fix: curate everything-claude-code skill output

This commit is contained in:
Affaan Mustafa
2026-03-10 19:36:12 -07:00
committed by Affaan Mustafa
parent 65cb240e88
commit c883289abb
2 changed files with 165 additions and 770 deletions

View File

@@ -1,458 +1,12 @@
# Instincts generated from https://github.com/affaan-m/everything-claude-code
# Generated: 2026-03-04T22:56:16.069Z
# Version: 2.0
---
id: everything-claude-code-commit-length
trigger: "when writing a commit message"
confidence: 0.6
domain: git
source: repo-analysis
source_repo: https://github.com/affaan-m/everything-claude-code
---
# Everything Claude Code Commit Length
## Action
Write moderate-length commit messages (~50 characters)
## Evidence
- Average commit message length: 70 chars
- Based on 200 commits
---
id: everything-claude-code-naming-files
trigger: "when creating a new file"
confidence: 0.8
domain: code-style
source: repo-analysis
source_repo: https://github.com/affaan-m/everything-claude-code
---
# Everything Claude Code Naming Files
## Action
Use camelCase naming convention
## Evidence
- Analyzed file naming patterns in repository
- Dominant pattern: camelCase
---
id: everything-claude-code-export-style
trigger: "when exporting from a module"
confidence: 0.7
domain: code-style
source: repo-analysis
source_repo: https://github.com/affaan-m/everything-claude-code
---
# Everything Claude Code Export Style
## Action
Prefer mixed exports
## Evidence
- Export pattern analysis
- Dominant style: mixed
---
id: everything-claude-code-test-separate
trigger: "when writing tests"
confidence: 0.8
domain: testing
source: repo-analysis
source_repo: https://github.com/affaan-m/everything-claude-code
---
# Everything Claude Code Test Separate
## Action
Place tests in the tests/ or __tests__/ directory, mirroring src structure
## Evidence
- Separate test directory pattern detected
- Tests live in dedicated test folders
---
id: everything-claude-code-test-framework
trigger: "when writing tests"
confidence: 0.9
domain: testing
source: repo-analysis
source_repo: https://github.com/affaan-m/everything-claude-code
---
# Everything Claude Code Test Framework
## Action
Use unknown as the test framework
## Evidence
- Test framework detected: unknown
- File pattern: *.test.js
---
id: everything-claude-code-test-naming
trigger: "when creating a test file"
confidence: 0.85
domain: testing
source: repo-analysis
source_repo: https://github.com/affaan-m/everything-claude-code
---
# Everything Claude Code Test Naming
## Action
Name test files using the pattern: *.test.js
## Evidence
- File pattern: *.test.js
- Consistent across test files
---
id: everything-claude-code-test-types
trigger: "when planning tests for a feature"
confidence: 0.7
domain: testing
source: repo-analysis
source_repo: https://github.com/affaan-m/everything-claude-code
---
# Everything Claude Code Test Types
## Action
Write unit, integration tests to match project standards
## Evidence
- Test types detected: unit, integration
- Coverage config: yes
---
id: everything-claude-code-workflow-database-migration
trigger: "when modifying the database schema or adding tables"
confidence: 0.65
domain: workflow
source: repo-analysis
source_repo: https://github.com/affaan-m/everything-claude-code
---
# Everything Claude Code Workflow Database Migration
## Action
Follow the database-migration workflow:
1. Create migration file
2. Update schema definitions
3. Generate/update types
## Evidence
- Workflow detected from commit patterns
- Frequency: ~3x per month
- Files: migrations/*
---
id: everything-claude-code-workflow-feature-development
trigger: "when implementing a new feature"
confidence: 0.9
domain: workflow
source: repo-analysis
source_repo: https://github.com/affaan-m/everything-claude-code
---
# Everything Claude Code Workflow Feature Development
## Action
Follow the feature-development workflow:
1. Add feature implementation
2. Add tests for feature
