cc-dev-template 0.1.81 → 0.1.82
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/bin/install.js +10 -1
- package/package.json +1 -1
- package/src/agents/objective-researcher.md +52 -0
- package/src/agents/question-generator.md +70 -0
- package/src/scripts/restrict-to-spec-dir.sh +23 -0
- package/src/skills/ship/SKILL.md +46 -0
- package/src/skills/ship/references/step-1-intent.md +50 -0
- package/src/skills/ship/references/step-2-questions.md +42 -0
- package/src/skills/ship/references/step-3-research.md +44 -0
- package/src/skills/ship/references/step-4-design.md +70 -0
- package/src/skills/ship/references/step-5-spec.md +86 -0
- package/src/skills/ship/references/step-6-tasks.md +83 -0
- package/src/skills/ship/references/step-7-implement.md +61 -0
- package/src/skills/ship/references/step-8-reflect.md +21 -0
- package/src/skills/execute-spec/SKILL.md +0 -40
- package/src/skills/execute-spec/references/phase-1-hydrate.md +0 -74
- package/src/skills/execute-spec/references/phase-2-build.md +0 -65
- package/src/skills/execute-spec/references/phase-3-validate.md +0 -73
- package/src/skills/execute-spec/references/phase-4-triage.md +0 -79
- package/src/skills/execute-spec/references/phase-5-reflect.md +0 -32
- package/src/skills/research/SKILL.md +0 -14
- package/src/skills/research/references/step-1-check-existing.md +0 -25
- package/src/skills/research/references/step-2-conduct-research.md +0 -65
- package/src/skills/research/references/step-3-reflect.md +0 -29
- package/src/skills/spec-interview/SKILL.md +0 -17
- package/src/skills/spec-interview/references/critic-prompt.md +0 -140
- package/src/skills/spec-interview/references/pragmatist-prompt.md +0 -76
- package/src/skills/spec-interview/references/researcher-prompt.md +0 -46
- package/src/skills/spec-interview/references/step-1-opening.md +0 -78
- package/src/skills/spec-interview/references/step-2-ideation.md +0 -73
- package/src/skills/spec-interview/references/step-3-ui-ux.md +0 -83
- package/src/skills/spec-interview/references/step-4-deep-dive.md +0 -137
- package/src/skills/spec-interview/references/step-5-research-needs.md +0 -53
- package/src/skills/spec-interview/references/step-6-verification.md +0 -89
- package/src/skills/spec-interview/references/step-7-finalize.md +0 -60
- package/src/skills/spec-interview/references/step-8-reflect.md +0 -32
- package/src/skills/spec-review/SKILL.md +0 -91
- package/src/skills/spec-sanity-check/SKILL.md +0 -82
- package/src/skills/spec-to-tasks/SKILL.md +0 -24
- package/src/skills/spec-to-tasks/references/step-1-identify-spec.md +0 -39
- package/src/skills/spec-to-tasks/references/step-2-explore.md +0 -43
- package/src/skills/spec-to-tasks/references/step-3-generate.md +0 -67
- package/src/skills/spec-to-tasks/references/step-4-review.md +0 -90
- package/src/skills/spec-to-tasks/references/step-5-reflect.md +0 -22
- package/src/skills/spec-to-tasks/templates/task.md +0 -30
- package/src/skills/task-review/SKILL.md +0 -18
- package/src/skills/task-review/references/checklist.md +0 -153
|
@@ -1,153 +0,0 @@
|
|
|
1
|
-
# Task Review Checklist
|
|
2
|
-
|
|
3
|
-
Evaluate each area. Fix every issue you find by editing the task files directly. Note what you found and fixed:
|
|
4
|
-
- **Critical**: Must fix — fix immediately
|
|
5
|
-
- **Warning**: Should fix — fix now
|
|
6
|
-
- **Note**: Minor suggestion — fix if straightforward
|
|
7
|
-
|
|
8
|
-
## 1. Coverage
|
|
9
|
-
|
|
10
|
-
Compare acceptance criteria in the spec to tasks generated.
