prizmkit 1.1.193 → 1.1.195
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/create-prizmkit.js +43 -12
- package/bundled/VERSION.json +3 -3
- package/bundled/dev-pipeline/.env.example +5 -0
- package/bundled/dev-pipeline/README.md +2 -1
- package/bundled/dev-pipeline/prizmkit_runtime/checkpoint_state.py +111 -30
- package/bundled/dev-pipeline/prizmkit_runtime/cli.py +44 -3
- package/bundled/dev-pipeline/prizmkit_runtime/commands.py +29 -9
- package/bundled/dev-pipeline/prizmkit_runtime/config.py +121 -44
- package/bundled/dev-pipeline/prizmkit_runtime/daemon.py +190 -37
- package/bundled/dev-pipeline/prizmkit_runtime/interoperability.py +1 -0
- package/bundled/dev-pipeline/prizmkit_runtime/iterate.py +2480 -0
- package/bundled/dev-pipeline/prizmkit_runtime/paths.py +3 -0
- package/bundled/dev-pipeline/prizmkit_runtime/runner_bookkeeping.py +32 -8
- package/bundled/dev-pipeline/prizmkit_runtime/runners.py +29 -12
- package/bundled/dev-pipeline/prizmkit_runtime/runtime_commit.py +13 -5
- package/bundled/dev-pipeline/prizmkit_runtime/status.py +166 -0
- package/bundled/dev-pipeline/scripts/feature_list_contract.py +964 -0
- package/bundled/dev-pipeline/scripts/generate-bootstrap-prompt.py +18 -40
- package/bundled/dev-pipeline/scripts/generate-bugfix-prompt.py +24 -19
- package/bundled/dev-pipeline/scripts/prompt_framework.py +24 -8
- package/bundled/dev-pipeline/templates/bootstrap-tier3.md +1 -63
- package/bundled/dev-pipeline/templates/bug-fix-list-schema.json +8 -6
- package/bundled/dev-pipeline/templates/bugfix-bootstrap-prompt.md +0 -10
- package/bundled/dev-pipeline/templates/feature-list-schema.json +8 -6
- package/bundled/dev-pipeline/templates/iterate/evaluate-prompt.md +97 -0
- package/bundled/dev-pipeline/templates/iterate/evaluation-schema.json +538 -0
- package/bundled/dev-pipeline/templates/iterate/headless-plan-prompt.md +66 -0
- package/bundled/dev-pipeline/templates/sections/phase-specify-plan-full.md +2 -2
- package/bundled/dev-pipeline/templates/sections/runtime-commit-handoff.md +13 -4
- package/bundled/rules/USAGE.md +15 -48
- package/bundled/rules/_rules-metadata.json +7 -14
- package/bundled/rules/general/coding-baseline.md +23 -0
- package/bundled/rules/prizm/prizm-progressive-loading.md +2 -2
- package/bundled/skills/_metadata.json +12 -42
- package/bundled/skills/app-planner/SKILL.md +2 -2
- package/bundled/skills/app-planner/references/generated-plan-review.md +2 -2
- package/bundled/skills/app-planner/references/project-state-detection.md +1 -1
- package/bundled/skills/app-planner/references/rules-configuration.md +158 -88
- package/bundled/skills/app-planner/scripts/validate-rules-configuration.py +543 -12
- package/bundled/skills/bug-planner/references/verification.md +4 -5
- package/bundled/skills/bugfix-pipeline-launcher/SKILL.md +20 -14
- package/bundled/skills/bugfix-pipeline-launcher/references/configuration.md +49 -9
- package/bundled/skills/feature-pipeline-launcher/SKILL.md +20 -14
- package/bundled/skills/feature-pipeline-launcher/references/configuration.md +49 -9
- package/bundled/skills/feature-planner/SKILL.md +3 -3
- package/bundled/skills/feature-planner/references/browser-interaction.md +9 -29
- package/bundled/skills/iterate-pipeline-launcher/SKILL.md +273 -0
- package/bundled/skills/iterate-pipeline-launcher/references/configuration.md +105 -0
- package/bundled/skills/prizmkit-code-review/SKILL.md +10 -8
- package/bundled/skills/prizmkit-code-review/references/independent-code-review.md +4 -1
- package/bundled/skills/prizmkit-code-review/references/review-report-template.md +2 -1
- package/bundled/skills/prizmkit-code-review/scripts/render_review_report.py +12 -8
- package/bundled/skills/prizmkit-implement/SKILL.md +2 -2
- package/bundled/skills/prizmkit-init/SKILL.md +10 -10
- package/bundled/skills/prizmkit-init/references/brownfield-deep-init.md +81 -0
- package/bundled/skills/prizmkit-plan/SKILL.md +2 -1
- package/bundled/skills/prizmkit-plan/assets/plan-template.md +2 -0
- package/bundled/skills/prizmkit-prizm-docs/SKILL.md +8 -4
- package/bundled/skills/prizmkit-prizm-docs/assets/prizm-docs-format.md +8 -7
