Add new requirements to spec.md or fill gaps in documents. Primary: Add features (replaces /enhance). Secondary: Fill gaps after /reverse. Triggers: reinforce, add requirements, new feature
Adds new requirements to spec.md or fills gaps in existing documents after reverse engineering.
/plugin marketplace add samdae/archflow/plugin install archflow@archflow-marketplaceThis skill is limited to using the following tools:
Global Rules: Adheres to
rules/archflow-rules.md. Req IDFR-{number}Rule: Always usemax(existing number) + 1. NEVER reuse deleted numbers.
Model: Sonnet (document merging). Opus for complex reasoning.
Add new requirements or fill gaps in existing documents.
New Proposal → /reinforce (spec.md) → /arch → /check → /build
| Tool | Alternative |
|---|---|
| Read | Request file from user → ask for copy-paste |
| AskQuestion | "Select: 1) A 2) B" format |
docs/{serviceName}/
├── spec.md # ← Input/Output
├── arch.md # ← Input/Output
└── trace.md
{
"title": "Start Document Reinforcement",
"questions": [
{
"id": "has_docs",
"prompt": "Do you have documents to reinforce?",
"options": [
{"id": "yes", "label": "Yes - I will provide file paths with @"},
{"id": "no", "label": "No - I don't have documents"}
]
}
]
}
no → guide to /reverseyes → request spec.md, arch.md pathsFrom path: docs/alert/spec.md → serviceName = "alert"
Read spec.md and arch.md.
Extract items marked with:
❓ Needs confirmation — requires user to provide content (delete and rewrite)❓ Unconfirmed — not yet verified by user❓ Inferred — AI-inferred, keep content but needs user confirmation to become ✅ ConfirmedNOTE: These three ❓ variants have different handling logic in Phase 4-3.
## Current Document Status
### spec.md
| Section | Status |
|---------|--------|
| Goal | ✅ Confirmed / ❓ Inferred / ❌ Unconfirmed |
| Non-goals | {status} |
| Feature Specification | {status} |
| Priority | {status} |
### arch.md
| Section | Status |
|---------|--------|
| Summary | {status} |
| Code Mapping | ✅ Extracted |
| API Spec | ✅ Extracted |
| Risks & Tradeoffs | {status} |
### Items Needing Reinforcement
1. {Item 1} - {current status}
2. {Item 2} - {current status}
{
"title": "What information do you want to add?",
"questions": [
{
"id": "reinforce_type",
"prompt": "Select the type of content to reinforce",
"options": [
{"id": "add_requirement", "label": "Add new requirements - New feature to spec.md (then run arch)"},
{"id": "fill_blank", "label": "Fill gaps - Items marked with ❓"},
{"id": "correct", "label": "Fix errors - Correct incorrect inferences"},
{"id": "add_new", "label": "Add new info - Later-acquired information"},
{"id": "guided", "label": "Guided mode - Ask me questions one by one"}
]
}
]
}
add_requirement (PRIMARY USE):
| Req ID | Category | Requirement | Priority | Status |
|--------|----------|-------------|----------|--------|
| FR-001 | Auth | ... | High | Designed |
| FR-002 | Auth | ... | Medium | Implemented |
| FR-003 | {category} | {new requirement} | {priority} | Draft |/arch to update design."fill_blank: For each ❓ item, ask user (provide / skip). correct: User specifies section + correct content. add_new: User describes freely, classify to appropriate section. guided: Ask about unconfirmed items in sequence.
| Information Type | Target Document |
|---|---|
| Business purpose/intent | spec.md - Goal, Non-goals |
| Feature description/behavior | spec.md - Feature Specification |
| Priority/importance | spec.md - Priority |
| Technical decision rationale | arch.md - Risks & Tradeoffs |
| Architecture changes | arch.md - Architecture, Code Mapping |
| API changes | arch.md - API Spec |
{
"title": "Classify Information",
"questions": [
{
"id": "classify",
"prompt": "Your input:\n\"{user input summary}\"\n\nWhere should this be reflected?",
"options": [
{"id": "requirements", "label": "Requirements (spec.md)"},
{"id": "arch", "label": "Architecture (arch.md)"},
{"id": "both", "label": "Both"},
{"id": "auto", "label": "You decide"}
]
}
]
}
| Section | Update Method |
|---|---|
| Goal | Inferred → Confirmed (remove ❓) |
| Non-goals | Empty → Fill with content |
| Feature Specification | Add/modify |
| Priority | Empty → Fill with content |
| Unclear Items | Remove resolved items |
| Section | Update Method |
|---|---|
| Summary | Confirm Goal/Non-goals |
| Scope | Clarify scope |
| Risks & Tradeoffs | Empty → Fill with content |
| Code Mapping | See rules below |
Code Mapping Impl column rules:
Impl status unchanged (do not modify [x] or [ ])Impl = [ ] and continue # numberingImpl as-isThree ❓ variants have different transformation rules:
❓ Needs confirmation → Content replacement (delete existing content, rewrite with user-provided info)❓ Inferred → ✅ Confirmed (keep content as-is, change status marker only)low → high (metadata change only, if user confirmed)## Reinforcement History
| Date | Type | Changes |
|------|------|---------|
| {date} | fill_blank | Confirmed Goal, Non-goals |
| {date} | add_new | Added Risks section |
## Changes to be Applied
### spec.md
| Section | Before | After |
|---------|--------|-------|
| {section} | {previous} | {new} |
### arch.md
| Section | Before | After |
|---------|--------|-------|
| {section} | {previous} | {new} |
Ask user: "I will update the documents with these changes. Proceed?"
docs/{serviceName}/spec.md and docs/{serviceName}/arch.md
Report: changed sections, change type, completion rate before/after, remaining unconfirmed items. Next: need more → re-run /reinforce; complete → use sync/build.
[reverse] → Incomplete documents
↓
[reinforce] ←──┐
│ │ (repeat)
↓ │
Reinforced ────┘
documents
↓ (when complete)
Use sync/build
Activates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use for discovering, retrieving, and improving prompts.
Search, retrieve, and install Agent Skills from the prompts.chat registry using MCP tools. Use when the user asks to find skills, browse skill catalogs, install a skill for Claude, or extend Claude's capabilities with reusable AI agent components.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.