150
|
**Question 1 — Critic review** (multiSelect: false):
|
|
@@ -66,6 +66,8 @@ Ask user: "Push to remote?"
|
|
|
66
66
|
- Yes: `git push`
|
|
67
67
|
- No: Stop
|
|
68
68
|
|
|
69
|
+
**Headless mode**: If the skill was invoked with `--headless` in the args (e.g., `/prizmkit-committer --headless feat(F-001): ...`), **SKIP this step entirely**. Do NOT ask the question. Do NOT push. Stop after Step 5 verification. Headless mode is used by autonomous pipeline sessions where there is no human to answer interactive prompts.
|
|
70
|
+
|
|
69
71
|
## Example
|
|
70
72
|
|
|
71
73
|
**Feature commit:**
|
|
@@ -139,6 +139,13 @@ Detect user intent from their message, then follow the corresponding workflow:
|
|
|
139
139
|
|
|
140
140
|
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.
|
|
141
141
|
|
|
142
|
+
⛔ **HARD STOP**: You MUST call `AskUserQuestion` with the questions below and WAIT for the user's response. You MUST NOT:
|
|
143
|
+
- Skip this step and jump to step 7
|
|
144
|
+
- Merge step 6 and step 7 into one response
|
|
145
|
+
- Assume default values and show the command without asking
|
|
146
|
+
- Show the command as text and ask "ready?" without presenting the options
|
|
147
|
+
If you find yourself writing the final command before the user has answered these questions, STOP — you are violating this rule.
|
|
148
|
+
|
|
142
149
|
Use `AskUserQuestion` to present the following configuration choices. Each question is a separate selectable option:
|
|
143
150
|
|
|
144
151
|
**Question 1 — Verbose logging** (multiSelect: false):
|