Triggered when managing, creating or validating feature specifications (specs) in spec-*.md

Use this skill when you want to sync GitHub activity with Jira — create tickets from issues, link PRs to tickets, update status from commits, or generate sprint summaries.

Diagnose and fix MCP configuration/runtime issues across supported integrations using agents CLI checks.

Pull Request creator skill with automated template, testing checklist, security audit checklist, and release notes generator.

Use this skill when you want to automatically triage GitHub issues — classify type, add labels, route to teams, and draft initial responses.

Use this skill when you want to automatically review GitHub pull requests and post line-level comments with findings, suggestions, and approval recommendations.

Use this skill when the user has a meeting recording, transcript, or notes and wants a structured summary with action items, decisions, and follow-ups.

Use this skill when the user wants to analyze log files — find errors and their frequency, detect anomalies, build incident timelines, or summarize what happened during an outage.

Standardized Git commit generator skill with Conventional Commits rules, scope tagging (e.g. feat(itau):, fix(security):), and change summary rules.

Use this skill when the user wants to create charts, graphs, or dashboards from data — bar charts, line charts, scatter plots, heatmaps, or multi-panel dashboards.

Scaffolding guide for building vertical slice features in FinanceHub (.NET 10), including Use Cases, Minimal API endpoints, Command/Query handlers, FluentValidation, and financial reconciliation endpoints.

Use this skill when the user wants to schedule recurring tasks, convert natural language schedules to cron expressions, or manage APScheduler jobs.

Use this skill when building agentic loops with Claude tool use — defining tools, handling tool calls, parallel execution, and multi-step reasoning.

Automated code review skill focusing on financial security, token leakage detection, concurrency bugs, EF Core performance traps, and architectural compliance.

Use this skill when you need Claude to return structured JSON — data extraction, classification, form parsing, or any task needing machine-readable output.

Use this skill when building retrieval-augmented generation (RAG) systems — document ingestion, chunking, embedding, vector search, and grounded responses.

Use this skill when the user wants to analyze, summarize, extract data from, or ask questions about PDF documents using Claude's native PDF support.

Use this skill when the user wants to automate desktop or browser tasks — clicking, typing, screenshotting, running GUI apps, or filling web forms.

Diagnose and classify MCP and Local Memory startup failures in this repo. Use this skill when codex mcp list, Codex startup, hook startup, mise trust, or Local Memory listener checks fail.

This skill should be used when the user asks to "test the harness", "run integration tests", "validate features with real API", "test with real model calls", "run agent loop tests", "verify end-to-end", or needs to verify OpenHarness features on a real codebase with actual LLM calls.