@hivehub/rulebook 5.8.1 → 6.0.0

package/templates/skills/cli/opencode/SKILL.md

@@ -1,82 +0,0 @@
----
-name: "Opencode"
-description: "OpenCode (open-source terminal coding agent by SST). Reads AGENTS.md natively. Rulebook generates opencode.json plus .opencode/commands, .opencode/agents, .opencode/skills."
-version: "1.0.0"
-category: "cli"
-author: "Rulebook"
-tags: ["cli", "opencode", "agents", "mcp"]
-dependencies: []
-conflicts: []
----
-<!-- OPENCODE:START -->
-# OpenCode Rules
-
-**Tool**: [OpenCode](https://opencode.ai) — open-source terminal coding agent.
-
-## Generated surface area
-
-When Rulebook detects OpenCode (`opencode.json` / `.opencode/` / `opencode`
-binary on PATH), it generates:
-
-- `opencode.json` with `$schema`, `mcp.rulebook`, and `instructions`.
-  Existing user keys (model, theme, permission, custom agents) are preserved.
-- `.opencode/commands/<name>.md` for every user-invocable Rulebook slash
-  command, with OpenCode-shaped frontmatter (`description`).
-- `.opencode/agents/<role>.md` for every Rulebook role agent
-  (researcher, implementer, tester, code-reviewer, architect, docs-writer,
-  security-reviewer, build-engineer, team-lead, etc.) with model tier
-  mapped (`haiku → claude-haiku-4-5`, `sonnet → claude-sonnet-4-6`,
-  `opus → claude-opus-4-7`) and a synthesized `permission` block.
-- `.opencode/skills/<normalized-name>/SKILL.md` for every Rulebook dev
-  skill, name-normalized to `[a-z0-9](-[a-z0-9])*` (≤64 chars) and
-  description bounded to ≤1024 chars.
-- `.opencode/.rulebook-managed.json` — sidecar listing managed keys so
-  `rulebook update` knows what to refresh vs. preserve.
-
-## Idempotency
-
-Files carrying the `<!-- RULEBOOK:START -->` marker are managed and
-refreshed on every `rulebook update`. Files without the marker are
-treated as user-owned and left untouched.
-
-## Sequential editing
-
-OpenCode follows the same Rulebook discipline as Claude Code:
-
-- Edit files one at a time.
-- For 3+ files, decompose into 1–2 file sub-tasks.
-- Diagnostic-first: type-check / lint before tests.
-
-## Quality gates
-
-- Type-check / lint must be clean.
-- Tests must pass.
-- Coverage ≥95%.
-- Pre-commit hooks enforce these — never `--no-verify`.
-
-## MCP
-
-`mcp.rulebook` in `opencode.json` exposes `rulebook_task_*`,
-`rulebook_memory_*`, `rulebook_decision_*`, `rulebook_knowledge_*`,
-`rulebook_learn_*`. Prefer MCP tools over shell commands when both
-exist.
-
-## Workflow
-
-1. Reference `AGENTS.md` and `.rulebook/specs/*.md`.
-2. Use `/rulebook-task-create`, `/rulebook-task-list`, `/handoff`.
-3. Delegate to role agents (`@researcher`, `@implementer`, `@tester`).
-4. Run quality checks before committing.
-5. Save learnings (`rulebook_memory_save`, `rulebook_knowledge_add`).
-
-## Documentation
-
-- [opencode.ai/docs/rules](https://opencode.ai/docs/rules/)
-- [opencode.ai/docs/config](https://opencode.ai/docs/config/)
-- [opencode.ai/docs/mcp-servers](https://opencode.ai/docs/mcp-servers/)
-- [opencode.ai/docs/commands](https://opencode.ai/docs/commands/)
-- [opencode.ai/docs/agents](https://opencode.ai/docs/agents/)
-- [opencode.ai/docs/skills](https://opencode.ai/docs/skills/)
-- [opencode.ai/docs/permissions](https://opencode.ai/docs/permissions/)
-
-<!-- OPENCODE:END -->

package/templates/skills/ides/copilot/SKILL.md

@@ -1,47 +0,0 @@
----
-name: "Copilot"
-description: "Tool: GitHub's AI pair programmer (inline + chat)"
-version: "1.0.0"
-category: "ides"
-author: "Rulebook"
-tags: ["ides", "ide"]
-dependencies: []
-conflicts: []
----
-<!-- COPILOT:START -->
-# GitHub Copilot Rules
-
-**Tool**: GitHub's AI pair programmer (inline + chat)
-
-## Quick Start
-
-Copilot reads:
-- `.github/copilot-instructions.md` (generated by `rulebook init`)
-- Workspace context (open files)
-
-## Usage
-
-```bash
-# In Copilot Chat:
-"Follow @AGENTS.md. Implement [feature] with tests (95%+ coverage)."
-
-# Inline suggestions:
-Accept/reject based on AGENTS.md standards
-```
-
-## Modes
-
-**Inline Completions**: Context-aware suggestions while typing
-**Copilot Chat**: Ask questions, request implementations
-**Workspace Agent** (Labs): Multi-file autonomous mode
-
-## Workflow
-
-1. Rulebook generates `.github/copilot-instructions.md` → references AGENTS.md
-2. Keep AGENTS.md open for context
-3. Use `@workspace` to include project context
-4. Reference `@AGENTS.md` explicitly in chat
-
-**Critical**: Generated `copilot-instructions.md` points Copilot to AGENTS.md standards.
-
-<!-- COPILOT:END -->

