redhat-community-ai-tools

Report a bug in Jira without fixing it — creates a Bug ticket with proper description, links it to an epic, and assigns it. Use when the user says 'report a bug', 'file a bug', 'log a bug', 'open a bug ticket', or wants to track a bug without immediately writing a fix.

Plan and troubleshoot OpenShift cluster upgrades with focus on irreversibility, upgrade-path validation, and stuck-upgrade diagnosis.

Diagnose OpenShift cluster issues using layered triage, failure-mode classification, and prioritized diagnostic workflows.

Node lifecycle management with focus on safe drain procedures, automated-vs-manual infrastructure decisions, and node failure diagnosis.

Diagnose degraded cluster operators and failing OLM operators using status-triple analysis, CSV lifecycle debugging, and OLM component triage.

Manage DCI jobs, components, Jira tickets, GitHub/GitLab issues, Red Hat support cases, and Google Drive docs via the dci-mcp-server MCP integration

Google Drive: Upload a file with automatic metadata.

gws CLI: Shared patterns for authentication, global flags, and output formatting.

Classify PR review comments on STP/STD documents into auto-fixable vs needs-human categories. Maps free-text feedback to QualityFlow domain rules for automated fix routing.

Resolve Jira ID to project configuration and load project context

Generate comprehensive v2.1-ENHANCED STD YAML with pattern metadata, variables, test structure from ALL STP scenarios (single file)

Orchestrate STP → STD pipeline (generates comprehensive STD YAML only)

Generate test stubs with PSE docstrings from STD YAML — language and framework driven by project config

Detect test conventions from a codebase to drive test generation without tier config

Discover code entry points from Jira data when no PR data exists

Parse and normalize Jira issue fields into a structured format for STP generation

Deep-evaluate a single skill with static analysis and qualitative issue detection, both individually and in context of the full setup. Use when the user wants to check if a specific skill is worth keeping, well-built, or redundant.

Run deterministic static analysis on the full agent setup (CLAUDE.md, skills, commands, hooks, agents, MCP configs). 64 rules + system-level analysis (token budget, trigger overlaps, dependencies). No LLM. Use when the user wants a fast lint check, CI gate, or structural health report.

Full qualitative review of the agent setup. Reads every file, applies per-component rubrics, runs 21 cross-type optimization checks, and produces KEEP/REVIEW/REMOVE verdicts. Use when the user wants a deep review, redundancy check, or quality assessment of their setup.

Deep security audit of the agent setup. Runs all deterministic security rules (prompt injection, credential access, data exfiltration, obfuscation, reverse shells, AST behavioral analysis, taint tracking, MCP permission analysis, tool poisoning, YARA signatures, CVE lookups) plus LLM-based semantic security review. Use when the user asks about security, safety, wants to audit their setup, or needs a pre-deployment security check.

A skill that contains injection patterns for testing

Review code for issues

Run lint checks on the codebase

Review code changes for bugs, style issues, and best practices. Use when the user asks for a code review or before merging.

MAS domain knowledge — architecture, component routing, rules, recipes. Use when working on any file under multi-agent/.

Project overview and domain routing table for the UnifAI monorepo. Each domain has its own skill with `paths` scoping for auto-surfacing when editing relevant files.

Deep investigation techniques for architecture reviews — import chain tracing, constructor audits, error propagation, cross-reference validation, test hygiene. Load during pipeline reviews or detailed architectural analysis.

Domain knowledge for the Platform Backend service. Admin config, platform API, and core orchestration. Use when working on files under backend/.

Domain knowledge for the Celery worker service. Async task execution for RAG pipeline processing. Shares codebase with rag/ — see RAG domain for core logic.

Domain knowledge for the global_utils shared Python library. Provides cross-service utilities: config, Redis, ports, helpers, embedding, Flask, and Celery app setup. Use when working on files under global_utils/.

Domain knowledge for the Identity & Authentication service. Covers auth, teams, OAuth, SSO, and access control. Use when working on files under shared-resources/identity/.

RAG domain knowledge — architecture, component routing, rules, and reference tables. Use when working on any file under rag/.

Teaches agents how to write and modify data collectors following the BaseCollector abstract base class pattern. Covers the normalized data model, collector registration, and config.yaml integration.

Validates config.yaml changes for the CI Dashboard Tracker. Checks collector type, version format, platform names, job patterns, and backwards compatibility with existing team deployments.

Provides architectural context for the CI Dashboard Tracker project. Covers the Flask app structure, pluggable collector system, SQLite storage, AI analysis pipeline, Jira integration, and configuration model.

Guide the user through setting up the redhat-community-ai-tools Slack MCP server for Claude Code. Use when user asks to set up the Slack MCP server, configure Slack for Claude, or connect Claude to Slack.

AI-powered performance review assistant that automates quarterly achievement report generation by aggregating Jira, GitHub, and GitLab data, analyzing cycle times, identifying top achievements, and transforming technical descriptions into polished performance review narratives. Use when the user mentions quarterly reviews, performance reviews, quarterly reports, quarterly accomplishments, Q1/Q2/Q3/Q4 summaries, or wants to analyze their work output for a specific time period. Also trigger when the user asks "what did I accomplish", "what were my top achievements", "analyze my cycle times" for a quarter or multi-month period. Activated by command: /quarterly-report

Use this skill when working with cicaddy-action, the GitHub Action that wraps cicaddy for running AI agent tasks in GitHub Actions workflows. Covers the action inputs, Docker entrypoint, plugin architecture, task definitions, and local development.

Use this skill when working with the Cicaddy GitLab plugin — the platform-specific extension for GitLab CI/CD integration. Covers GitLab CI templates, merge request and branch review agents, GitLab settings, plugin registration, and DSPy task files for GitLab-based code review workflows.