- package/bundled/skills/prizmkit-prizm-docs/references/op-init.md +33 -16
- package/bundled/skills/prizmkit-prizm-docs/references/op-validate.md +1 -1
- package/bundled/skills/prizmkit-retrospective/SKILL.md +29 -12
- package/bundled/skills/prizmkit-retrospective/references/retrospective-result-schema.json +126 -2
- package/bundled/skills/prizmkit-retrospective/references/rule-evolution-steps.md +86 -0
- package/bundled/skills/prizmkit-test/SKILL.md +2 -1
- package/bundled/skills/prizmkit-workflow/SKILL.md +8 -0
- package/bundled/skills/prizmkit-workflow/references/cold-start-rules.md +84 -0
- package/bundled/templates/project-memory-template.md +3 -3
- package/package.json +1 -1
- package/src/clean.js +2 -3
- package/src/config.js +52 -39
- package/src/index.js +29 -111
- package/src/prompts.js +20 -87
- package/src/runtime-passthrough.js +324 -0
- package/src/scaffold.js +41 -294
- package/src/upgrade.js +7 -39
- package/bundled/dev-pipeline/templates/sections/phase-browser-verification-auto.md +0 -127
- package/bundled/dev-pipeline/templates/sections/phase-browser-verification-opencli.md +0 -124
- package/src/external-skills.js +0 -103
package/bundled/rules/USAGE.md
CHANGED
|
@@ -4,16 +4,21 @@
|
|
|
4
4
|
|
|
5
5
|
```
|
|
6
6
|
core/rules/
|
|
7
|
-
├── _rules-metadata.json #
|
|
7
|
+
├── _rules-metadata.json # Built-in rule registry
|
|
8
8
|
├── prizm/ # PrizmKit-specific rules
|
|
9
9
|
│ ├── prizm-documentation.md
|
|
10
10
|
│ ├── prizm-commit-workflow.md
|
|
11
11
|
│ └── prizm-progressive-loading.md
|
|
12
12
|
└── general/ # General AI behavior rules
|
|
13
|
-
|
|
13
|
+
├── prefer-linux-commands.md
|
|
14
|
+
├── cohesive-modeling.md
|
|
15
|
+
├── agent-operational-rules.md
|
|
16
|
+
└── coding-baseline.md
|
|
14
17
|
```
|
|
15
18
|
|
|
16
|
-
##
|
|
19
|
+
## Built-In Rules
|
|
20
|
+
|
|
21
|
+
All rules registered in `core/rules/_rules-metadata.json` are installed automatically on `npx prizmkit install` and deployed on `npx prizmkit upgrade` (there are no rules presets or `--rules` flags).
|
|
17
22
|
|
|
18
23
|
### PrizmKit-Specific Rules (`prizm/`)
|
|
19
24
|
|
|
@@ -28,25 +33,9 @@ core/rules/
|
|
|
28
33
|
| File | Description |
|
|
29
34
|
|------|-------------|
|
|
30
35
|
| `prefer-linux-commands.md` | Prefer Linux/Unix commands, avoid platform-specific syntax |
|
|
31
|
-
|
|
32
|
-
|
|
33
|
-
|
|
34
|
-
## Installation Presets
|
|
35
|
-
|
|
36
|
-
Select a preset via the `--rules` option during installation, defined in the `presets` field of `_rules-metadata.json`:
|
|
37
|
-
|
|
38
|
-
| Preset | Included Rules |
|
|
39
|
-
|--------|---------------|
|
|
40
|
-
| `recommended` (default) | All 4 rules |
|
|
41
|
-
| `minimal` | prizm-progressive-loading + prefer-linux-commands |
|
|
42
|
-
| `none` | No rules installed |
|
|
43
|
-
|
|
44
|
-
Installation commands:
|
|
45
|
-
```bash
|
|
46
|
-
npx prizmkit install . --rules recommended
|
|
47
|
-
npx prizmkit install . --rules minimal
|
|
48
|
-
npx prizmkit install . --rules none
|
|
49
|
-
```
|
|
36
|
+
| `cohesive-modeling.md` | Group co-occurring variables, fields, and concepts into a cohesive unit |
|
|
37
|
+
| `agent-operational-rules.md` | Framework-level operational rules for all agents (Edit failure recovery, Read offset safety, stale line counts) |
|
|
38
|
+
| `coding-baseline.md` | Zero-config coding baseline (intent naming, modular boundaries, explicit error handling, dead/duplicated logic hygiene, baseline security, testability) |
|
|
50
39
|
|
|
51
40
|
---
|
|
52
41
|
|
|
@@ -100,7 +89,7 @@ globs:
|
|
|
100
89
|
|
|
101
90
|
### 2. Register in `_rules-metadata.json`
|
|
102
91
|
|
|
103
|
-
Open `core/rules/_rules-metadata.json` and add an entry in the `rules` object:
|
|
92
|
+
Open `core/rules/_rules-metadata.json` and add an entry in the `rules` object (and keep `presets.recommended.rules` aligned):
|
|
104
93
|
|
|
105
94
|
```json
|
|
106
95
|
{
|
|
@@ -113,33 +102,11 @@ Open `core/rules/_rules-metadata.json` and add an entry in the `rules` object:
|
|
|
113
102
|
}
|
|
114
103
|
```
|
|
115
104
|
|
|
116
|
-
Rule name format: `<category>/<filename>` (without the `.md` extension).
