terrylica

Park a draft message/text in macOS Notes for the operator to review and edit, then read it back before acting (e.g. before sending to a real person). Notes is the source of truth (AppleScript CRUD, iCloud-synced, provenance-stamped with the Claude Code session UUID); Stickies is a best-effort view-only desktop mirror. Use whenever you draft something a human should confirm/edit before it is sent or committed — messages, replies, announcements, anything outbound. TRIGGERS - hold this draft, park the message, let me edit first, draft for my approval, save to notes for review, read back the draft.

Autonomous polyglot monorepo bootstrap meta-prompt on the moon + proto + Bun stack (Nx-convergent). TRIGGERS - new monorepo, new repository, polyglot setup, scaffold repo, moon proto bootstrap, monorepo from scratch.

Access Gmail via CLI with 1Password OAuth. Use when user wants to read emails, search inbox, export messages, create drafts, or.

Keep a graphify knowledge graph current automatically: --watch mode (live rebuild on file save) or a post-commit git hook (rebuild per commit). TRIGGERS - graphify watch, auto-sync graph, keep graph updated, graphify git hook, graph out of date.

Build a multimodal knowledge graph from any folder (code, markdown, PDFs, images) using graphify. Produces graph.html, GRAPH_REPORT.md, graph.json, Obsidian vault, optional agent wiki. TRIGGERS - graphify, build knowledge graph, graph this folder, map this codebase, concept graph, god nodes, surprising connections.

Query an already-built graphify knowledge graph: natural-language questions, path-finding between two concepts, or explain a single node — without re-reading the source files. TRIGGERS - graphify query, ask the graph, what connects, path between concepts, explain node, query knowledge graph.

Install and verify the graphify engine (uv tool install graphifyy). Use for first-time setup, upgrades, or when the graphify CLI is missing/broken. TRIGGERS - install graphify, graphify setup, setup knowledge graph tool, graphify not found.

Send Pushover notifications with UUID-linked verbatim JSONL audit trail. TRIGGERS - pushover notify, send pushover, observability alert, verbatim notification, fleet alert, pushover-lookup, audit log notification, push notification with UUID

Autonomous setup and management of external service monitoring using UptimeRobot (HTTP endpoint monitoring) and Healthchecks.io (heartbeat/Dead Man's Switch monitoring). Use when setting up monitoring for Cloud Run Jobs, VM services, or investigating monitoring configuration issues. Includes Pushover integration, validated API patterns, and dual-service architecture.

Workflow for acquiring historical Ethereum blockchain data using Google BigQuery free tier. Empirically validated for cost estimation, streaming downloads, and DuckDB integration. Use when planning bulk historical data acquisition or comparing data source options for blockchain network metrics.

Empirical validation workflow for blockchain data collection pipelines before production implementation. Use when validating data sources, testing DuckDB integration, building POC collectors, or verifying complete fetch-to-storage pipelines for blockchain data.

Systematic workflow for researching and validating blockchain RPC providers. Use when evaluating RPC providers for historical data collection, rate limits, archive access, compute unit costs, or timeline estimation for large-scale blockchain data backfills.

Execute chunked historical blockchain data backfills using canonical 1-year pattern. Use when loading multi-year historical data, filling gaps in ClickHouse, or preventing OOM failures on Cloud Run. Keywords chunked_backfill.sh, BigQuery historical, gap filling, memory-safe backfill.

Troubleshoot and manage GCP e2-micro VM running eth-realtime-collector. Use when VM service is down, systemd failures occur, real-time data stream stops, or VM network issues arise. Keywords systemd, journalctl, eth-collector, gcloud compute.

Monitor and troubleshoot dual-pipeline data collection systems on GCP. This skill should be used when checking pipeline health, viewing logs, diagnosing failures, or monitoring long-running operations for data collection workflows. Supports Cloud Run Jobs (batch pipelines) and VM systemd services (real-time streams).

AI-powered issue operations via gh-models. TRIGGERS - issue summarization, auto-labeling, issue insights.

Create GitHub Issue knowledge entries. TRIGGERS - share knowledge, document solution, create how-to, add to knowledge base.

Regex file search via gh-grep extension. TRIGGERS - search code files, grep repository, file content search.

GitHub label and milestone management. TRIGGERS - create label, edit label, manage milestones, issue taxonomy.

GitHub Issue CRUD and state management. TRIGGERS - create issue, close issue, update issue, bulk process issues.

Search GitHub Issues and PRs with qualifiers. TRIGGERS - search issues, find issue, issue filter, gh issue list.

Test and validate ClickHouse Cloud connection using clickhouse-connect for gapless-crypto-clickhouse. Use when validating connectivity, troubleshooting connection issues, or verifying environment configuration. Includes version check and query validation.

Store ClickHouse Cloud credentials in Doppler + 1Password for gapless-crypto-clickhouse. Use when setting up new services, rotating credentials, or backing up authentication material. Covers API keys, connection details, and database password storage.