3. Update documentation
## Evidence
- Workflow detected from commit patterns
- Frequency: ~14x per month
- Files: .opencode/*, .opencode/plugins/*, .opencode/tools/*
---
id: everything-claude-code-workflow-multi-language-documentation-sync
trigger: "when doing multi language documentation sync"
confidence: 0.9
domain: workflow
source: repo-analysis
source_repo: https://github.com/affaan-m/everything-claude-code
---
# Everything Claude Code Workflow Multi Language Documentation Sync
## Action
Follow the multi-language-documentation-sync workflow:
1. Update English documentation
2. Translate changes to zh-CN
3. Translate changes to zh-TW
4. Translate changes to ja-JP
5. Update cross-references
## Evidence
- Workflow detected from commit patterns
- Frequency: ~10x per month
- Files: README.md, docs/zh-CN/*.md, docs/zh-TW/*.md
---
id: everything-claude-code-workflow-cross-platform-harness-sync
trigger: "when doing cross platform harness sync"
confidence: 0.9
domain: workflow
source: repo-analysis
source_repo: https://github.com/affaan-m/everything-claude-code
---
# Everything Claude Code Workflow Cross Platform Harness Sync
## Action
Follow the cross-platform-harness-sync workflow:
1. Update main platform files
2. Port to .cursor/ directory
3. Port to .codex/ directory
4. Port to .opencode/ directory
5. Update platform-specific configs
## Evidence
- Workflow detected from commit patterns
- Frequency: ~8x per month
- Files: .cursor/*, .codex/*, .opencode/*
---
id: everything-claude-code-workflow-skill-addition-workflow
trigger: "when doing skill addition workflow"
confidence: 0.8
domain: workflow
source: repo-analysis
source_repo: https://github.com/affaan-m/everything-claude-code
---
# Everything Claude Code Workflow Skill Addition Workflow
## Action
Follow the skill-addition-workflow workflow:
1. Create main skill SKILL.md
2. Add to README.md
3. Port to .cursor/skills/
4. Port to .agents/skills/ with openai.yaml
5. Update package.json
6. Add translations if needed
## Evidence
- Workflow detected from commit patterns
- Frequency: ~6x per month
- Files: skills/*/SKILL.md, README.md, .cursor/skills/*/SKILL.md
---
id: everything-claude-code-workflow-version-release-workflow
trigger: "when doing version release workflow"
confidence: 0.65
domain: workflow
source: repo-analysis
source_repo: https://github.com/affaan-m/everything-claude-code
---
# Everything Claude Code Workflow Version Release Workflow
## Action
Follow the version-release-workflow workflow:
1. Update package.json version
2. Update .claude-plugin/ manifests
3. Update .opencode/package.json
4. Update README version references
5. Update CHANGELOG.md
## Evidence
- Workflow detected from commit patterns
- Frequency: ~3x per month
- Files: package.json, .claude-plugin/plugin.json, .claude-plugin/marketplace.json
---
id: everything-claude-code-workflow-hook-system-updates
trigger: "when doing hook system updates"
confidence: 0.7
domain: workflow
source: repo-analysis
source_repo: https://github.com/affaan-m/everything-claude-code
---
# Everything Claude Code Workflow Hook System Updates
## Action
Follow the hook-system-updates workflow:
1. Update hooks/hooks.json
2. Create/update hook scripts
3. Port to .cursor/hooks/
4. Update tests/hooks/ or tests/integration/
5. Update hook documentation
## Evidence
- Workflow detected from commit patterns
- Frequency: ~4x per month
- Files: hooks/hooks.json, scripts/hooks/*.js, .cursor/hooks/*.js
---
id: everything-claude-code-workflow-continuous-learning-updates
trigger: "when doing continuous learning updates"
confidence: 0.75
domain: workflow
source: repo-analysis
source_repo: https://github.com/affaan-m/everything-claude-code
---
# Everything Claude Code Workflow Continuous Learning Updates
## Action
Follow the continuous-learning-updates workflow:
1. Update main continuous-learning-v2 skill
2. Update observer scripts
3. Port to platform-specific directories
4. Update translations