|
|
117
|
-
|
|
118
|
-
### 3. Add to a Preset (Optional)
|
|
119
|
-
|
|
120
|
-
If you want the new rule to be installed by default with `recommended`, append it to the `presets.recommended.rules` array:
|
|
121
|
-
|
|
122
|
-
```json
|
|
123
|
-
{
|
|
124
|
-
"presets": {
|
|
125
|
-
"recommended": {
|
|
126
|
-
"rules": [
|
|
127
|
-
"prizm/prizm-documentation",
|
|
128
|
-
"prizm/prizm-commit-workflow",
|
|
129
|
-
"prizm/prizm-progressive-loading",
|
|
130
|
-
"general/prefer-linux-commands",
|
|
131
|
-
"prizm/my-new-rule"
|
|
132
|
-
]
|
|
133
|
-
}
|
|
134
|
-
}
|
|
135
|
-
}
|
|
136
|
-
```
|
|
137
|
-
|
|
138
|
-
You can also add it to a specific preset only, or not add it to any preset (the rule exists but is not installed by default).
|
|
105
|
+
Rule name format: `<category>/<filename>` (without the `.md` extension). Every entry registered in `rules` is deployed automatically to all selected platforms.
|
|
139
106
|
|
|
140
|
-
###
|
|
107
|
+
### 3. Re-bundle
|
|
141
108
|
|
|
142
|
-
After modifying `core/rules/`,
|
|
109
|
+
After modifying `core/rules/`, update the npm package's `bundled/` contents:
|
|
143
110
|
|
|
144
111
|
```bash
|
|
145
112
|
npm run bundle
|
|
@@ -24,31 +24,24 @@
|
|
|
24
24
|
"general/agent-operational-rules": {
|
|
25
25
|
"description": "Framework-level operational rules for all agents — Edit failure recovery, Read offset safety, test output hygiene, incremental validation",
|
|
26
26
|
"tags": ["general", "agent", "operational"]
|
|
27
|
+
},
|
|
28
|
+
"general/coding-baseline": {
|
|
29
|
+
"description": "Zero-config coding baseline covering intent naming, modular boundaries, explicit error handling, dead/duplicated code hygiene, baseline security, and testability",
|
|
30
|
+
"tags": ["general", "coding", "baseline"]
|
|
27
31
|
}
|
|
28
32
|
},
|
|
29
33
|
"presets": {
|
|
30
34
|
"recommended": {
|
|
31
|
-
"description": "All PrizmKit rules + general rules (
|
|
35
|
+
"description": "All built-in PrizmKit rules + general rules (installed automatically)",
|
|
32
36
|
"rules": [
|
|
33
37
|
"prizm/prizm-documentation",
|
|
34
38
|
"prizm/prizm-commit-workflow",
|
|
35
39
|
"prizm/prizm-progressive-loading",
|
|
36
40
|
"general/prefer-linux-commands",
|
|
37
41
|
"general/cohesive-modeling",
|
|
38
|
-
"general/agent-operational-rules"
|
|
42
|
+
"general/agent-operational-rules",
|
|
43
|
+
"general/coding-baseline"
|
|
39
44
|
]
|
|
40
|
-
},
|
|
41
|
-
"minimal": {
|
|
42
|
-
"description": "Minimal: progressive loading + general rules + operational rules",
|
|
43
|
-
"rules": [
|
|
44
|
-
"prizm/prizm-progressive-loading",
|
|
45
|
-
"general/prefer-linux-commands",
|
|
46
|
-
"general/agent-operational-rules"
|
|
47
|
-
]
|
|
48
|
-
},
|
|
49
|
-
"none": {
|
|
50
|
-
"description": "No rules installed",
|
|
51
|
-
"rules": []
|
|
52
45
|
}
|
|
53
46
|
}
|
|
54
47
|
}
|
|
@@ -0,0 +1,23 @@
|
|
|
1
|
+
---
|
|
2
|
+
description: "Zero-config coding baseline covering clear intent, modular boundaries, explicit error handling, no dead/duplicated core logic, baseline security, and testable minimal diffs"
|
|
3
|
+
---
|
|
4
|
+
|
|
5
|
+
# Coding Baseline
|
|
6
|
+
|
|
7
|
+
Apply these falsifiable baselines when planning, implementing, or reviewing code. When no matching `.prizmkit/rules/<layer>-rules.md` exists, explicitly activate `framework-coding-baseline` with detected language/stack conventions (e.g., strict typing and handled promises in TypeScript, no bare `except:` or mutable defaults in Python, explicit `err` handling in Go, parameterized SQL).
