@mrciphersmith/keryx 0.2.9

package/src/gdskills/bundled/skills/planning/autodoc-writer/SKILL.md

@@ -0,0 +1,253 @@
+---
+name: autodoc-writer
+description: >
+  Phase 4 subagent for autodoc-orchestrator. Writes one documentation section
+  from analysis artifacts. Dispatched in parallel — one instance per section.
+  Use when: dispatched by autodoc-orchestrator Phase 4.
+  NOT for: direct user invocation.
+version: 1.0.0
+---
+
+# autodoc-writer
+
+## Purpose
+
+Transform technical analysis artifacts into clear, human-readable documentation
+for one specific section. Each instance handles exactly one output file.
+
+## Iron Laws
+
+| # | Law |
+|---|-----|
+| 1 | Write ONE section per invocation |
+| 2 | All content MUST be derived from input artifacts — no hallucination |
+| 3 | Write for the target audience (developer onboarding, API consumers, architects) |
+| 4 | Use concrete examples from the actual codebase (real file paths, real commands) |
+| 5 | If a section requires info not in the artifacts, note it as [TODO: add X] rather than inventing |
+
+---
+
+## Input Contract
+
+```yaml
+section: "onboarding | architecture | modules | api-reference | data-models"
+language: "en | ru"
+input_artifacts:
+  - ".metaproject/jobs/<job>/artifacts/project-map.md"
+  - ".metaproject/jobs/<job>/artifacts/architecture.md"
+  - ".metaproject/jobs/<job>/artifacts/analysis/*.md"
+output_path: ".metaproject/jobs/<job>/docs/<section>.md"
+JOB_DIR: "<job directory>"
+PROJECT_DIR: "<project path>"
+```
+
+## Output Contract
+
+```yaml
+status: "DONE" | "DONE_WITH_CONCERNS"
+summary: "<2-3 sentences: what was written, any gaps found>"
+concerns: ["<info that was missing from artifacts>"]
+artifact_path: ".metaproject/jobs/<job>/docs/<section>.md"
+```
+
+---
+
+## Section Templates
+
+### onboarding.md
+
+Target audience: developer joining the project for the first time.
+
+```markdown
+# Getting Started with <Project Name>
+
+## What Is This Project?
+<1-paragraph overview: what it does, who uses it, main value>
+
+## Architecture at a Glance
+<3-5 bullet points covering the main components>
+Full details: [Architecture](architecture.md)
+
+## Prerequisites
+- <runtime + version>
+- <tool + version>
+- <env requirements>
+
+## Setup
+
+### 1. Clone the Repository
+```bash
+git clone <repo url>
+cd <project>
+```
+
+### 2. Install Dependencies
+```bash
+<install command per module>
+```
+
+### 3. Configure Environment
+```bash
+cp .env.example .env
+# Required variables:
+# DATABASE_URL=...
+# API_KEY=...
+```
+
+### 4. Run Locally
+```bash
+<dev command>
+```
+
+### 5. Run Tests
+```bash
+<test command>
+```
+
+## Project Structure
+<annotated top-level directory tree>
+
+## Development Workflow
+<branch strategy, PR process, CI/CD pipeline>
+
+## Common Tasks
+| Task | Command |
+|------|---------|
+| Start dev server | `<cmd>` |
+| Run tests | `<cmd>` |
+| Build for production | `<cmd>` |
+| Run migrations | `<cmd>` |
+```
+
+---
+
+### architecture.md
+
+Target audience: developer understanding system design.
+
+```markdown
+# Architecture
+
+## Overview
+<2-3 paragraphs: architectural style, why it was chosen (if evident), main trade-offs>
+
+## Components
+<system diagram in text / table form>
+
+## Module Breakdown
+<for each module: 1 paragraph + key responsibilities>
+
+## Data Flow
+<main request path through the system, step by step>
+
+## Cross-Cutting Concerns
+<auth, logging, error handling, caching — how each works>
+
+## Key Design Decisions
+<important architectural choices evident from the codebase>
+```
+
+---
+
+### modules.md
+
+Target audience: developer working on a specific module.
+
+```markdown
+# Module Reference
+
+## <Module Name>
+
+### Purpose
+<what this module does>
+
+### Entry Point
+`<file path>`
+
+### Directory Structure
+<annotated tree>
+
+### Key Components
+| Component | File | Responsibility |
+|-----------|------|---------------|
+
+### Public API
+<endpoints or exports with descriptions>
+
+### Configuration
+| Variable | Required | Description |
+|----------|---------|-------------|
+
+### Testing
+<how to run, test patterns>
+
+---
+<repeat for each module>
+```
+
+---
+
+### api-reference.md
+
+Target audience: API consumer / integration developer.
+
+```markdown
+# API Reference
+
+## Base URL
+`<base URL>`
+
+## Authentication
+<how to authenticate>
+
+## Endpoints
+
+### <Resource Name>
+
+#### `<METHOD> <path>`
+**Description**: <what it does>
+
+**Request**
+```json
+{
+  "field": "type — description"
+}
+```
+
+**Response**
+```json
+{
+  "field": "type — description"
+}
+```
+
+**Errors**
+| Code | Meaning |
+|------|---------|
+
+---
+<repeat for each endpoint group>
+```
+
+---
+
+### data-models.md
+
+Target audience: developer working with data layer.
+
+```markdown
+# Data Models
+
+## <Model Name>
+**Source**: `<schema file path>`
+**Used in**: <modules/endpoints>
+
+| Field | Type | Required | Description |
+|-------|------|---------|-------------|
+
+## Relationships
+<entity relationship description>
+
+## Migrations
+<how to run, where they live>
+```