package/templates/skills/ides/cursor/SKILL.md

@@ -1,53 +0,0 @@
----
-name: "Cursor"
-description: "IDE: AI-first code editor with Agent mode and Composer"
-version: "1.0.0"
-category: "ides"
-author: "Rulebook"
-tags: ["ides", "ide"]
-dependencies: []
-conflicts: []
----
-<!-- CURSOR:START -->
-# Cursor IDE Rules
-
-**IDE**: AI-first code editor with Agent mode and Composer
-
-## Quick Start
-
-Cursor automatically reads:
-- `.cursorrules` (generated by `rulebook init`)
-- `AGENTS.md` (via `@AGENTS.md` references)
-
-## Usage
-
-```bash
-# In Cursor chat/composer:
-"Follow @AGENTS.md. Implement [feature] with tests (95%+ coverage)."
-
-# Agent mode (Ctrl+Shift+K):
-Use for complex multi-file changes
-Reference @AGENTS.md for standards
-
-# Composer (Cmd+I):
-Use for quick edits
-Reference @AGENTS.md when needed
-```
-
-## Features
-
-- **Auto-context**: Reads .cursorrules automatically
-- **@ Mentions**: Use `@AGENTS.md` to include standards
-- **Agent Mode**: Autonomous multi-step implementations
-- **Composer**: Quick inline edits
-
-## Workflow
-
-1. Rulebook generates `.cursorrules` pointing to AGENTS.md
-2. Use `@AGENTS.md` in prompts for explicit reference
-3. Agent/Composer follows standards automatically
-4. Review changes and run quality checks
-
-**Critical**: `.cursorrules` ensures Cursor follows AGENTS.md by default.
-
-<!-- CURSOR:END -->

package/templates/skills/ides/jetbrains-ai/SKILL.md

@@ -1,45 +0,0 @@
----
-name: "JetBrains AI"
-description: "IDEs: IntelliJ, PyCharm, WebStorm, GoLand, RustRover, Rider, CLion, PhpStorm"
-version: "1.0.0"
-category: "ides"
-author: "Rulebook"
-tags: ["ides", "ide"]
-dependencies: []
-conflicts: []
----
-<!-- JETBRAINS_AI:START -->
-# JetBrains AI Assistant Rules
-
-**IDEs**: IntelliJ, PyCharm, WebStorm, GoLand, RustRover, Rider, CLion, PhpStorm
-
-## Quick Start
-
-JetBrains AI reads workspace files automatically.
-
-## Usage
-
-```bash
-# In AI Assistant chat:
-"Follow @AGENTS.md. Implement [feature] with tests (95%+ coverage)."
-
-# Keep AGENTS.md open for AI to reference
-```
-
-## Features
-
-- **AI Chat**: Full conversation mode
-- **Inline Suggestions**: Context-aware completions
-- **Refactoring**: AI-powered code improvements
-- **Test Generation**: Automated test creation
-
-## Workflow
-
-1. Keep AGENTS.md open in editor
-2. Use AI Chat with "@AGENTS.md" references
-3. Review suggested changes
-4. Run IDE quality checks (built-in linters, tests)
-
-**Critical**: Keep AGENTS.md open for AI Assistant to include standards in context.
-
-<!-- JETBRAINS_AI:END -->

package/templates/skills/ides/replit/SKILL.md

@@ -1,46 +0,0 @@
----
-name: "Replit"
-description: "Tool: Cloud IDE with Ghostwriter AI"
-version: "1.0.0"
-category: "ides"
-author: "Rulebook"
-tags: ["ides", "ide"]
-dependencies: []
-conflicts: []
----
-<!-- REPLIT:START -->
-# Replit IDE Rules
-
-**Tool**: Cloud IDE with Ghostwriter AI
-
-## Quick Start
-
-Replit Ghostwriter reads workspace files automatically.
-
-## Usage
-
-```bash
-# In Ghostwriter chat:
-"Follow @AGENTS.md. Implement [feature] with tests."
-
-# Inline completions:
-Accept/reject based on AGENTS.md standards
-```
-
-## Features
-
-- **Ghostwriter Chat**: AI assistant
-- **Inline Completions**: Code suggestions
-- **Explain Code**: AI explanations
-- **Generate Code**: Full implementations
-
-## Workflow
-
-1. Keep AGENTS.md in workspace (Ghostwriter reads it)
-2. Reference `@AGENTS.md` in chat
-3. Review suggestions
-4. Run tests in Replit console
-
-**Critical**: Ghostwriter has workspace context - AGENTS.md is automatically available.
-
-<!-- REPLIT:END -->