|
|
8
|
+
|
|
9
|
+
## Six Baseline Pillars
|
|
10
|
+
|
|
11
|
+
1. **Intent-Revealing Naming & Single Responsibility**: Name modules, types, functions, and variables by domain intent. Keep each unit to one cohesive responsibility rather than mixing I/O, business logic, and formatting.
|
|
12
|
+
2. **Modular Boundaries**: Complement `cohesive-modeling.md` by isolating domain logic behind explicit interfaces; prevent circular imports and hidden cross-module state coupling.
|
|
13
|
+
3. **Boundary Input Validation & Explicit Error Handling**: Validate untrusted or cross-boundary inputs (requests, CLI args, config/env, deserialized payloads) at the entry boundary and fail fast with contextual errors; never swallow failures with empty catch/except blocks or silent fallbacks.
|
|
14
|
+
4. **Zero Dead Code & No Duplicated Core Logic**: Remove unused code, unreachable branches, commented-out blocks, and obsolete flags; centralize shared invariants instead of copy-pasting core logic.
|
|
15
|
+
5. **Baseline Security**: Use parameterized queries and structured command arguments (never interpolate untrusted input into SQL or shell strings); never hardcode or log secrets/tokens; enforce least privilege and explicit authorization checks.
|
|
16
|
+
6. **Minimal-Blast-Radius Testability**: Keep side effects, I/O, clocks, and storage behind narrow seams for deterministic tests and localized diffs.
|
|
17
|
+
|
|
18
|
+
## Precedence
|
|
19
|
+
|
|
20
|
+
Resolve conflicts without clarification pauses:
|
|
21
|
+
1. Repository explicit contracts, current source/detail docs, committed schemas, linters/compilers, host instructions (highest)
|
|
22
|
+
2. `.prizmkit/rules/<layer>-rules.md`
|
|
23
|
+
3. Framework `coding-baseline` and language conventions
|
|
@@ -5,9 +5,9 @@ description: "PrizmKit progressive context loading protocol"
|
|
|
5
5
|
This project uses PrizmKit's progressive loading protocol:
|
|
6
6
|
- ON SESSION START: Read exact `.prizmkit/prizm-docs/root.prizm` (L0 project map) when it exists.
|
|
7
7
|
- ON TASK: Read only relevant direct-child L1 documents (`.prizmkit/prizm-docs/<module>.prizm`) selected through root MODULE_INDEX/MODULE_GROUPS pointers.
|
|
8
|
-
- LAYER_RULES: If the current task lands on frontend, backend, database, or mobile, Read `.prizmkit/rules/<layer>-rules.md` when that exact convention path exists
|
|
8
|
+
- LAYER_RULES: If the current task lands on frontend, backend, database, or mobile, Read `.prizmkit/rules/<layer>-rules.md` when that exact convention path exists and enforce it consciously for planning, implementation HOW refinement, and code review. Never load all four files by default. If a task spans two layers, read both existing files. Map browser UI work to frontend, service or API work to backend, schema migration or ORM work to database, and iOS, Android, React Native, or Flutter work to mobile. Discover by exact path Read; do not depend on git tracking or glob. When the file does not exist, do not block and do not silently skip—explicitly activate the built-in `coding-baseline` plus detected language/stack conventions (e.g., strict typing and no unhandled promises in TypeScript, no bare `except:` or mutable default arguments in Python, explicit `err` handling in Go, parameterized SQL) and record the active rule source (`project-layer-rules` vs `framework-coding-baseline`). Enforce three-tier override precedence without a clarification pause: Tier 1 (highest) repository explicit contracts, current source and L2 `.prizm` facts, committed OpenAPI/schemas, project linters/compilers, and host project instruction conventions; Tier 2 `.prizmkit/rules/<layer>-rules.md`; Tier 3 (fallback) framework `coding-baseline` and language conventions—when rules conflict, those current sources win without a clarification pause. L0 `RULES:` MUST/NEVER remain authoritative for that key.