package/src/gdskills/bundled/skills/planning/brainstorm/SKILL.claude.md

@@ -0,0 +1,46 @@
+---
+description: Structured brainstorming — architecture decisions, problem solving, open exploration
+allowed-tools: Read(*), Glob(*), Bash(git log:*), Bash(git branch:*)
+---
+
+## Context
+
+- Project: !`basename $(git rev-parse --show-toplevel 2>/dev/null) 2>/dev/null || basename $PWD`
+- Current branch: !`git branch --show-current 2>/dev/null || echo "n/a"`
+- Recent work: !`git log --oneline -5 2>/dev/null || echo "n/a"`
+
+## Your task
+
+Topic to brainstorm: $ARGUMENTS
+
+Run a structured brainstorm session. Auto-detect mode from topic:
+
+### Mode A — Feature / Architecture
+*when topic is about building or designing something*
+
+1. **Restate the problem** in one sentence
+2. **Constraints** — perf, compat, team, time, existing stack
+3. **5-7 distinct approaches** — each with: catchy name, core idea (1-2 sentences), key trade-off
+4. **Wild card** — one unconventional idea that breaks assumptions
+5. **Recommendation** — top 2 with reasoning
+6. **Open questions** — what must be decided before committing
+
+### Mode B — Problem Solving
+*when topic is a bug, failure, or "why is X happening"*
+
+1. **Reproduce** — what fails, when, under what conditions
+2. **5 hypotheses** — ordered by likelihood
+3. **Fastest disproof** — specific command or check for each
+4. **Most likely culprit** — and why
+5. **Fix options** — quick fix vs proper fix
+
+### Mode C — Open-ended / Creative
+*when topic is vague or exploratory*
+
+1. **Expand the space** — 3 different framings of the question
+2. **Diverge** — 10 raw ideas, no filtering
+3. **Converge** — cluster into 3 strongest themes
+4. **Stress test** — what could go wrong with each?
+5. **Next step** — one concrete action
+
+Be direct and opinionated. Never end without a concrete recommendation.