package/templates/skills/ides/tabnine/SKILL.md

@@ -1,39 +0,0 @@
----
-name: "Tabnine"
-description: "Tool: Multi-IDE AI completion with team learning"
-version: "1.0.0"
-category: "ides"
-author: "Rulebook"
-tags: ["ides", "ide"]
-dependencies: []
-conflicts: []
----
-<!-- TABNINE:START -->
-# Tabnine AI Rules
-
-**Tool**: Multi-IDE AI completion with team learning
-
-## Quick Start
-
-Works in: VS Code, JetBrains, Vim, Sublime, Atom, Emacs
-
-## Usage
-
-Tabnine learns from your codebase automatically. Keep AGENTS.md in workspace for team learning.
-
-## Features
-
-- **Inline Completions**: AI-powered code suggestions
-- **Team Learning**: Learns from team patterns
-- **Multi-IDE**: Consistent across all editors
-
-## Workflow
-
-1. Keep AGENTS.md in project root
-2. Tabnine learns standards from codebase
-3. Accept/reject suggestions based on AGENTS.md patterns
-4. Team model improves over time
-
-**Critical**: Tabnine learns from existing code - maintain AGENTS.md standards in all files.
-
-<!-- TABNINE:END -->

package/templates/skills/ides/vscode/SKILL.md

@@ -1,50 +0,0 @@
----
-name: "VS Code"
-description: "IDE: VS Code with Copilot, Cody, Continue, or other AI extensions"
-version: "1.0.0"
-category: "ides"
-author: "Rulebook"
-tags: ["ides", "ide"]
-dependencies: []
-conflicts: []
----
-<!-- VSCODE:START -->
-# VS Code AI Extensions Rules
-
-**IDE**: VS Code with Copilot, Cody, Continue, or other AI extensions
-
-## Quick Start
-
-VS Code reads:
-- `.vscode/settings.json` (generated by `rulebook init`)
-- `.vscode/copilot-instructions.md` (if Copilot enabled)
-
-## Usage
-
-```bash
-# In any AI chat/extension:
-"Follow @AGENTS.md. Implement [feature] with tests (95%+ coverage)."
-
-# Keep AGENTS.md open for context
-# Extensions will reference it automatically
-```
-
-## Supported Extensions
-
-- GitHub Copilot
-- Cody
-- Continue
-- Codeium
-- Tabnine
-- Amazon Q
-
-## Workflow
-
-1. Rulebook generates `.vscode/settings.json` and `copilot-instructions.md`
-2. Keep AGENTS.md open in workspace
-3. Reference `@AGENTS.md` in extension prompts
-4. Extensions read workspace context automatically
-
-**Critical**: Generated settings point extensions to AGENTS.md standards.
-
-<!-- VSCODE:END -->

package/templates/skills/ides/windsurf/SKILL.md

@@ -1,46 +0,0 @@
----
-name: "Windsurf"
-description: "IDE: AI-powered editor with Cascade AI and Flow State"
-version: "1.0.0"
-category: "ides"
-author: "Rulebook"
-tags: ["ides", "ide"]
-dependencies: []
-conflicts: []
----
-<!-- WINDSURF:START -->
-# Windsurf IDE Rules
-
-**IDE**: AI-powered editor with Cascade AI and Flow State
-
-## Quick Start
-
-Windsurf reads:
-- `.windsurfrules` (generated by `rulebook init`)
-- AGENTS.md (when open in workspace)
-
-## Usage
-
-```bash
-# In Windsurf chat:
-"Follow @AGENTS.md. Implement [feature] with tests."
-
-# Cascade AI:
-Multi-file autonomous mode
-Reference @AGENTS.md for standards
-
-# Flow State:
-Inline suggestions
-Context-aware completions
-```
-
-## Workflow
-
-1. Rulebook generates `.windsurfrules` → points to AGENTS.md
-2. Keep AGENTS.md open in workspace
-3. Use Cascade for complex tasks with `@AGENTS.md` references
-4. Flow State provides inline suggestions
-
-**Critical**: `.windsurfrules` ensures standards are followed automatically.
-
-<!-- WINDSURF:END -->

package/templates/skills/ides/zed/SKILL.md

@@ -1,42 +0,0 @@
----
-name: "Zed"
-description: "Tool: High-performance collaborative editor (Rust-powered)"
-version: "1.0.0"
-category: "ides"
-author: "Rulebook"
-tags: ["ides", "ide"]
-dependencies: []
-conflicts: []
----
-<!-- ZED:START -->
-# Zed Editor Rules
-
-**Tool**: High-performance collaborative editor (Rust-powered)
-
-## Quick Start
-
-Zed reads workspace files for AI context.
-
-## Usage
-
-```bash
-# In Zed AI assistant:
-"Follow @AGENTS.md. Implement [feature] with tests."
-```
-
-## Features
-
-- **AI Assistant**: Inline chat
-- **Collaborative Editing**: Real-time collaboration
-- **Fast Performance**: Rust-based, instant responsiveness
-
-## Workflow
-
-1. Keep AGENTS.md open in workspace
-2. Use AI assistant with `@AGENTS.md` references
-3. Review suggestions
-4. Run quality checks in terminal
-
-**Critical**: Zed's AI reads open files - keep AGENTS.md accessible.
-
-<!-- ZED:END -->