5. Update related commands
## Evidence
- Workflow detected from commit patterns
- Frequency: ~5x per month
- Files: skills/continuous-learning-v2/*, .cursor/skills/continuous-learning-v2/*, commands/evolve.md
---
id: everything-claude-code-camel-case-files
trigger: "When creating new JavaScript files"
confidence: 0.85
domain: code-style
source: repo-analysis
source_repo: affaan-m/everything-claude-code
---
# Everything Claude Code Camel Case Files
## Action
Use camelCase naming convention
## Evidence
- Consistent camelCase pattern in codeStyle analysis
- Files follow camelCase in folderStructure
---
id: everything-claude-code-pascal-case-classes
trigger: "When defining JavaScript classes"
confidence: 0.85
domain: code-style
source: repo-analysis
source_repo: affaan-m/everything-claude-code
---
# Everything Claude Code Pascal Case Classes
## Action
Use PascalCase naming convention
## Evidence
- PascalCase classes specified in namingConventions
- Consistent pattern across codebase
---
id: everything-claude-code-screaming-snake-constants
trigger: "When defining constants"
confidence: 0.85
domain: code-style
source: repo-analysis
source_repo: affaan-m/everything-claude-code
---
# Everything Claude Code Screaming Snake Constants
## Action
Use SCREAMING_SNAKE_CASE naming convention
## Evidence
- SCREAMING_SNAKE_CASE constants in namingConventions
- Standard JavaScript practice
---
id: everything-claude-code-try-catch-errors
trigger: "When handling potential errors"
confidence: 0.8
domain: code-style
source: repo-analysis
source_repo: affaan-m/everything-claude-code
---
# Everything Claude Code Try Catch Errors
## Action
Use try-catch blocks for error handling
## Evidence
- try-catch style specified in errorHandling
- No custom error classes or global handlers detected
---
id: everything-claude-code-unit-integration-tests
trigger: "When writing tests"
confidence: 0.8
domain: testing
source: repo-analysis
source_repo: affaan-m/everything-claude-code
---
# Everything Claude Code Unit Integration Tests
## Action
Create both unit and integration tests using *.test.js pattern
## Evidence
- testTypes include unit and integration
- filePattern shows *.test.js convention
# Curated instincts for affaan-m/everything-claude-code
# Import with: /instinct-import .claude/homunculus/instincts/inherited/everything-claude-code-instincts.yaml
---
id: everything-claude-code-conventional-commits
trigger: "When making commits"
trigger: "when making a commit in everything-claude-code"
confidence: 0.9
domain: git
source: repo-analysis
source: repo-curation
source_repo: affaan-m/everything-claude-code
---
@@ -460,59 +14,99 @@ source_repo: affaan-m/everything-claude-code
## Action
Use conventional commit format with prefixes: feat, fix, docs, chore, test, refactor
Use conventional commit prefixes such as `feat:`, `fix:`, `docs:`, `test:`, `chore:`, and `refactor:`.
## Evidence
- All commit examples follow conventional format
- Consistent prefixes across commit history
- Mainline history consistently uses conventional commit subjects.
- Release and changelog automation expect readable commit categorization.
---
id: everything-claude-code-70-char-commit-length
trigger: "When writing commit messages"
confidence: 0.75
id: everything-claude-code-commit-length
trigger: "when writing a commit subject in everything-claude-code"
confidence: 0.8
domain: git
source: repo-analysis
source: repo-curation
source_repo: affaan-m/everything-claude-code
---
# Everything Claude Code 70 Char Commit Length
# Everything Claude Code Commit Length
## Action
Keep commit messages around 70 characters average length
Keep commit subjects concise and close to the repository norm of about 70 characters.
## Evidence
- averageLength shows 70 characters
- Commit examples align with this pattern
- Recent history clusters around ~70 characters, not ~50.
- Short, descriptive subjects read well in release notes and PR summaries.