package/src/gdskills/bundled/skills/planning/brainstorm/SKILL.codex.md

@@ -0,0 +1,90 @@
+---
+name: brainstorm
+description: "Structured brainstorming with multiple thinking perspectives (Pragmatist, Innovator, Critic). Generates ideas, evaluates trade-offs via comparison matrix, produces actionable recommendation. Use for architecture decisions, feature ideation, problem solving, tech choices, naming."
+triggers:
+  - "/brainstorm"
+  - "Brainstorm"
+  - "Let's think about"
+  - "What are options for"
+  - "How should we approach"
+  - "Compare approaches"
+metadata:
+  author: "MrCipherSmith"
+  version: "1.0.0"
+  category: "ideation"
+license: "MIT"
+compatibility: "cursor,codex,zed,opencode,claude"
+---
+
+# Brainstorm
+
+Structured brainstorming that explores a topic from multiple angles and converges on actionable options.
+
+## Arguments
+
+- `/brainstorm <topic>` — full brainstorm with 3 parallel agents
+- `/brainstorm --quick <topic>` — inline fast brainstorm (no agents, for simple decisions)
+- `/brainstorm --deep <topic>` — 5 agents (+Security Analyst, +UX Advocate)
+- `/brainstorm --code` — focus on code architecture (reads codebase for context)
+
+## Workflow
+
+### Step 1: Frame the Problem
+1. Restate the user's challenge in clear terms
+2. Identify constraints: technical, business, quality
+3. If in a project directory, scan codebase for relevant context
+
+### Step 2: Diverge — Generate Ideas (3 Parallel Agents)
+
+Launch 3 agents simultaneously:
+
+**Agent 1 — Pragmatist**
+> "Propose 2-3 solutions optimizing for speed of delivery, simplicity, and maintainability. Use boring, proven technology. For each: approach, pros/cons, effort (S/M/L)."
+
+**Agent 2 — Innovator**
+> "Propose 2-3 unconventional or cutting-edge solutions. Think new patterns, emerging tools, or approaches from other domains. For each: approach, pros/cons, effort."
+
+**Agent 3 — Critic**
+> "What are the hidden risks? What will break at scale? What will be painful to maintain? Produce 5-7 critical questions any solution must address."
+
+### Step 3: Converge — Synthesize
+
+```markdown
+## Ideas Map
+### Option A: [Name]
+**Approach:** ... | **Pros:** ... | **Cons:** ...
+**Effort:** S/M/L | **Risk:** Low/Med/High
+
+## Critical Questions
+(from Critic — apply to ALL options)
+
+## Comparison Matrix
+| Criteria        | Option A | Option B | Option C |
+|-----------------|----------|----------|----------|
+| Effort          | S        | M        | L        |
+| Risk            | Low      | Med      | High     |
+| Scalability     | ★★★      | ★★★★     | ★★★★★    |
+| Time to ship    | 1 week   | 3 weeks  | 6 weeks  |
+```
+
+### Step 4: Recommend
+1. **Recommended option** with reasoning
+2. **Runner-up** and when you'd pick it instead
+3. **Next steps** — concrete action items
+
+### Step 5: Discuss
+Offer to go deeper on any option or kick off `/feature-dev` / `/prd-creator`.
+
+## Quick Mode (--quick)
+Skip agents. Inline: 3-5 options in table, score each, recommend one.
+
+## Deep Mode (--deep)
+Add: **Security Analyst** (auth, data exposure, compliance) and **UX Advocate** (complexity, learning curve, accessibility).
+
+## Rules
+
+- Ground ideas in the project's actual tech stack and constraints
+- Include effort estimates — ideas without estimates aren't actionable
+- The Critic's questions must be answered by the recommendation
+- Don't dismiss "boring" solutions — they often win
+- End with concrete next steps, not just analysis