|
|
9
9
|
- ON FILE EDIT: Read the complete relevant nested L2 document and complete parent/child documents needed to resolve its SUBDIRS or DETAILS pointer before modification. Grep-only fragments are insufficient modification context.
|
|
10
|
-
- IF L2 IS ABSENT: Inspect only bounded target source and narrowly implicated contracts; proceed without creating a placeholder. Documentation creation belongs to Retrospective or explicit documentation repair and requires complete Value-Gate-qualified content.
|
|
10
|
+
- IF L2 IS ABSENT: Inspect only bounded target source and narrowly implicated contracts; proceed without creating a placeholder. Documentation creation belongs to brownfield core initialization, Retrospective, or explicit documentation repair and requires complete Value-Gate-qualified content.
|
|
11
11
|
- NEVER load all L1/L2 documents at session start, create L3, or load unrelated modules.
|
|
12
12
|
- PATH LEVELS: only exact `root.prizm` is L0; every other direct `.prizm` child is L1; every nested `.prizm` document is L2.
|
|
13
13
|
- Arrow notation (`->`) identifies resolving documentation pointers.
|
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
{
|
|
2
|
-
"version": "1.1.
|
|
2
|
+
"version": "1.1.195",
|
|
3
3
|
"skills": {
|
|
4
4
|
"prizmkit": {
|
|
5
5
|
"description": "Framework introduction and navigation for the formal single-requirement lifecycle, project initialization, Prizm docs, and independent deployment.",
|
|
@@ -111,7 +111,7 @@
|
|
|
111
111
|
"hasScripts": true
|
|
112
112
|
},
|
|
113
113
|
"feature-pipeline-launcher": {
|
|
114
|
-
"description": "Build feature pipeline start, status, logs, stop, and safe retry commands from a validated feature-list.json without executing
|
|
114
|
+
"description": "Build feature pipeline start, status, logs, stop, and safe retry commands from a validated feature-list.json with optional on-demand read-only AI CLI capability probing, without executing pipelines.",
|
|
115
115
|
"tier": "companion",
|
|
116
116
|
"category": "orchestration-skill",
|
|
117
117
|
"subcategory": "pipelines",
|
|
@@ -119,7 +119,15 @@
|
|
|
119
119
|
"hasScripts": false
|
|
120
120
|
},
|
|
121
121
|
"bugfix-pipeline-launcher": {
|
|
122
|
-
"description": "Build bugfix pipeline start, status, logs, stop, and safe retry commands from a validated bug-fix-list.json without executing
|
|
122
|
+
"description": "Build bugfix pipeline start, status, logs, stop, and safe retry commands from a validated bug-fix-list.json with optional on-demand read-only AI CLI capability probing, without executing pipelines.",
|
|
123
|
+
"tier": "companion",
|
|
124
|
+
"category": "orchestration-skill",
|
|
125
|
+
"subcategory": "pipelines",
|
|
126
|
+
"hasAssets": false,
|
|
127
|
+
"hasScripts": false
|
|
128
|
+
},
|
|
129
|
+
"iterate-pipeline-launcher": {
|
|
130
|
+
"description": "Build autonomous product-iteration start, status, logs, stop, and post-pause resume commands with optional on-demand read-only AI CLI capability probing, without executing pipelines.",
|
|
123
131
|
"tier": "companion",
|
|
124
132
|
"category": "orchestration-skill",
|
|
125
133
|
"subcategory": "pipelines",
|
|
@@ -164,48 +172,10 @@
|
|
|
164
172
|
"bug-planner",
|
|
165
173
|
"feature-pipeline-launcher",
|
|
166
174
|
"bugfix-pipeline-launcher",
|
|
175
|
+
"iterate-pipeline-launcher",
|
|
167
176
|
"bug-fix-workflow",
|
|
168
177
|
"recovery-workflow"
|
|
169
178
|
]
|
|
170
|
-
},
|
|
171
|
-
"minimal": {
|
|
172
|
-
"description": "Minimal single-requirement lifecycle: composite workflow plus all six formal stages and Prizm documentation sync",
|
|
173
|
-
"skills": [
|
|
174
|
-
"prizmkit",
|
|
175
|
-
