@heytherevibin/skillforge 0.2.1

package/skills/clickhouse-io/SKILL.md

@@ -0,0 +1,438 @@
+---
+name: clickhouse-io
+description: ClickHouse database patterns, query optimization, analytics, and data engineering best practices for high-performance analytical workloads.
+---
+
+# ClickHouse Analytics Patterns
+
+ClickHouse-specific patterns for high-performance analytics and data engineering.
+
+## When to Activate
+
+- Designing ClickHouse table schemas (MergeTree engine selection)
+- Writing analytical queries (aggregations, window functions, joins)
+- Optimizing query performance (partition pruning, projections, materialized views)
+- Ingesting large volumes of data (batch inserts, Kafka integration)
+- Migrating from PostgreSQL/MySQL to ClickHouse for analytics
+- Implementing real-time dashboards or time-series analytics
+
+## Overview
+
+ClickHouse is a column-oriented database management system (DBMS) for online analytical processing (OLAP). It's optimized for fast analytical queries on large datasets.
+
+**Key Features:**
+- Column-oriented storage
+- Data compression
+- Parallel query execution
+- Distributed queries
+- Real-time analytics
+
+## Table Design Patterns
+
+### MergeTree Engine (Most Common)
+
+```sql
+CREATE TABLE markets_analytics (
+    date Date,
+    market_id String,
+    market_name String,
+    volume UInt64,
+    trades UInt32,
+    unique_traders UInt32,
+    avg_trade_size Float64,
+    created_at DateTime
+) ENGINE = MergeTree()
+PARTITION BY toYYYYMM(date)
+ORDER BY (date, market_id)
+SETTINGS index_granularity = 8192;
+```
+
+### ReplacingMergeTree (Deduplication)
+
+```sql
+-- For data that may have duplicates (e.g., from multiple sources)
+CREATE TABLE user_events (
+    event_id String,
+    user_id String,
+    event_type String,
+    timestamp DateTime,
+    properties String
+) ENGINE = ReplacingMergeTree()
+PARTITION BY toYYYYMM(timestamp)
+ORDER BY (user_id, event_id, timestamp)
+PRIMARY KEY (user_id, event_id);
+```
+
+### AggregatingMergeTree (Pre-aggregation)
+
+```sql
+-- For maintaining aggregated metrics
+CREATE TABLE market_stats_hourly (
+    hour DateTime,
+    market_id String,
+    total_volume AggregateFunction(sum, UInt64),
+    total_trades AggregateFunction(count, UInt32),
+    unique_users AggregateFunction(uniq, String)
+) ENGINE = AggregatingMergeTree()
+PARTITION BY toYYYYMM(hour)
+ORDER BY (hour, market_id);
+
+-- Query aggregated data
+SELECT
+    hour,
+    market_id,
+    sumMerge(total_volume) AS volume,
+    countMerge(total_trades) AS trades,
+    uniqMerge(unique_users) AS users
+FROM market_stats_hourly
+WHERE hour >= toStartOfHour(now() - INTERVAL 24 HOUR)
+GROUP BY hour, market_id
+ORDER BY hour DESC;
+```
+
+## Query Optimization Patterns
+
+### Efficient Filtering
+
+```sql
+-- PASS: GOOD: Use indexed columns first
+SELECT *
+FROM markets_analytics
+WHERE date >= '2025-01-01'
+  AND market_id = 'market-123'
+  AND volume > 1000
+ORDER BY date DESC
+LIMIT 100;
+
+-- FAIL: BAD: Filter on non-indexed columns first
+SELECT *
+FROM markets_analytics
+WHERE volume > 1000
+  AND market_name LIKE '%election%'
+  AND date >= '2025-01-01';
+```
+
+### Aggregations
+
+```sql
+-- PASS: GOOD: Use ClickHouse-specific aggregation functions
+SELECT
+    toStartOfDay(created_at) AS day,
+    market_id,
+    sum(volume) AS total_volume,
+    count() AS total_trades,
+    uniq(trader_id) AS unique_traders,
+    avg(trade_size) AS avg_size
+FROM trades
+WHERE created_at >= today() - INTERVAL 7 DAY
+GROUP BY day, market_id
+ORDER BY day DESC, total_volume DESC;
+
+-- PASS: Use quantile for percentiles (more efficient than percentile)