---
id: everything-claude-code-multilang-docs-sync
trigger: "When updating core documentation or features"
confidence: 0.95
id: everything-claude-code-js-file-naming
trigger: "when creating a new JavaScript or TypeScript module in everything-claude-code"
confidence: 0.85
domain: code-style
source: repo-curation
source_repo: affaan-m/everything-claude-code
---
# Everything Claude Code JS File Naming
## Action
Prefer camelCase for JavaScript and TypeScript module filenames, and keep skill or command directories in kebab-case.
## Evidence
- `scripts/` and test helpers mostly use camelCase module names.
- `skills/` and `commands/` directories use kebab-case consistently.
---
id: everything-claude-code-test-runner
trigger: "when adding or updating tests in everything-claude-code"
confidence: 0.9
domain: testing
source: repo-curation
source_repo: affaan-m/everything-claude-code
---
# Everything Claude Code Test Runner
## Action
Use the repository's existing Node-based test flow: targeted `*.test.js` files first, then `node tests/run-all.js` or `npm test` for broader verification.
## Evidence
- The repo uses `tests/run-all.js` as the central test orchestrator.
- Test files follow the `*.test.js` naming pattern across hook, CI, and integration coverage.
---
id: everything-claude-code-hooks-change-set
trigger: "when modifying hooks or hook-adjacent behavior in everything-claude-code"
confidence: 0.88
domain: workflow
source: repo-analysis
source: repo-curation
source_repo: affaan-m/everything-claude-code
---
# Everything Claude Code Multilang Docs Sync
# Everything Claude Code Hooks Change Set
## Action
Update English first, then translate to zh-CN, zh-TW, ja-JP and update cross-references
Update the hook script, its configuration, its tests, and its user-facing documentation together.
## Evidence
- multi-language-documentation-sync workflow frequency ~10x/month
- Clear pattern in filesInvolved across language directories
- Hook fixes routinely span `hooks/hooks.json`, `scripts/hooks/`, `tests/hooks/`, `tests/integration/`, and `hooks/README.md`.
- Partial hook changes are a common source of regressions and stale docs.
---
id: everything-claude-code-cross-platform-sync
trigger: "When adding new features or updating platform configurations"
trigger: "when shipping a user-visible feature across ECC surfaces"
confidence: 0.9
domain: workflow
source: repo-analysis
source: repo-curation
source_repo: affaan-m/everything-claude-code
---
@@ -520,130 +114,49 @@ source_repo: affaan-m/everything-claude-code
## Action
Port changes to .cursor/, .codex/, .opencode/, and .agents/ directories
Treat the root repo as the source of truth, then mirror shipped changes to `.cursor/`, `.codex/`, `.opencode/`, and `.agents/` only where the feature actually exists.
## Evidence
- cross-platform-harness-sync workflow frequency ~8x/month
- Multiple platform directories in architecture
- ECC maintains multiple harness-specific surfaces with overlapping but not identical files.
- The safest workflow is root-first followed by explicit parity updates.
---
id: everything-claude-code-skill-structure
trigger: "When adding a new skill or capability"
confidence: 0.88
id: everything-claude-code-release-sync
trigger: "when preparing a release for everything-claude-code"
confidence: 0.86
domain: workflow
source: repo-analysis
source: repo-curation
source_repo: affaan-m/everything-claude-code
---
# Everything Claude Code Skill Structure
# Everything Claude Code Release Sync
## Action
Create SKILL.md in main skills/, port to platform-specific directories, update README.md and package.json
Keep package versions, plugin manifests, and release-facing docs synchronized before publishing.
## Evidence
- skill-addition-workflow frequency ~6x/month
- Consistent skill structure across platforms
- Release work spans `package.json`, `.claude-plugin/*`, `.opencode/package.json`, and release-note content.
- Version drift causes broken update paths and confusing install surfaces.