"prizmkit-workflow",
|
|
176
|
-
"prizmkit-init",
|
|
177
|
-
"prizmkit-prizm-docs",
|
|
178
|
-
"prizmkit-plan",
|
|
179
|
-
"prizmkit-implement",
|
|
180
|
-
"prizmkit-code-review",
|
|
181
|
-
"prizmkit-test",
|
|
182
|
-
"prizmkit-retrospective",
|
|
183
|
-
"prizmkit-committer"
|
|
184
|
-
]
|
|
185
179
|
}
|
|
186
|
-
},
|
|
187
|
-
"external_skills": {
|
|
188
|
-
"known": [
|
|
189
|
-
{
|
|
190
|
-
"name": "find-skills",
|
|
191
|
-
"description": "Helps discover and install agent skills by capability",
|
|
192
|
-
"repo": "https://github.com/vercel-labs/skills",
|
|
193
|
-
"tags": [
|
|
194
|
-
"search",
|
|
195
|
-
"utility"
|
|
196
|
-
]
|
|
197
|
-
},
|
|
198
|
-
{
|
|
199
|
-
"name": "frontend-design",
|
|
200
|
-
"description": "Production-grade frontend design skill from pbakaus/impeccable",
|
|
201
|
-
"repo": "pbakaus/impeccable",
|
|
202
|
-
"tags": [
|
|
203
|
-
"design",
|
|
204
|
-
"frontend",
|
|
205
|
-
"ui",
|
|
206
|
-
"ux"
|
|
207
|
-
]
|
|
208
|
-
}
|
|
209
|
-
]
|
|
210
180
|
}
|
|
211
181
|
}
|
|
@@ -62,7 +62,7 @@ Return `NEEDS_FIXES` whenever any answer is unavailable or ambiguous. Ask the us
|
|
|
62
62
|
- Do NOT use `app-planner` when user already has a brief and wants features or refactoring on an existing project (`feature-planner`), wants to run the pipeline (`feature-pipeline-launcher`), or wants debugging or direct coding.
|
|
63
63
|
- **On-demand guides**: load `${SKILL_DIR}/references/app-design-guide.md` on demand for greenfield vision or unresolved stack selection; load `architecture-decisions.md` (architecture choices), `frontend-design-guide.md` (UI), `brainstorm-guide.md` + `red-team-checklist.md` (exploration/Phase C), and `project-brief-guide.md` (brief rules).
|
|
64
64
|
- **Conventions & Infrastructure discovery** (after Intent Confirmation): resolve the target once through **Current-host project instruction target resolution**, inspect `### Project Conventions` (if missing/incomplete, read `${SKILL_DIR}/references/project-conventions-discovery.md` for project-specific AI discovery via `AskUserQuestion`—no fixed checklist; normalize & pass the Pre-Generation gate before saving under `### Project Conventions`). Then check `### Infrastructure` using `${SKILL_DIR}/references/infrastructure-convention-discovery.md` (DB/deployment/cloud services via `AskUserQuestion`, each question offering `"Skip — decide later"` → `<!-- [topic]: deferred -->`), pass the gate, and update `### Infrastructure`.
|
|
65
|
-
- **Rules Configuration (after CP-AP-1.5)**: optional per-layer rules (`.prizmkit/rules/<layer>-rules.md` — skip freely if declined). Read `${SKILL_DIR}/references/rules-configuration.md` and
|
|
65
|
+
- **Rules Configuration (after CP-AP-1.5)**: optional per-layer rules (`.prizmkit/rules/<layer>-rules.md` — skip freely if declined). Read `${SKILL_DIR}/references/rules-configuration.md`: present detected/confirmed layers once with `AI Auto-Synthesize (Recommended)` as the default path (fusing project facts including pointed detail `.prizm` docs, canonical `references/rules/<layer>/` assets, built-in rule deduplication, and conflict-gated stack risks into the unified 5-section contract, upgrading any `Mode: cold-start-lightweight` file while preserving `## 5. Project-Evolved Rules`), plus `Advanced Manual Questionnaire (Quick / Full)` and `Skip rules configuration`. Run `${SKILL_DIR}/scripts/validate-rules-configuration.py --rules-root ${SKILL_DIR}/references/rules` before synthesis/questioning and `--validate-output` after rendering; pass both conflict and Pre-Generation gates before finalizing `.prizmkit/rules/` or updating `.prizmkit/prizm-docs/root.prizm` (`LAYER_RULES:` block only).