+SELECT
+    quantile(0.50)(trade_size) AS median,
+    quantile(0.95)(trade_size) AS p95,
+    quantile(0.99)(trade_size) AS p99
+FROM trades
+WHERE created_at >= now() - INTERVAL 1 HOUR;
+```
+
+### Window Functions
+
+```sql
+-- Calculate running totals
+SELECT
+    date,
+    market_id,
+    volume,
+    sum(volume) OVER (
+        PARTITION BY market_id
+        ORDER BY date
+        ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW
+    ) AS cumulative_volume
+FROM markets_analytics
+WHERE date >= today() - INTERVAL 30 DAY
+ORDER BY market_id, date;
+```
+
+## Data Insertion Patterns
+
+### Bulk Insert (Recommended)
+
+```typescript
+import { ClickHouse } from 'clickhouse'
+
+const clickhouse = new ClickHouse({
+  url: process.env.CLICKHOUSE_URL,
+  port: 8123,
+  basicAuth: {
+    username: process.env.CLICKHOUSE_USER,
+    password: process.env.CLICKHOUSE_PASSWORD
+  }
+})
+
+// PASS: Batch insert (efficient)
+async function bulkInsertTrades(trades: Trade[]) {
+  const values = trades.map(trade => `(
+    '${trade.id}',
+    '${trade.market_id}',
+    '${trade.user_id}',
+    ${trade.amount},
+    '${trade.timestamp.toISOString()}'
+  )`).join(',')
+
+  await clickhouse.query(`
+    INSERT INTO trades (id, market_id, user_id, amount, timestamp)
+    VALUES ${values}
+  `).toPromise()
+}
+
+// FAIL: Individual inserts (slow)
+async function insertTrade(trade: Trade) {
+  // Don't do this in a loop!
+  await clickhouse.query(`
+    INSERT INTO trades VALUES ('${trade.id}', ...)
+  `).toPromise()
+}
+```
+
+### Streaming Insert
+
+```typescript
+// For continuous data ingestion
+import { createWriteStream } from 'fs'
+import { pipeline } from 'stream/promises'
+
+async function streamInserts() {
+  const stream = clickhouse.insert('trades').stream()
+
+  for await (const batch of dataSource) {
+    stream.write(batch)
+  }
+
+  await stream.end()
+}
+```
+
+## Materialized Views
+
+### Real-time Aggregations
+
+```sql
+-- Create materialized view for hourly stats
+CREATE MATERIALIZED VIEW market_stats_hourly_mv
+TO market_stats_hourly
+AS SELECT
+    toStartOfHour(timestamp) AS hour,
+    market_id,
+    sumState(amount) AS total_volume,
+    countState() AS total_trades,
+    uniqState(user_id) AS unique_users
+FROM trades
+GROUP BY hour, market_id;
+
+-- Query the materialized view
+SELECT
+    hour,
+    market_id,
+    sumMerge(total_volume) AS volume,
+    countMerge(total_trades) AS trades,
+    uniqMerge(unique_users) AS users
+FROM market_stats_hourly
+WHERE hour >= now() - INTERVAL 24 HOUR
+GROUP BY hour, market_id;
+```
+
+## Performance Monitoring
+
+### Query Performance
+
+```sql
+-- Check slow queries
+SELECT
+    query_id,
+    user,
+    query,
+    query_duration_ms,
+    read_rows,
+    read_bytes,
+    memory_usage
+FROM system.query_log
+WHERE type = 'QueryFinish'
+  AND query_duration_ms > 1000
+  AND event_time >= now() - INTERVAL 1 HOUR
+ORDER BY query_duration_ms DESC
+LIMIT 10;
+```
+
+### Table Statistics
+
+```sql
+-- Check table sizes
+SELECT
+    database,
+    table,
+    formatReadableSize(sum(bytes)) AS size,
+    sum(rows) AS rows,
+    max(modification_time) AS latest_modification
+FROM system.parts
+WHERE active
+GROUP BY database, table
+ORDER BY sum(bytes) DESC;
+```
+
+## Common Analytics Queries
+
+### Time Series Analysis
+
+```sql
+-- Daily active users
+SELECT
+    toDate(timestamp) AS date,
+    uniq(user_id) AS daily_active_users
+FROM events
+WHERE timestamp >= today() - INTERVAL 30 DAY
+GROUP BY date
+ORDER BY date;
+
+-- Retention analysis
+SELECT
+    signup_date,
+    countIf(days_since_signup = 0) AS day_0,
