@hivehub/rulebook 5.4.1 → 5.5.0

package/templates/skills/core/documentation-rules/SKILL.md

@@ -1,47 +1,47 @@
----
-name: "Documentation Rules"
-description: "All documentation in English. Root README concise, detailed docs in `/docs`."
-version: "1.0.0"
-category: "core"
-author: "Rulebook"
-tags: ["core"]
-dependencies: []
-conflicts: []
----
-# Documentation Standards
-
-**CRITICAL**: All documentation in English. Root README concise, detailed docs in `/docs`.
-
-## Structure
-
-**Root-Level (ONLY):**
-- `README.md` - Overview + quick start
-- `CHANGELOG.md` - Version history
-- `AGENTS.md` - AI instructions
-- `LICENSE`, `CONTRIBUTING.md`, `SECURITY.md`
-
-**All Other Docs in `/docs`:**
-- `ARCHITECTURE.md`, `DEVELOPMENT.md`, `ROADMAP.md`
-- `specs/`, `guides/`, `diagrams/`, `benchmarks/`
-
-## Update Requirements by Commit Type
-
-| Type | Update |
-|------|--------|
-| `feat` | README features, API docs, CHANGELOG "Added" |
-| `fix` | Troubleshooting, CHANGELOG "Fixed" |
-| `breaking` | CHANGELOG + migration guide, version docs |
-| `perf` | Benchmarks, CHANGELOG "Performance" |
-| `security` | SECURITY.md, CHANGELOG "Security" |
-| `docs` | Verify spelling/links only |
-| `refactor` | Update if behavior changed |
-
-## Quality Checks (CI/CD)
-
-```bash
-markdownlint **/*.md         # Lint markdown
-markdown-link-check **/*.md  # Check links
-codespell **/*.md            # Spell check
-```
-
+---
+name: "Documentation Rules"
+description: "All documentation in English. Root README concise, detailed docs in `/docs`."
+version: "1.0.0"
+category: "core"
+author: "Rulebook"
+tags: ["core"]
+dependencies: []
+conflicts: []
+---
+# Documentation Standards
+
+**CRITICAL**: All documentation in English. Root README concise, detailed docs in `/docs`.
+
+## Structure
+
+**Root-Level (ONLY):**
+- `README.md` - Overview + quick start
+- `CHANGELOG.md` - Version history
+- `AGENTS.md` - AI instructions
+- `LICENSE`, `CONTRIBUTING.md`, `SECURITY.md`
+
+**All Other Docs in `/docs`:**
+- `ARCHITECTURE.md`, `DEVELOPMENT.md`, `ROADMAP.md`
+- `specs/`, `guides/`, `diagrams/`, `benchmarks/`
+
+## Update Requirements by Commit Type
+
+| Type | Update |
+|------|--------|
+| `feat` | README features, API docs, CHANGELOG "Added" |
+| `fix` | Troubleshooting, CHANGELOG "Fixed" |
+| `breaking` | CHANGELOG + migration guide, version docs |
+| `perf` | Benchmarks, CHANGELOG "Performance" |
+| `security` | SECURITY.md, CHANGELOG "Security" |
+| `docs` | Verify spelling/links only |
+| `refactor` | Update if behavior changed |
+
+## Quality Checks (CI/CD)
+
+```bash
+markdownlint **/*.md         # Lint markdown
+markdown-link-check **/*.md  # Check links
+codespell **/*.md            # Spell check
+```
+
 **MUST pass before commit** (see AGENT_AUTOMATION).

