Skill Creator
terrylica
70 published skills · 194 GitHub stars across the catalog. View on GitHub ↗
pr-gfm-validator
Validate and auto-fix GitHub Flavored Markdown links in PR descriptions. Use when creating pull requests, mentioning PR links, gh pr create, GFM validation, or fixing broken PR links. Converts repo-relative paths to branch-specific blob URLs.
iterm2-layout
Configure iTerm2 workspace layouts with TOML-based configuration. Use when user mentions iTerm2 layout, workspace tabs, layout.toml, AutoLaunch script, or configuring terminal workspaces.
hooks-development
Claude Code hooks development guide covering all 10 hook events lifecycle, PostToolUse visibility patterns, PreToolUse guards, Stop hook schema, and debugging. Use when creating hooks, troubleshooting hook output, understanding hook lifecycle, or when user mentions decision block, hook JSON output, stop hook, or Claude Code hooks.
graph-easy
Create ASCII diagrams for any GitHub Flavored Markdown file using graph-easy. Use for READMEs, design docs, specifications, or any markdown needing architecture diagrams. Zero external dependencies for rendering - pure text output embeds directly in markdown.
mise-configuration
Configure environment via mise [env] SSoT. TRIGGERS - mise env, mise.toml, environment variables, centralize config, Python venv, mise templates.
mise-tasks
Orchestrate workflows with mise [tasks]. TRIGGERS - mise tasks, mise run, task runner, depends, depends_post, workflow automation, task dependencies.
link-validation
Universal link validation using lychee for Claude Code sessions. Runs at session end to detect broken links and path policy violations.
link-validator
Validate markdown link portability in Claude Code skills and plugins. Use when checking links, validating portability, fixing broken links, absolute paths, relative paths, or before skill distribution. Ensures relative paths for cross-installation compatibility.
article-extractor
Extracts and organizes MQL5 articles and documentation. Use when researching MQL5 features, MetaTrader API documentation, Python MT5 integration, or algorithmic trading resources.
log-reader
Reads MetaTrader 5 log files to validate indicator execution, unit tests, and compilation errors. Use when user mentions Experts pane, MT5 logs, errors, or asks "did it work".
mql5-indicator-patterns
Develop custom MQL5 indicators with proper patterns. Use when creating indicators, debugging OnCalculate(), working with buffers, or implementing multi-timeframe indicators in MetaTrader 5.
python-workspace
Configures Python development workspace for MQL5 integration. Use when setting up MetaTrader 5 Python API, configuring mt5 package, or establishing MQL5-Python workflows.
notion-sdk
Control Notion via Python SDK. TRIGGERS - Notion API, create page, query database, add blocks, automate Notion. PREFLIGHT - requires token from notion.so/my-integrations.
plugin-validator
Validate plugin structure, manifests, and silent failure patterns. TRIGGERS - plugin validation, validate plugin, check plugin, silent failures, hook audit, stderr emission.
skill-architecture
Meta-skill for creating Claude Code skills. TRIGGERS - create skill, YAML frontmatter, validate skill, TodoWrite templates, bundled resources (scripts/references/assets), progressive disclosure, allowed-tools, skill architecture. Use when creating, validating, or structuring skills.
slash-command-factory
Generate custom Claude Code slash commands through intelligent 5-7 question flow. Creates powerful commands for business research, content analysis, healthcare compliance, API integration, documentation automation, and workflow optimization. Outputs organized commands to generated-commands/ with validation and installation guidance.
clickhouse-architect
ClickHouse schema design authority (hub skill). Use when designing schemas, selecting compression codecs, tuning ORDER BY, optimizing queries, or reviewing table structure. **Delegates to**: clickhouse-cloud-management for user creation, clickhouse-pydantic-config for DBeaver config, schema-e2e-validation for YAML contracts. Triggers: "design ClickHouse schema", "compression codecs", "MergeTree optimization", "ORDER BY tuning", "partition key", "ClickHouse performance", "SharedMergeTree", "ReplicatedMergeTree", "migrate to ClickHouse".
code-clone-assistant
Detects and refactors code duplication using PMD CPD. Use when identifying code clones, addressing DRY violations, or refactoring duplicate code across repositories.
multi-agent-e2e-validation
Multi-agent parallel E2E validation workflow for database refactors and system migrations. Use when validating QuestDB deployments, schema migrations, bulk data ingestion pipelines, or any database-centric refactor requiring comprehensive testing across environment, data flow, and query layers.
multi-agent-performance-profiling
Multi-agent parallel performance profiling workflow for identifying bottlenecks in data pipelines. Use when investigating performance issues, optimizing ingestion pipelines, profiling database operations, or diagnosing throughput bottlenecks in multi-stage data systems.
schema-e2e-validation
Run Earthly E2E validation for YAML schema contracts. Use when validating YAML schema changes, testing schema contracts against live ClickHouse, or regenerating Python types, DDL, and docs from YAML. For SQL schema design and optimization, use clickhouse-architect skill instead.
constraint-discovery
Spawn 5 parallel Explore agents to discover project constraints. TRIGGERS - constraint scan, degrees of freedom, /ralph:start Step 1.4.5, project memory analysis.
session-guidance
Configure Ralph loop guidance via AUQ flows - forbidden/encouraged items from constraint scan. TRIGGERS - session guidance, loop configuration, /ralph:start Step 1.6.
ai-assisted-operations
AI-powered issue summarization, auto-labeling, and Q&A using gh-models with 88% effectiveness. Use when analyzing issue content, suggesting labels, or extracting insights.