+    countIf(days_since_signup = 1) AS day_1,
+    countIf(days_since_signup = 7) AS day_7,
+    countIf(days_since_signup = 30) AS day_30
+FROM (
+    SELECT
+        user_id,
+        min(toDate(timestamp)) AS signup_date,
+        toDate(timestamp) AS activity_date,
+        dateDiff('day', signup_date, activity_date) AS days_since_signup
+    FROM events
+    GROUP BY user_id, activity_date
+)
+GROUP BY signup_date
+ORDER BY signup_date DESC;
+```
+
+### Funnel Analysis
+
+```sql
+-- Conversion funnel
+SELECT
+    countIf(step = 'viewed_market') AS viewed,
+    countIf(step = 'clicked_trade') AS clicked,
+    countIf(step = 'completed_trade') AS completed,
+    round(clicked / viewed * 100, 2) AS view_to_click_rate,
+    round(completed / clicked * 100, 2) AS click_to_completion_rate
+FROM (
+    SELECT
+        user_id,
+        session_id,
+        event_type AS step
+    FROM events
+    WHERE event_date = today()
+)
+GROUP BY session_id;
+```
+
+### Cohort Analysis
+
+```sql
+-- User cohorts by signup month
+SELECT
+    toStartOfMonth(signup_date) AS cohort,
+    toStartOfMonth(activity_date) AS month,
+    dateDiff('month', cohort, month) AS months_since_signup,
+    count(DISTINCT user_id) AS active_users
+FROM (
+    SELECT
+        user_id,
+        min(toDate(timestamp)) OVER (PARTITION BY user_id) AS signup_date,
+        toDate(timestamp) AS activity_date
+    FROM events
+)
+GROUP BY cohort, month, months_since_signup
+ORDER BY cohort, months_since_signup;
+```
+
+## Data Pipeline Patterns
+
+### ETL Pattern
+
+```typescript
+// Extract, Transform, Load
+async function etlPipeline() {
+  // 1. Extract from source
+  const rawData = await extractFromPostgres()
+
+  // 2. Transform
+  const transformed = rawData.map(row => ({
+    date: new Date(row.created_at).toISOString().split('T')[0],
+    market_id: row.market_slug,
+    volume: parseFloat(row.total_volume),
+    trades: parseInt(row.trade_count)
+  }))
+
+  // 3. Load to ClickHouse
+  await bulkInsertToClickHouse(transformed)
+}
+
+// Run periodically
+setInterval(etlPipeline, 60 * 60 * 1000)  // Every hour
+```
+
+### Change Data Capture (CDC)
+
+```typescript
+// Listen to PostgreSQL changes and sync to ClickHouse
+import { Client } from 'pg'
+
+const pgClient = new Client({ connectionString: process.env.DATABASE_URL })
+
+pgClient.query('LISTEN market_updates')
+
+pgClient.on('notification', async (msg) => {
+  const update = JSON.parse(msg.payload)
+
+  await clickhouse.insert('market_updates', [
+    {
+      market_id: update.id,
+      event_type: update.operation,  // INSERT, UPDATE, DELETE
+      timestamp: new Date(),
+      data: JSON.stringify(update.new_data)
+    }
+  ])
+})
+```
+
+## Best Practices
+
+### 1. Partitioning Strategy
+- Partition by time (usually month or day)
+- Avoid too many partitions (performance impact)
+- Use DATE type for partition key
+
+### 2. Ordering Key
+- Put most frequently filtered columns first
+- Consider cardinality (high cardinality first)
+- Order impacts compression
+
+### 3. Data Types
+- Use smallest appropriate type (UInt32 vs UInt64)
+- Use LowCardinality for repeated strings
+- Use Enum for categorical data
+
+### 4. Avoid
+- SELECT * (specify columns)
+- FINAL (merge data before query instead)
+- Too many JOINs (denormalize for analytics)
+- Small frequent inserts (batch instead)
+
+### 5. Monitoring
+- Track query performance
+- Monitor disk usage
+- Check merge operations
+- Review slow query log
+
+**Remember**: ClickHouse excels at analytical workloads. Design tables for your query patterns, batch inserts, and leverage materialized views for real-time aggregations.