|
|
11
|
-
|
|
12
|
-
**Check:**
|
|
13
|
-
- [ ] Every acceptance criterion has exactly one corresponding task
|
|
14
|
-
- [ ] No criteria were skipped or forgotten
|
|
15
|
-
- [ ] No phantom tasks that don't map to a criterion
|
|
16
|
-
|
|
17
|
-
**How to verify:**
|
|
18
|
-
List each criterion from the spec's Acceptance Criteria section. For each, find the matching task file. Flag any orphans in either direction.
|
|
19
|
-
|
|
20
|
-
## 2. Dependency Order
|
|
21
|
-
|
|
22
|
-
Tasks should be sequenced so each can be completed without waiting on later tasks.
|
|
23
|
-
|
|
24
|
-
**Check:**
|
|
25
|
-
- [ ] Task file names sort in valid execution order (T001, T002, etc.)
|
|
26
|
-
- [ ] Each task's `depends_on` references only earlier tasks
|
|
27
|
-
- [ ] No circular dependencies
|
|
28
|
-
- [ ] Foundation work comes before features that use it
|
|
29
|
-
|
|
30
|
-
**Common issues:**
|
|
31
|
-
- API route task before the service it calls
|
|
32
|
-
- UI component before the API it fetches from
|
|
33
|
-
- Test file before the code it tests (tests should be in same task as code)
|
|
34
|
-
|
|
35
|
-
## 3. File Plausibility
|
|
36
|
-
|
|
37
|
-
Files listed in each task should make sense for the project.
|
|
38
|
-
|
|
39
|
-
**Check:**
|
|
40
|
-
- [ ] File paths follow project conventions (use Explorer if unsure)
|
|
41
|
-
- [ ] Files to modify actually exist in the codebase
|
|
42
|
-
- [ ] Files to create are in appropriate directories
|
|
43
|
-
- [ ] No duplicate files across tasks (each file appears in exactly one task)
|
|
44
|
-
|
|
45
|
-
**How to verify:**
|
|
46
|
-
For files to modify, confirm they exist. For files to create, confirm the parent directory exists and the naming follows conventions.
|
|
47
|
-
|
|
48
|
-
## 4. Verification Executability
|
|
49
|
-
|
|
50
|
-
Each task's verification method must be concrete and runnable.
|
|
51
|
-
|
|
52
|
-
**Check:**
|
|
53
|
-
- [ ] Verification is a specific command or script, not vague prose
|
|
54
|
-
- [ ] Test file paths exist or will be created by the task
|
|
55
|
-
- [ ] agent-browser commands reference real routes/elements
|
|
56
|
-
- [ ] No "manually verify" without clear steps
|
|
57
|
-
|
|
58
|
-
**Red flags:**
|
|
59
|
-
- "Verify it works correctly"
|
|
60
|
-
- "Check that the feature functions"
|
|
61
|
-
- Test commands for files not listed in the task
|
|
62
|
-
|
|
63
|
-
## 5. Verification Completeness
|
|
64
|
-
|
|
65
|
-
Each task's verification must test ALL behaviors mentioned in its criterion.
|
|
66
|
-
|
|
67
|
-
**Check:**
|
|
68
|
-
- [ ] Read the criterion text carefully - identify every distinct behavior or edge case mentioned
|
|
69
|
-
- [ ] For each behavior, confirm there's a corresponding verification step
|
|
70
|
-
- [ ] Flag any behaviors in the criterion that have no verification
|
|
71
|
-
|
|
72
|
-
**How to verify:**
|
|
73
|
-
For each task, extract bullet points from the criterion. For each bullet, find the matching verification step. If a behavior is mentioned but not tested, that's a Critical issue.
|
|
74
|
-
|
|
75
|
-
**Common gaps:**
|
|
76
|
-
- Criterion mentions "X persists across refresh" but verification doesn't test refresh
|
|
77
|
-
- Criterion mentions "handles edge case Y" but verification only tests happy path
|
|
78
|
-
- Criterion mentions animation/timing but verification can't test it (should note "Manual test required")
|
|
79
|
-
|
|
80
|
-
## 6. Dependency Completeness
|
|
81
|
-
|
|
82
|
-
Dependencies must be complete, not just valid.