package/templates/skills/core/karpathy-guidelines/SKILL.md

@@ -0,0 +1,93 @@
+---
+name: "Karpathy Guidelines"
+description: "Behavioral guidelines to reduce common LLM coding mistakes — overcomplication, sloppy refactors, hidden assumptions, weak goals. Use when writing, reviewing, or refactoring code. Auto-applies; invoke explicitly via /karpathy-guidelines or 'follow karpathy discipline'."
+version: "1.0.0"
+category: "core"
+author: "Andrej Karpathy (originator) / forrestchang (skill packaging) / Rulebook (Rulebook adaptation)"
+tags: ["core", "discipline", "quality"]
+dependencies: []
+conflicts: []
+license: "MIT"
+upstream: "https://github.com/forrestchang/andrej-karpathy-skills"
+source: "https://x.com/karpathy/status/2015883857489522876"
+---
+<!-- KARPATHY_GUIDELINES:START -->
+# Karpathy Guidelines
+
+Behavioral guidelines to reduce common LLM coding mistakes, derived from [Andrej Karpathy's observations](https://x.com/karpathy/status/2015883857489522876) on LLM coding pitfalls.
+
+**Tradeoff:** these guidelines bias toward caution over speed. For trivial tasks, use judgment.
+
+## 1. Think Before Coding
+
+**Don't assume. Don't hide confusion. Surface tradeoffs.**
+
+Before implementing:
+
+- State your assumptions explicitly. If uncertain, ask.
+- If multiple interpretations exist, present them — don't pick silently.
+- If a simpler approach exists, say so. Push back when warranted.
+- If something is unclear, stop. Name what's confusing. Ask.
+
+## 2. Simplicity First
+
+**Minimum code that solves the problem. Nothing speculative.**
+
+- No features beyond what was asked.
+- No abstractions for single-use code.
+- No "flexibility" or "configurability" that wasn't requested.
+- No error handling for impossible scenarios.
+- If you write 200 lines and it could be 50, rewrite it.
+
+Ask yourself: "would a senior engineer say this is overcomplicated?" If yes, simplify.
+
+## 3. Surgical Changes
+
+**Touch only what you must. Clean up only your own mess.**
+
+When editing existing code:
+
+- Don't "improve" adjacent code, comments, or formatting.
+- Don't refactor things that aren't broken.
+- Match existing style, even if you'd do it differently.
+- If you notice unrelated dead code, mention it — don't delete it.
+
+When your changes create orphans:
+
+- Remove imports/variables/functions that YOUR changes made unused.
+- Don't remove pre-existing dead code unless asked.
+
+The test: every changed line should trace directly to the user's request.
+
+## 4. Goal-Driven Execution
+
+**Define success criteria. Loop until verified.**
+
+Transform tasks into verifiable goals:
+
+- "Add validation" → "write tests for invalid inputs, then make them pass."
+- "Fix the bug" → "write a test that reproduces it, then make it pass."
+- "Refactor X" → "ensure tests pass before and after."
+
+For multi-step tasks, state a brief plan:
+
+```
+1. [Step] → verify: [check]
+2. [Step] → verify: [check]
+3. [Step] → verify: [check]
+```
+
+Strong success criteria let you loop independently. Weak criteria ("make it work") require constant clarification.
+
+## Interaction with Rulebook
+
+This skill complements existing Rulebook rules:
+
+- `no-shortcuts.md` forbids stubs/TODOs; **Simplicity First** forbids the opposite — bloat.
+- `research-first.md` requires investigating unknowns; **Think Before Coding** adds *surfacing* what was investigated.
+- `incremental-implementation.md` tests each step; **Goal-Driven Execution** adds defining the test up front.
+- **Surgical Changes** has no Rulebook counterpart and fills a real gap: no rule today forbids opportunistic refactor of adjacent code.
+
+Skill body is deliberately small (≤80 lines) so it adds < 1KB to the context budget per session.
+
+<!-- KARPATHY_GUIDELINES:END -->