package/skills/code-tour/SKILL.md

@@ -0,0 +1,235 @@
+---
+name: code-tour
+description: Create CodeTour `.tour` files — persona-targeted, step-by-step walkthroughs with real file and line anchors. Use for onboarding tours, architecture walkthroughs, PR tours, RCA tours, and structured "explain how this works" requests.
+---
+
+# Code Tour
+
+Create **CodeTour** `.tour` files for codebase walkthroughs that open directly to real files and line ranges. Tours live in `.tours/` and are meant for the CodeTour format, not ad hoc Markdown notes.
+
+A good tour is a narrative for a specific reader:
+- what they are looking at
+- why it matters
+- what path they should follow next
+
+Only create `.tour` JSON files. Do not modify source code as part of this skill.
+
+## When to Use
+
+Use this skill when:
+- the user asks for a code tour, onboarding tour, architecture walkthrough, or PR tour
+- the user says "explain how X works" and wants a reusable guided artifact
+- the user wants a ramp-up path for a new engineer or reviewer
+- the task is better served by a guided sequence than a flat summary
+
+Examples:
+- onboarding a new maintainer
+- architecture tour for one service or package
+- PR-review walk-through anchored to changed files
+- RCA tour showing the failure path
+- security review tour of trust boundaries and key checks
+
+## When NOT to Use
+
+| Instead of code-tour | Use |
+| --- | --- |
+| A one-off explanation in chat is enough | answer directly |
+| The user wants prose docs, not a `.tour` artifact | `documentation-lookup` or repo docs editing |
+| The task is implementation or refactoring | do the implementation work |
+| The task is broad codebase onboarding without a tour artifact | `codebase-onboarding` |
+
+## Workflow
+
+### 1. Discover
+
+Explore the repo before writing anything:
+- README and package/app entry points
+- folder structure
+- relevant config files
+- the changed files if the tour is PR-focused
+
+Do not start writing steps before you understand the shape of the code.
+
+### 2. Infer the reader
+
+Decide the persona and depth from the request.
+
+| Request shape | Persona | Suggested depth |
+| --- | --- | --- |
+| "onboarding", "new joiner" | `new-joiner` | 9-13 steps |
+| "quick tour", "vibe check" | `vibecoder` | 5-8 steps |
+| "architecture" | `architect` | 14-18 steps |
+| "tour this PR" | `pr-reviewer` | 7-11 steps |
+| "why did this break" | `rca-investigator` | 7-11 steps |
+| "security review" | `security-reviewer` | 7-11 steps |
+| "explain how this feature works" | `feature-explainer` | 7-11 steps |
+| "debug this path" | `bug-fixer` | 7-11 steps |
+
+### 3. Read and verify anchors
+
+Every file path and line anchor must be real:
+- confirm the file exists
+- confirm the line numbers are in range
+- if using a selection, verify the exact block
+- if the file is volatile, prefer a pattern-based anchor
+
+Never guess line numbers.