---
id: everything-claude-code-version-release-sync
trigger: "When preparing a new release"
confidence: 0.85
id: everything-claude-code-learning-curation
trigger: "when importing or evolving instincts for everything-claude-code"
confidence: 0.84
domain: workflow
source: repo-analysis
source: repo-curation
source_repo: affaan-m/everything-claude-code
---
# Everything Claude Code Version Release Sync
# Everything Claude Code Learning Curation
## Action
Update all package.json files, plugin manifests, README version references, and CHANGELOG.md
Prefer a small set of accurate instincts over bulk-generated, duplicated, or contradictory instincts.
## Evidence
- version-release-workflow frequency ~3x/month
- Multiple package.json files in different directories
---
id: everything-claude-code-hook-system-testing
trigger: "When modifying hook behavior or adding new hooks"
confidence: 0.82
domain: workflow
source: repo-analysis
source_repo: affaan-m/everything-claude-code
---
# Everything Claude Code Hook System Testing
## Action
Update hooks.json, create/update scripts, port to .cursor/, and update corresponding tests
## Evidence
- hook-system-updates workflow frequency ~4x/month
- hooks/ and tests/ directories in architecture
---
id: everything-claude-code-learning-system-updates
trigger: "When enhancing continuous learning capabilities"
confidence: 0.87
domain: workflow
source: repo-analysis
source_repo: affaan-m/everything-claude-code
---
# Everything Claude Code Learning System Updates
## Action
Update main continuous-learning-v2 skill, port to platforms, update translations and related commands
## Evidence
- continuous-learning-updates workflow frequency ~5x/month
- commands/evolve.md and instinct-*.md files referenced
---
id: everything-claude-code-hybrid-module-organization
trigger: "When organizing code modules"
confidence: 0.75
domain: architecture
source: repo-analysis
source_repo: affaan-m/everything-claude-code
---
# Everything Claude Code Hybrid Module Organization
## Action
Use hybrid module organization with separate test location
## Evidence
- moduleOrganization: hybrid
- testLocation: separate in architecture analysis
---
id: everything-claude-code-mixed-import-export
trigger: "When writing import/export statements"
confidence: 0.7
domain: code-style
source: repo-analysis
source_repo: affaan-m/everything-claude-code
---
# Everything Claude Code Mixed Import Export
## Action
Use mixed import and export styles as appropriate for the context
## Evidence
- importStyle: mixed and exportStyle: mixed in codeStyle
- Flexible approach across codebase
- Auto-generated instinct dumps can duplicate rules, widen triggers too far, or preserve placeholder detector output.
- Curated instincts are easier to import, audit, and trust during continuous-learning workflows.

View File

@@ -1,215 +1,97 @@
# everything-claude-code Development Patterns
# Everything Claude Code
> Auto-generated skill from repository analysis
Use this skill when working inside the `everything-claude-code` repository and you need repo-specific guidance instead of generic coding advice.
## Overview
Optional companion instincts live at `.claude/homunculus/instincts/inherited/everything-claude-code-instincts.yaml` for teams using `continuous-learning-v2`.
This skill teaches the development patterns for the everything-claude-code repository - a comprehensive multi-platform AI coding assistant system. The codebase maintains compatibility across multiple AI platforms (Claude, Cursor, Codex, OpenCode) while supporting internationalization across four languages (English, Chinese Simplified/Traditional, Japanese). The system focuses on skill-based architecture, continuous learning capabilities, and cross-platform synchronization.
## When to Use
## Coding Conventions
Activate this skill when the task touches one or more of these areas:
- cross-platform parity across Claude Code, Cursor, Codex, and OpenCode
- hook scripts, hook docs, or hook tests
- skills, commands, agents, or rules that must stay synchronized across surfaces
- release work such as version bumps, changelog updates, or plugin metadata updates
- continuous-learning or instinct workflows inside this repository
### File Naming
- Use **camelCase** for JavaScript files
- Use **kebab-case** for directories and skill names
- Test files follow pattern: `*.test.js`
## How It Works
```javascript
// File structure examples
skills/continuousLearningV2/SKILL.md
tests/hooks/hookManager.test.js
scripts/platformSync.js
### 1. Follow the repo's development contract
- Use conventional commits such as `feat:`, `fix:`, `docs:`, `test:`, `chore:`.