package/templates/skills/core/quality-enforcement/SKILL.md

@@ -1,78 +1,78 @@
----
-name: "Quality Enforcement"
-description: "These rules are NON-NEGOTIABLE and MUST be followed without exception."
-version: "1.0.0"
-category: "core"
-author: "Rulebook"
-tags: ["core"]
-dependencies: []
-conflicts: []
----
-<!-- QUALITY_ENFORCEMENT:START -->
-# Quality Enforcement Rules
-
-**CRITICAL**: These rules are NON-NEGOTIABLE and MUST be followed without exception.
-
-## Absolute Prohibitions
-
-### Test Bypassing - STRICTLY FORBIDDEN
-- NEVER use .skip(), .only(), or .todo() to bypass failing tests
-- NEVER comment out failing tests
-- NEVER use @ts-ignore, @ts-expect-error, or similar to hide test errors
-- NEVER mock/stub functionality just to make tests pass without fixing root cause
-- FIX the actual problem causing test failures
-
-### Git Hook Bypassing - STRICTLY FORBIDDEN  
-- NEVER use --no-verify flag on git commit
-- NEVER use --no-verify flag on git push
-- NEVER disable or skip pre-commit hooks
-- NEVER disable or skip pre-push hooks
-- FIX the issues that hooks are detecting
-
-### Test Implementation - STRICTLY FORBIDDEN
-- NEVER create boilerplate tests that don't actually test behavior
-- NEVER write tests that always pass regardless of implementation
-- NEVER write tests without assertions
-- NEVER mock everything to avoid testing real behavior
-- WRITE meaningful tests that verify actual functionality
-
-### Problem Solving Approach - REQUIRED
-- DO NOT seek the simplest bypass or workaround
-- DO NOT be creative with shortcuts that compromise quality
-- DO solve problems properly following best practices
-- DO use proven, established solutions from decades of experience
-- DO fix root causes, not symptoms
-
-### Temporary Files and Scripts - STRICTLY FORBIDDEN
-- **NEVER** create temporary files in project root or any directory outside `/scripts`
-- **NEVER** create test files, log files, or debug files outside `/scripts`
-- **NEVER** leave temporary files after use - they MUST be deleted immediately
-- **ALWAYS** create all scripts inside `/scripts` directory
-- **ALWAYS** remove temporary files immediately after use (MANDATORY)
-- **ALWAYS** clean up test artifacts, log files, and debug files before committing
-- **ALWAYS** use `/scripts` directory for any temporary scripts or test files
-
-**Why This Matters:**
-LLM assistants often create temporary files for testing but forget to remove them, accumulating dozens of junk files that pollute the repository. All temporary work MUST be done in `/scripts` and cleaned up immediately.
-
-**Examples:**
-- ❌ Creating `test.js`, `debug.log`, `temp.json` in project root
-- ❌ Leaving test files after debugging
-- ❌ Creating scripts outside `/scripts` directory
-- ✅ Creating `/scripts/test-feature.js` and removing it after use
-- ✅ Using `/scripts` for all temporary work
-- ✅ Cleaning up all temporary files before committing
-
-## Enforcement
-
-These rules apply to ALL implementations:
-- Bug fixes
-- New features  
-- Refactoring
-- Documentation changes
-- Any code modifications
-
-**Violation = Implementation Rejected**
-
-<!-- QUALITY_ENFORCEMENT:END -->
-
+---
+name: "Quality Enforcement"
+description: "These rules are NON-NEGOTIABLE and MUST be followed without exception."
+version: "1.0.0"
+category: "core"
+author: "Rulebook"
+tags: ["core"]
+dependencies: []
+conflicts: []
+---
+<!-- QUALITY_ENFORCEMENT:START -->
+# Quality Enforcement Rules
+
+**CRITICAL**: These rules are NON-NEGOTIABLE and MUST be followed without exception.
+
+## Absolute Prohibitions
+
+### Test Bypassing - STRICTLY FORBIDDEN
+- NEVER use .skip(), .only(), or .todo() to bypass failing tests
+- NEVER comment out failing tests
+- NEVER use @ts-ignore, @ts-expect-error, or similar to hide test errors
+- NEVER mock/stub functionality just to make tests pass without fixing root cause
+- FIX the actual problem causing test failures
+
+### Git Hook Bypassing - STRICTLY FORBIDDEN  
+- NEVER use --no-verify flag on git commit
+- NEVER use --no-verify flag on git push
+- NEVER disable or skip pre-commit hooks
+- NEVER disable or skip pre-push hooks
+- FIX the issues that hooks are detecting
+
+### Test Implementation - STRICTLY FORBIDDEN
+- NEVER create boilerplate tests that don't actually test behavior
+- NEVER write tests that always pass regardless of implementation
+- NEVER write tests without assertions
+- NEVER mock everything to avoid testing real behavior
+- WRITE meaningful tests that verify actual functionality
+
+### Problem Solving Approach - REQUIRED
+- DO NOT seek the simplest bypass or workaround
+- DO NOT be creative with shortcuts that compromise quality
+- DO solve problems properly following best practices
+- DO use proven, established solutions from decades of experience
+- DO fix root causes, not symptoms
+
+### Temporary Files and Scripts - STRICTLY FORBIDDEN
+- **NEVER** create temporary files in project root or any directory outside `/scripts`
+- **NEVER** create test files, log files, or debug files outside `/scripts`
+- **NEVER** leave temporary files after use - they MUST be deleted immediately
+- **ALWAYS** create all scripts inside `/scripts` directory
+- **ALWAYS** remove temporary files immediately after use (MANDATORY)
+- **ALWAYS** clean up test artifacts, log files, and debug files before committing
+- **ALWAYS** use `/scripts` directory for any temporary scripts or test files
+
+**Why This Matters:**
+LLM assistants often create temporary files for testing but forget to remove them, accumulating dozens of junk files that pollute the repository. All temporary work MUST be done in `/scripts` and cleaned up immediately.
+
+**Examples:**
+- ❌ Creating `test.js`, `debug.log`, `temp.json` in project root
+- ❌ Leaving test files after debugging
+- ❌ Creating scripts outside `/scripts` directory
+- ✅ Creating `/scripts/test-feature.js` and removing it after use
+- ✅ Using `/scripts` for all temporary work
+- ✅ Cleaning up all temporary files before committing
+
+## Enforcement
+
+These rules apply to ALL implementations:
+- Bug fixes
+- New features  
+- Refactoring
+- Documentation changes
+- Any code modifications
+
+**Violation = Implementation Rejected**
+
+<!-- QUALITY_ENFORCEMENT:END -->
+