|
|
66
66
|
- **Project brief accumulation**: maintain normalized checklist items in memory or `.prizmkit/plans/project-brief.draft.md`; do not write the final `.prizmkit/plans/project-brief.md` until the Pre-Generation Headless Context Completeness Gate passes.
|
|
67
67
|
- **Prerequisites** (read-only, never block, do not create `config.json` here): check `.prizmkit/prizm-docs/root.prizm`, `.prizmkit/config.json` (`tech_stack` pre-fill — confirm instead of re-asking), and resolved `### Project Conventions` / `### Infrastructure`.
|
|
68
68
|
|
|
@@ -93,7 +93,7 @@ Run this gate before any final handoff whenever the current `app-planner` sessio
|
|
|
93
93
|
1. **Load the local reference**: read `${SKILL_DIR}/references/generated-plan-review.md` and follow it as the source of truth for app-planner generated content review.
|
|
94
94
|
2. **Read actual planning artifacts directly**: inspect current-session final outputs such as `.prizmkit/plans/project-brief.md`, changed sections in the resolved project instruction target, `.prizmkit/rules/<layer>-rules.md`, and `.prizmkit/prizm-docs/root.prizm` `LAYER_RULES:` pointer block. Do not rely on `git status`, `git diff`, or `git diff --cached`, because `.prizmkit` planning artifacts are often gitignored or untracked.
|
|
95
95
|
3. **Scope to new/changed app-planning content**: compare against pre-session snapshots or in-memory drafts when available. Preserve unchanged historical brief items, instruction-file sections, rules files, and Prizm doc content. For explore-only sessions, draft-save exits, or flows with no new final planning content, report: `Local generated-plan review: not applicable — no new final planning content written.`
|
|
96
|
-
4. **Run the local checklist and fresh-session simulation** from the reference: project brief completeness; consistency of conventions, infrastructure, and architecture decisions; Rules Configuration resource-validation and conflict-gate evidence; selected-decision precedence; explicit not-applicable/deferred sections; dual-native profile separation; rules pointer consistency; normalization of selected decisions; purpose-tagged references; app-planner writable-boundary compliance; and downstream `feature-planner` readiness to produce `.prizmkit/plans/feature-list.json` without guessing or seeing the original conversation.
|
|
96
|
+
4. **Run the local checklist and fresh-session simulation** from the reference: project brief completeness; consistency of conventions, infrastructure, and architecture decisions; Rules Configuration resource-validation (`--rules-root`), output-validation (`--validate-output`), cold-start evolution-preservation, and conflict-gate evidence; selected-decision precedence; explicit not-applicable/deferred sections; dual-native profile separation; rules pointer consistency; normalization of selected decisions; purpose-tagged references; app-planner writable-boundary compliance; and downstream `feature-planner` readiness to produce `.prizmkit/plans/feature-list.json` without guessing or seeing the original conversation.
|
|
97
97
|
5. **Apply accepted fixes through the source/writer path**: project brief fixes go through the draft/checklist source, instruction-file section fixes go through the resolved project instruction target's section source with user confirmation when changing approved wording, rules fixes re-render from rules configuration answers/templates when available, and `root.prizm` fixes are limited to the `LAYER_RULES:` pointer block.
|
|
98
98
|
6. **Recheck changed sections directly** after every accepted fix batch.
|
|
99
99
|
7. **Report CP-AP-6** in the completion summary: include local generated-plan review verdict, reviewed app-planning artifacts/sections, accepted fixes (or "none"), and final writer/validation result.
|
|
@@ -33,7 +33,7 @@ Do not rely on `git status`, `git diff`, or `git diff --cached` to decide whethe
|
|
|
33
33
|
|
|
34
34
|
- `project-brief.md` fixes go through the draft/checklist project brief source representation described in `project-brief-guide.md`, then rewrite the final brief through the existing project brief writer path.
|
|
35
35
|
- Project conventions, infrastructure, frontend design direction, and architecture decisions are source sections in the exact project instruction target selected for the current session. If a fix changes user-approved wording or meaning, ask for user confirmation before rewriting.