- Keep commit subjects concise and close to the repo norm of about 70 characters.
- Prefer camelCase for JavaScript and TypeScript module filenames.
- Use kebab-case for skill directories and command filenames.
- Keep test files on the existing `*.test.js` pattern.
### 2. Treat the root repo as the source of truth
Start from the root implementation, then mirror changes where they are intentionally shipped.
Typical mirror targets:
- `.cursor/`
- `.codex/`
- `.opencode/`
- `.agents/`
Do not assume every `.claude/` artifact needs a cross-platform copy. Only mirror files that are part of the shipped multi-platform surface.
### 3. Update hooks with tests and docs together
When changing hook behavior:
1. update `hooks/hooks.json` or the relevant script in `scripts/hooks/`
2. update matching tests in `tests/hooks/` or `tests/integration/`
3. update `hooks/README.md` if behavior or configuration changed
4. verify parity for `.cursor/hooks/` and `.opencode/plugins/` when applicable
### 4. Keep release metadata in sync
When preparing a release, verify the same version is reflected anywhere it is surfaced:
- `package.json`
- `.claude-plugin/plugin.json`
- `.claude-plugin/marketplace.json`
- `.opencode/package.json`
- release notes or changelog entries when the release process expects them
### 5. Be explicit about continuous-learning changes
If the task touches `skills/continuous-learning-v2/` or imported instincts:
- prefer accurate, low-noise instincts over auto-generated bulk output
- keep instinct files importable by `instinct-cli.py`
- remove duplicated or contradictory instincts instead of layering more guidance on top
## Examples
### Naming examples
```text
skills/continuous-learning-v2/SKILL.md
commands/update-docs.md
scripts/hooks/session-start.js
tests/hooks/hooks.test.js
```
### Import/Export Style
- Mixed import styles (both CommonJS and ES modules supported)
- Mixed export styles based on platform compatibility
### Commit examples
```javascript
// CommonJS style
const hookManager = require('./hookManager');
module.exports = { syncPlatforms };
// ES module style
import { translateDocs } from './translationUtils.js';
export { processSkills };