+
+### 4. Write the `.tour`
+
+Write to:
+
+```text
+.tours/<persona>-<focus>.tour
+```
+
+Keep the path deterministic and readable.
+
+### 5. Validate
+
+Before finishing:
+- every referenced path exists
+- every line or selection is valid
+- the first step is anchored to a real file or directory
+- the tour tells a coherent story rather than listing files
+
+## Step Types
+
+### Content
+
+Use sparingly, usually only for a closing step:
+
+```json
+{ "title": "Next Steps", "description": "You can now trace the request path end to end." }
+```
+
+Do not make the first step content-only.
+
+### Directory
+
+Use to orient the reader to a module:
+
+```json
+{ "directory": "src/services", "title": "Service Layer", "description": "The core orchestration logic lives here." }
+```
+
+### File + line
+
+This is the default step type:
+
+```json
+{ "file": "src/auth/middleware.ts", "line": 42, "title": "Auth Gate", "description": "Every protected request passes here first." }
+```
+
+### Selection
+
+Use when one code block matters more than the whole file:
+
+```json
+{
+  "file": "src/core/pipeline.ts",
+  "selection": {
+    "start": { "line": 15, "character": 0 },
+    "end": { "line": 34, "character": 0 }
+  },
+  "title": "Request Pipeline",
+  "description": "This block wires validation, auth, and downstream execution."
+}
+```
+
+### Pattern
+
+Use when exact lines may drift:
+
+```json
+{ "file": "src/app.ts", "pattern": "export default class App", "title": "Application Entry" }
+```
+
+### URI
+
+Use for PRs, issues, or docs when helpful:
+
+```json
+{ "uri": "https://github.com/org/repo/pull/456", "title": "The PR" }
+```
+
+## Writing Rule: SMIG
+
+Each description should answer:
+- **Situation**: what the reader is looking at
+- **Mechanism**: how it works
+- **Implication**: why it matters for this persona
+- **Gotcha**: what a smart reader might miss
+
+Keep descriptions compact, specific, and grounded in the actual code.
+
+## Narrative Shape
+
+Use this arc unless the task clearly needs something different:
+1. orientation
+2. module map
+3. core execution path
+4. edge case or gotcha
+5. closing / next move
+
+The tour should feel like a path, not an inventory.
+
+## Example
+
+```json
+{
+  "$schema": "https://aka.ms/codetour-schema",
+  "title": "API Service Tour",
+  "description": "Walkthrough of the request path for the payments service.",
+  "ref": "main",
+  "steps": [
+    {
+      "directory": "src",
+      "title": "Source Root",
+      "description": "All runtime code for the service starts here."
+    },
+    {
+      "file": "src/server.ts",
+      "line": 12,
+      "title": "Entry Point",
+      "description": "The server boots here and wires middleware before any route is reached."
+    },
+    {
+      "file": "src/routes/payments.ts",
+      "line": 8,
+      "title": "Payment Routes",
+      "description": "Every payments request enters through this router before hitting service logic."
+    },
+    {
+      "title": "Next Steps",
+      "description": "You can now follow any payment request end to end with the main anchors in place."
+    }
+  ]
+}
+```
+
+## Anti-Patterns
+
+| Anti-pattern | Fix |
+| --- | --- |
+| Flat file listing | Tell a story with dependency between steps |
+| Generic descriptions | Name the concrete code path or pattern |
+| Guessed anchors | Verify every file and line first |
+| Too many steps for a quick tour | Cut aggressively |
+| First step is content-only | Anchor the first step to a real file or directory |
+| Persona mismatch | Write for the actual reader, not a generic engineer |
+
+## Best Practices
+
+- keep step count proportional to repo size and persona depth
+- use directory steps for orientation, file steps for substance
+- for PR tours, cover changed files first
+- for monorepos, scope to the relevant packages instead of touring everything
+- close with what the reader can now do, not a recap
+
+## Related Skills
+
+- `codebase-onboarding`
+- `coding-standards`
+- `council`
+- official upstream format: `microsoft/codetour`