|
|
83
|
-
|
|
84
|
-
**Check:**
|
|
85
|
-
- [ ] If task X modifies a file, check if another task creates it - that task must be in X's depends_on
|
|
86
|
-
- [ ] If task X uses a component/function/route, check if another task creates it - that task must be in X's depends_on
|
|
87
|
-
- [ ] If task X requires context from task Y (e.g., branding, layout, shared state), Y must be in X's depends_on
|
|
88
|
-
|
|
89
|
-
**How to verify:**
|
|
90
|
-
For each task, look at its Files section. For each "modify" entry, search other tasks for where that file is created. If found, verify the creating task is in depends_on. Also check the criterion for implicit dependencies (e.g., "shows branding" implies depending on the branding task).
|
|
91
|
-
|
|
92
|
-
**Common gaps:**
|
|
93
|
-
- Task uses a layout but doesn't depend on the task that configures the layout
|
|
94
|
-
- Task modifies shared state but doesn't depend on the task that creates the context
|
|
95
|
-
- Task assumes a feature exists but the feature is created by a later task
|
|
96
|
-
|
|
97
|
-
## 7. Task Scope
|
|
98
|
-
|
|
99
|
-
Each task should be appropriately sized for the coder→QA loop.
|
|
100
|
-
|
|
101
|
-
**Check:**
|
|
102
|
-
- [ ] No task touches more than ~10 files (consider splitting)
|
|
103
|
-
- [ ] No trivially small tasks that could merge with related work
|
|
104
|
-
- [ ] Each task produces a verifiable outcome, not just "creates a file"
|
|
105
|
-
|
|
106
|
-
## 8. Consistency
|
|
107
|
-
|
|
108
|
-
Cross-check task files against each other and the spec.
|
|
109
|
-
|
|
110
|
-
**Check:**
|
|
111
|
-
- [ ] Task titles match or closely reflect the acceptance criterion
|
|
112
|
-
- [ ] Status is `pending` for all new tasks
|
|
113
|
-
- [ ] Frontmatter format is consistent across all task files
|
|
114
|
-
- [ ] Implementation Notes and Review Notes sections exist (empty is fine)
|
|
115
|
-
|
|
116
|
-
## 9. Component Consolidation
|
|
117
|
-
|
|
118
|
-
Scan for tasks that create structurally similar files.
|
|
119
|
-
|
|
120
|
-
**Check:**
|
|
121
|
-
- [ ] No two tasks create components with similar names, purposes, or overlapping structure
|
|
122
|
-
- [ ] Shared patterns (cards, forms, list items, layout sections) use a single shared component with configuration, not separate implementations
|
|
123
|
-
- [ ] Utility functions or services with similar logic are consolidated
|
|
124
|
-
|
|
125
|
-
**How to verify:**
|
|
126
|
-
Compare files-to-create across all tasks. Group by similarity (naming patterns, structural role, data shape). When two or more tasks create similar files, flag for consolidation.
|
|
127
|
-
|
|
128
|
-
**Common issues:**
|
|
129
|
-
- Three "card" components for different pages that differ only by displayed fields
|
|
130
|
-
- Two form components with nearly identical validation and submission logic
|
|
131
|
-
- Repeated layout patterns that could be a shared template with slots/children
|
|
132
|
-
|
|
133
|
-
---
|
|
134
|
-
|
|
135
|
-
## Review and Fix Loop
|
|
136
|
-
|
|
137
|
-
Run the checklist above against all task files. Fix every issue you find by editing the task files directly. Then re-run the full checklist from the top. Repeat until no issues remain.
|
|
138
|
-
|
|
139
|
-
## Output Format
|
|
140
|
-
|
|
141
|
-
After all issues are fixed, report what you found and fixed:
|
|
142
|
-
|
|
143
|
-
```
|
|
144
|
-
## Review Summary
|
|
145
|
-
- [T002] Fixed: reordered dependency — was depending on T005 which came later
|
|
146
|
-
- [T003] Fixed: added concrete verification command (was missing)
|
|
147
|
-
- [T001] Fixed: split into T001a/T001b — was touching 12 files
|
|
148
|
-
|
|
149
|
-
## Skill Observations (optional)
|
|
150
|
-
If any checklist items or review patterns in this skill were wrong or misleading, note them here.
|
|
151
|
-
```
|
|
152
|
-
|
|
153
|
-
If no issues found, state: "Task breakdown looks good. All criteria covered, dependencies valid, verification methods concrete."
|