```text
fix: harden session summary extraction on Stop hook
docs: align Codex config examples with current schema
test: cover Windows formatter fallback behavior
```
### Commit Conventions
- Use conventional commit prefixes: `feat:`, `fix:`, `test:`, `chore:`, `docs:`
- Keep commit messages under 70 characters
- Be descriptive about cross-platform impacts
### Skill update checklist
```bash
feat: add multi-language skill sync workflow
fix: resolve cursor platform hook integration
docs: update zh-CN translation for continuous learning
```text
1. Update the root skill or command.
2. Mirror it only where that surface is shipped.
3. Run targeted tests first, then the broader suite if behavior changed.
4. Review docs and release notes for user-visible changes.
```
## Workflows
### Release checklist
### Multi-Language Documentation Sync
**Trigger:** When core documentation or features are updated
**Command:** `/sync-docs`
1. Update English documentation in root README.md or skill files
2. Identify sections that need translation updates
3. Update Chinese Simplified (`docs/zh-CN/*.md`)
4. Update Traditional Chinese (`docs/zh-TW/*.md`)
5. Update Japanese (`docs/ja-JP/*.md`)
6. Verify cross-references and links work across all languages
7. Test that skill descriptions match across platforms
```markdown
<!-- Example translation structure -->
# English: skills/example/SKILL.md
# Chinese: docs/zh-CN/skills/example/SKILL.md
# Japanese: docs/ja-JP/skills/example/SKILL.md
```text
1. Bump package and plugin versions.
2. Run npm test.
3. Verify platform-specific manifests.
4. Publish the release notes with a human-readable summary.
```
### Cross-Platform Harness Sync
**Trigger:** When adding new features or updating platform configurations
**Command:** `/sync-platforms`
1. Update main platform files in root directory
2. Port changes to `.cursor/` directory for Cursor IDE
3. Port changes to `.codex/` directory for Codex integration
4. Port changes to `.opencode/` directory for OpenCode platform
5. Update platform-specific configuration files
6. Test that each platform can load and execute the changes
7. Verify skill compatibility across all platforms
```javascript
// Platform-specific config example
// .cursor/package.json
{
"name": "everything-claude-code-cursor",
"platform": "cursor"
}
// .opencode/package.json
{
"name": "everything-claude-code-opencode",
"platform": "opencode"
}
```
### Skill Addition Workflow
**Trigger:** When adding a new skill or capability
**Command:** `/add-skill`
1. Create main skill directory: `skills/{skillName}/`
2. Write comprehensive `SKILL.md` with examples and usage
3. Add skill reference to root `README.md`
4. Port skill to `.cursor/skills/{skillName}/SKILL.md`
5. Port to `.agents/skills/{skillName}/` with `openai.yaml`
6. Update `package.json` with new skill metadata
7. Add translations for skill name and description
8. Test skill loading across all platforms
```yaml
# .agents/skills/example/openai.yaml
name: example-skill
description: Example skill for demonstration
version: 1.0.0
compatibility: ["openai", "claude", "cursor"]
```
### Version Release Workflow
**Trigger:** When preparing a new release
**Command:** `/release`
1. Update version in root `package.json`
2. Update `.claude-plugin/plugin.json` manifest version
3. Update `.claude-plugin/marketplace.json` with release notes
4. Update `.opencode/package.json` version to match
5. Update version references in `README.md`
6. Update `CHANGELOG.md` with new features and fixes
7. Create git tag and push release
8. Verify plugin compatibility across platforms
```json
// package.json version sync
{
"version": "2.1.0",
"name": "everything-claude-code"
}
```
### Hook System Updates
**Trigger:** When modifying hook behavior or adding new hooks
**Command:** `/update-hooks`
1. Update `hooks/hooks.json` with new hook definitions
2. Create or modify hook scripts in `scripts/hooks/`
3. Port hook implementations to `.cursor/hooks/`
4. Update tests in `tests/hooks/` or `tests/integration/`
5. Update hook documentation in `hooks/README.md`
6. Test hook execution across different trigger scenarios
7. Verify platform-specific hook behaviors
```json
// hooks/hooks.json example
{
"pre-commit": {
"script": "scripts/hooks/preCommit.js",
"platforms": ["cursor", "opencode"],
"enabled": true
}
}
```
### Continuous Learning Updates
**Trigger:** When enhancing the continuous learning capabilities
**Command:** `/update-learning`
1. Update main `skills/continuous-learning-v2/` skill files
2. Modify observer scripts for better learning detection
3. Port updates to platform-specific skill directories
4. Update translation files for learning prompts
5. Update related commands in `commands/evolve.md`
6. Update instinct commands (`commands/instinct-*.md`)
7. Test learning feedback loops across platforms
```javascript
// Learning observer example
class LearningObserver {
observePatterns() {
// Detect coding patterns
// Update skill knowledge
// Sync across platforms
}
}
```
## Testing Patterns
Tests follow the `*.test.js` pattern and focus on:
- Cross-platform compatibility verification
- Multi-language content validation
- Hook execution testing
- Skill loading and execution
```javascript
// Example test structure
describe('Platform Sync', () => {
test('should sync skills across all platforms', () => {
const platforms = ['cursor', 'opencode', 'codex'];
platforms.forEach(platform => {
expect(skillExists(platform, 'continuous-learning-v2')).toBe(true);
});
});
});
```
## Commands
| Command | Purpose |
|---------|---------|
| `/sync-docs` | Synchronize documentation across all language versions |
| `/sync-platforms` | Port changes across AI coding platforms |
| `/add-skill` | Add new skill with full cross-platform support |
| `/release` | Prepare and publish new version release |
| `/update-hooks` | Modify hook system and test integration |
| `/update-learning` | Enhance continuous learning capabilities |
| `/test-platforms` | Run compatibility tests across all platforms |
| `/translate` | Generate translations for new content |