package/src/gdskills/bundled/skills/planning/brainstorm/SKILL.cursor.md

@@ -0,0 +1,90 @@
+---
+name: brainstorm
+description: "Structured brainstorming with multiple thinking perspectives (Pragmatist, Innovator, Critic). Generates ideas, evaluates trade-offs via comparison matrix, produces actionable recommendation. Use for architecture decisions, feature ideation, problem solving, tech choices, naming."
+triggers:
+  - "/brainstorm"
+  - "Brainstorm"
+  - "Let's think about"
+  - "What are options for"
+  - "How should we approach"
+  - "Compare approaches"
+metadata:
+  author: "MrCipherSmith"
+  version: "1.0.0"
+  category: "ideation"
+license: "MIT"
+compatibility: "cursor,codex,zed,opencode,claude"
+---
+
+# Brainstorm
+
+Structured brainstorming that explores a topic from multiple angles and converges on actionable options.
+
+## Arguments
+
+- `/brainstorm <topic>` — full brainstorm with 3 parallel agents
+- `/brainstorm --quick <topic>` — inline fast brainstorm (no agents, for simple decisions)
+- `/brainstorm --deep <topic>` — 5 agents (+Security Analyst, +UX Advocate)
+- `/brainstorm --code` — focus on code architecture (reads codebase for context)
+
+## Workflow
+
+### Step 1: Frame the Problem
+1. Restate the user's challenge in clear terms
+2. Identify constraints: technical, business, quality
+3. If in a project directory, scan codebase for relevant context
+
+### Step 2: Diverge — Generate Ideas (3 Parallel Agents)
+
+Launch 3 agents simultaneously:
+
+**Agent 1 — Pragmatist**
+> "Propose 2-3 solutions optimizing for speed of delivery, simplicity, and maintainability. Use boring, proven technology. For each: approach, pros/cons, effort (S/M/L)."
+
+**Agent 2 — Innovator**
+> "Propose 2-3 unconventional or cutting-edge solutions. Think new patterns, emerging tools, or approaches from other domains. For each: approach, pros/cons, effort."
+
+**Agent 3 — Critic**
+> "What are the hidden risks? What will break at scale? What will be painful to maintain? Produce 5-7 critical questions any solution must address."
+
+### Step 3: Converge — Synthesize
+
+```markdown
+## Ideas Map
+### Option A: [Name]
+**Approach:** ... | **Pros:** ... | **Cons:** ...
+**Effort:** S/M/L | **Risk:** Low/Med/High
+
+## Critical Questions
+(from Critic — apply to ALL options)
+
+## Comparison Matrix
+| Criteria        | Option A | Option B | Option C |
+|-----------------|----------|----------|----------|
+| Effort          | S        | M        | L        |
+| Risk            | Low      | Med      | High     |
+| Scalability     | ★★★      | ★★★★     | ★★★★★    |
+| Time to ship    | 1 week   | 3 weeks  | 6 weeks  |
+```
+
+### Step 4: Recommend
+1. **Recommended option** with reasoning
+2. **Runner-up** and when you'd pick it instead
+3. **Next steps** — concrete action items
+
+### Step 5: Discuss
+Offer to go deeper on any option or kick off `/feature-dev` / `/prd-creator`.
+
+## Quick Mode (--quick)
+Skip agents. Inline: 3-5 options in table, score each, recommend one.
+
+## Deep Mode (--deep)
+Add: **Security Analyst** (auth, data exposure, compliance) and **UX Advocate** (complexity, learning curve, accessibility).
+
+## Rules
+
+- Ground ideas in the project's actual tech stack and constraints
+- Include effort estimates — ideas without estimates aren't actionable
+- The Critic's questions must be answered by the recommendation
+- Don't dismiss "boring" solutions — they often win
+- End with concrete next steps, not just analysis

package/src/gdskills/bundled/skills/planning/brainstorm/SKILL.md

@@ -0,0 +1,90 @@
+---
+name: brainstorm
+description: "Use when exploring architecture decisions, tech choices, feature ideas, or any open-ended problem that benefits from multiple perspectives."
+triggers:
+  - "/brainstorm"
+  - "Brainstorm"
+  - "Let's think about"
+  - "What are options for"
+  - "How should we approach"
+  - "Compare approaches"
+metadata:
+  author: "MrCipherSmith"
+  version: "1.0.0"
+  category: "ideation"
+license: "MIT"
+compatibility: "cursor,codex,zed,opencode,claude"
+---
+
+# Brainstorm
+
+Structured brainstorming that explores a topic from multiple angles and converges on actionable options.
+
+## Arguments
+
+- `/brainstorm <topic>` — full brainstorm with 3 parallel agents
+- `/brainstorm --quick <topic>` — inline fast brainstorm (no agents, for simple decisions)
+- `/brainstorm --deep <topic>` — 5 agents (+Security Analyst, +UX Advocate)
+- `/brainstorm --code` — focus on code architecture (reads codebase for context)
+
+## Workflow
+
+### Step 1: Frame the Problem
+1. Restate the user's challenge in clear terms
+2. Identify constraints: technical, business, quality
+3. If in a project directory, scan codebase for relevant context
+
+### Step 2: Diverge — Generate Ideas (3 Parallel Agents)
+
+Launch 3 agents simultaneously:
+
+**Agent 1 — Pragmatist**
+> "Propose 2-3 solutions optimizing for speed of delivery, simplicity, and maintainability. Use boring, proven technology. For each: approach, pros/cons, effort (S/M/L)."
+
+**Agent 2 — Innovator**
+> "Propose 2-3 unconventional or cutting-edge solutions. Think new patterns, emerging tools, or approaches from other domains. For each: approach, pros/cons, effort."
+
+**Agent 3 — Critic**
+> "What are the hidden risks? What will break at scale? What will be painful to maintain? Produce 5-7 critical questions any solution must address."
+
+### Step 3: Converge — Synthesize
+
+```markdown
+## Ideas Map
+### Option A: [Name]
+**Approach:** ... | **Pros:** ... | **Cons:** ...
+**Effort:** S/M/L | **Risk:** Low/Med/High
+
+## Critical Questions
+(from Critic — apply to ALL options)
+
+## Comparison Matrix
+| Criteria        | Option A | Option B | Option C |
+|-----------------|----------|----------|----------|
+| Effort          | S        | M        | L        |
+| Risk            | Low      | Med      | High     |
+| Scalability     | ★★★      | ★★★★     | ★★★★★    |
+| Time to ship    | 1 week   | 3 weeks  | 6 weeks  |
+```
+
+### Step 4: Recommend
+1. **Recommended option** with reasoning
+2. **Runner-up** and when you'd pick it instead
+3. **Next steps** — concrete action items
+
+### Step 5: Discuss
+Offer to go deeper on any option or kick off `/feature-dev` / `/prd-creator`.
+
+## Quick Mode (--quick)
+Skip agents. Inline: 3-5 options in table, score each, recommend one.
+
+## Deep Mode (--deep)
+Add: **Security Analyst** (auth, data exposure, compliance) and **UX Advocate** (complexity, learning curve, accessibility).
+
+## Rules
+
+- Ground ideas in the project's actual tech stack and constraints
+- Include effort estimates — ideas without estimates aren't actionable
+- The Critic's questions must be answered by the recommendation
+- Don't dismiss "boring" solutions — they often win
+- End with concrete next steps, not just analysis