Fetch ClickHouse Cloud service details from API (organization ID, service endpoints, configuration). Use when setting up new ClickHouse Cloud services, discovering endpoints, or validating service metadata for gapless-crypto-clickhouse project.

Onboard company employees (Claude Code CLI users) to use gapless-crypto-clickhouse package with ClickHouse Cloud credentials. Use when company employee needs to set up ClickHouse Cloud access, mentions first-time setup, credential configuration, connection testing, or troubleshooting ClickHouse Cloud connections.

Install, configure, and validate local ClickHouse for gapless-crypto-clickhouse development and backtesting. Use when setting up local development environment, enabling offline mode, improving query performance for backtesting, or running E2E validation. Includes mise/Homebrew/apt installation, mode detection, connection validation, and E2E workflow scripts.

Fetch market data using CryptoKlineVisionData with Failover Control Protocol (cache → Vision API → REST API). TRIGGERS - fetch market data, use CKVD, access Binance, get klines, OHLCV data, CryptoKlineVisionData API.

Run tests for crypto-kline-vision-data with proper markers and coverage. TRIGGERS - write tests, run tests, pytest, test coverage, unit tests, integration tests, mocking patterns.

Research CKVD codebase for implementation details, patterns, or architecture questions. TRIGGERS - how does FCP work, understand data flow, find code, explore codebase, architecture questions.

Monitor and diagnose FCP (Failover Control Protocol) behavior, cache health, and data source performance. TRIGGERS - FCP issues, cache problems, slow data, Vision API errors, REST fallback, data source debugging.

Systematically improve documentation quality from 7/10 → 9/10 using assessment checklists and transformation patterns. Use when documentation exists but lacks Quick Start, clear prerequisites, or working examples. Optimized for crypto/trading data projects.

Query remote Parquet files via HTTP without downloading using DuckDB httpfs. Leverage column pruning, row filtering, and range requests for efficient bandwidth usage. Use for crypto/trading data distribution and analytics.

Decompose complex questions into 4-6 parallel investigations with different perspectives, synthesize into phased decision framework. Use when facing architecture decisions with multiple unknowns in crypto/trading data platforms.

Schema migrations: ALTER patterns, engine changes, zero-downtime swaps, clickhouse-local offline migrations, and lightweight UPDATE/DELETE strategies.

Advanced query tuning: join algorithms, skip index selection, EXPLAIN interpretation, ProfileEvents profiling, and optimizer settings.

Reference for pi-mono build pipeline and runtime compilation methods. Covers tsgo compilation, bun build --compile for standalone binaries, cross-platform builds, build order, and performance characteristics. Use when building pi, optimizing startup, choosing between source vs binary execution, or troubleshooting build issues.

Reference for pi-mono fork infrastructure - Minimax M2.5-highspeed provider setup, 1Password service token auth chain, pi binary builds, and dual-tool wiring (Claude Code Max + Minimax). Use when configuring providers, debugging auth, building pi, or onboarding to this fork.

ClickHouse SQL anti-patterns and performance constraints discovered during Gen200-Gen600 barrier framework. Use when writing ClickHouse SQL, creating new barrier/pattern generations, modifying array functions, window functions, parameter sweeps, forward arrays, or encountering slow queries, OOM, NULL entry prices, wrong barrier detection, arrayFirstIndex returning 0, or aligning SQL results with backtesting.py. TRIGGERS - ClickHouse SQL, barrier SQL, array function, window function, trailing stop SQL, parameter sweep, slow query, OOM, arrayFirstIndex, leadInFrame, groupArray, arrayFold, arrayScan, threshold-relative, anti-pattern, performance constraint, forward arrays, self-join, O(N×M), SQL vs Python, SQL vs backtesting.

Brute-force pattern sweep methodology for range bar microstructure discovery. Guidelines (not constraints) for designing, executing, and evaluating new sweep generations. Use when creating Gen600+, designing feature sweeps, setting barrier parameters, choosing evaluation metrics, or reviewing sweep results. TRIGGERS - new generation, Gen600, sweep design, feature sweep, barrier grid, evaluation metrics, cross-asset validation, multiple testing, Kelly fraction, Bonferroni, signal count, rolling window, quantile method.

CCXT cryptocurrency exchange library for Java developers. Covers both REST API (standard) and WebSocket API (real-time). Helps install CCXT, connect to exchanges, fetch market data, place orders, stream live tickers/orderbooks, handle authentication, and manage errors in Java projects. Use when working with crypto exchanges in Java applications, trading systems, or financial software. Requires Java 21+.

Compile MQL5 indicators via CLI using X: drive mapping to bypass 'Program Files' path spaces issue. Use PROACTIVELY after editing ANY .mq5 or .mqh file. Triggers - after editing MQL5 code, compile, build, MetaEditor, .mq5, .mqh, indicator, script, EA, expert advisor, "test it", "try it", "run it", path space errors. (project)