|
|
36
|
-
- `.prizmkit/rules/<layer>-rules.md` fixes should re-render from the normalized decision ledger, invariant/derivation sources, and template inputs. Rerun `scripts/validate-rules-configuration.py` and the Rules Configuration conflict gate before
|
|
36
|
+
- `.prizmkit/rules/<layer>-rules.md` fixes should re-synthesize (in `ai-synthesized` mode) from project facts, canonical `references/rules/<layer>/` assets, and the normalized decision ledger—or re-render (in `manual-questionnaire` mode) from the normalized decision ledger, invariant/derivation sources, and template inputs—while preserving any existing `## 5. Project-Evolved Rules` entries verbatim. Rerun both `python3 ${SKILL_DIR}/scripts/validate-rules-configuration.py --rules-root ${SKILL_DIR}/references/rules` and `python3 ${SKILL_DIR}/scripts/validate-rules-configuration.py --validate-output .prizmkit/rules/<layer>-rules.md` (or `--validate-output .prizmkit/rules`) plus the Rules Configuration conflict gate before finalizing. If no structured source remains, rebuild the decision ledger or ask for clarification; do not hand-patch a contradictory final rule file.
|
|
37
37
|
- `root.prizm` fixes are limited to correcting or adding the `LAYER_RULES:` pointer block; do not rewrite unrelated root content or convert `LAYER_RULES:` into MUST/NEVER `RULES:` entries.
|
|
38
38
|
|
|
39
39
|
## Review Checklist
|
|
@@ -46,7 +46,7 @@ For every reviewed app-planning artifact or section, check:
|
|
|
46
46
|
- Project brief completeness: goal, users, differentiators, constraints, tech stack assumptions, and at least three actionable ideas when producing a final brief
|
|
47
47
|
- Consistency among conventions, infrastructure, architecture decisions, and project brief content
|
|
48
48
|
- Infrastructure completeness or explicit deferral for database, deployment, and cloud services topics when those flows ran
|
|
49
|
-
- Rules Configuration integrity:
|
|
49
|
+
- Rules Configuration integrity: both deterministic validators passed (`--rules-root` static check and `--validate-output` returning `valid: true` on every written `.prizmkit/rules/<layer>-rules.md`); unified metadata headers (`Owner: app-planner`, `Mode`, `Layer`, `Stack Snapshot`) and all five sections (`## 1.`–`## 5.`) are present; `ai-synthesized` Section 1 entries carry provenance (`verified-from-code`, `confirmed-by-user`, or `ai-inferred-default`); Quick defaults were explicitly authorized when manual mode ran; upgraded `cold-start-lightweight` files preserved all pre-existing `## 5. Project-Evolved Rules` entries verbatim; fixed content contains only invariants without duplicating `coding-baseline.md` or `cohesive-modeling.md`; selected decisions own their policy domains; no active rule conflicts with the decision ledger or Deny List; unmatched/not-applicable choices are explicit; dual-native decisions remain in separate iOS/Android profiles; raw UTF-8 size stays <= 16 KB (warning at 12 KB) and `## 5. Project-Evolved Rules` <= 20 entries; and rendered files contain no residual placeholders
|
|
50
50
|
- Rules pointer consistency: generated `.prizmkit/rules/<layer>-rules.md` files are referenced by the `root.prizm` `LAYER_RULES:` pointer block when rules were configured; `RULES:` remains MUST/NEVER and is not a file pointer
|
|
51
51
|
- Substantive user meaning and detail preservation at matching detail after conversational normalization in project brief ideas, conventions, infrastructure notes, architecture decisions, and rules
|
|
52
52
|
- Artifact-wide readability: every generated natural-language value across all AI-visible fields and sections—including briefs/drafts, instruction sections, generated rules, appendices, comments, brainstorm summaries, quoted evidence, and parentheticals—is a standalone domain statement without dialogue-role labels, question IDs, answer tokens, planning-option recommendation markers, raw answer-map content, or planning provenance
|
|
@@ -54,7 +54,7 @@ Do NOT ask the user to describe their project — read it yourself first:
|
|
|
54
54
|
- `go.mod` -> Go module info
|
|
55
55
|
- `README.md` -> project description and goals
|
|
56
56
|
- `.prizmkit/config.json` -> previously detected tech stack
|
|
57
|
-
- `.prizmkit/prizm-docs/root.prizm` -> existing architecture context
|
|
57
|
+
- `.prizmkit/prizm-docs/root.prizm` -> existing architecture context; when present, also read relevant pointed module/detail `.prizm` documents (contracts, dependencies, traps, and decisions) to inform planning and default AI rules synthesis
|
|
58
58
|
|
|
59
59
|
3. **Read key source files** (entry points, main routes, core models) to understand what the project actually does — don't rely solely on metadata.
|
|
60
60
|
|