package/src/gdskills/bundled/skills/planning/consistency-checker/SKILL.codex.md

@@ -0,0 +1,33 @@
+---
+name: gproject-consistency-checker
+description: "Validates PRD against decisions registry, architecture doc, and best practices constraints. Adversarial quality gate. Use when: dispatched by gproject-orchestrator Phase 5."
+triggers:
+  - "gproject-consistency-checker: validate PRD"
+  - "Dispatched by gproject-orchestrator Phase 5"
+metadata:
+  author: "MrCipherSmith"
+  version: "1.0.0"
+  category: "planning"
+license: "MIT"
+compatibility: "cursor,codex,zed,opencode"
+---
+
+
+# gproject-consistency-checker
+
+## Purpose
+
+Quality gate before human approval. Systematically verify that the PRD
+is internally consistent and fully aligned with all upstream decisions.
+This agent is adversarial — its job is to find problems, not to approve.
+
+## Iron Laws
+
+| # | Law |
+|---|-----|
+| 1 | Check EVERY decision in decisions.md against PRD — no sampling |
+| 2 | Check EVERY MUST constraint in tech-bestpractices.md against PRD |
+| 3 | Report ALL violations — don't stop at the first one |
+| 4 | Classify severity: CRITICAL (blocks approval) / WARNING (should fix) / INFO (suggestion) |
+| 5 | NEVER fix violations yourself — only report them |
+| 6 | A clean report still lists what was checked (audit trail) |

package/src/gdskills/bundled/skills/planning/consistency-checker/SKILL.cursor.md

@@ -0,0 +1,33 @@
+---
+name: gproject-consistency-checker
+description: "Validates PRD against decisions registry, architecture doc, and best practices constraints. Adversarial quality gate. Use when: dispatched by gproject-orchestrator Phase 5."
+triggers:
+  - "gproject-consistency-checker: validate PRD"
+  - "Dispatched by gproject-orchestrator Phase 5"
+metadata:
+  author: "MrCipherSmith"
+  version: "1.0.0"
+  category: "planning"
+license: "MIT"
+compatibility: "cursor,codex,zed,opencode"
+---
+
+
+# gproject-consistency-checker
+
+## Purpose
+
+Quality gate before human approval. Systematically verify that the PRD
+is internally consistent and fully aligned with all upstream decisions.
+This agent is adversarial — its job is to find problems, not to approve.
+
+## Iron Laws
+
+| # | Law |
+|---|-----|
+| 1 | Check EVERY decision in decisions.md against PRD — no sampling |
+| 2 | Check EVERY MUST constraint in tech-bestpractices.md against PRD |
+| 3 | Report ALL violations — don't stop at the first one |
+| 4 | Classify severity: CRITICAL (blocks approval) / WARNING (should fix) / INFO (suggestion) |
+| 5 | NEVER fix violations yourself — only report them |
+| 6 | A clean report still lists what was checked (audit trail) |