ilude

Capture and review operator feedback, frustration about agent behavior, or workflow failures when refining AGENTS.md, skills, or agent workflows. Compare relevant prior evidence before proposing changes.

Inspect and operate ZeroOne OpenStack resources using the local cloud configuration. Use for flavors, quotas, worker capacity, networking, floating IPs, and OpenTofu deployment questions.

Local browser automation via Brave CDP. Use for logged-in checks, exact page targets, screenshots, or controlled browser comparisons.

Use native Herdr for explicitly directed communication with independent sessions on the same connected Herdr server, requested long-running processes and logs inside Herdr, or visible-agent recovery when owned subagent controls cannot reach a pane.

Review code changes for defects and relevant concerns, with evidence and priorities calibrated to the project's actual use. Use for reviews of working-tree changes, commits, branches, or pull requests, including adversarial review.

Classify and analyze tool-call and subagent failures without confusing legitimate command, test, HTTP, or application outcomes with failures of the tool mechanism. Use for session reviews, failure counts, recurring-error analysis, and diagnosis of tool or…

Analyze existing Pi sessions and usage records across default, legacy, or both profiles. Prefer log_analytics; use read-only JSONL shell tools when it cannot answer. Use for session discovery, tool failures, content lookup, and local usage analysis, not new…

Safely integrate plan or subagent branches, especially when the destination checkout has existing changes. Use for Git merges, dirty-worktree preservation, conflict handling, and post-merge cleanup.

Activate when user needs multi-URL scraping, browser automation pipelines, or efficient tool orchestration to reduce API round-trips and context usage.

Language-agnostic API design patterns covering REST and GraphQL, including resource naming, HTTP methods, status codes, versioning, pagination, filtering, authentication, error handling, and schema design. Activate when working with APIs, REST endpoints,…

Git workflow and commit guidelines. Trigger keywords: git, commit, push, .git, version control. MUST be activated before ANY git commit, push, or version control operation. Includes security scanning for secrets (API keys, tokens, .env files), commit message…

Testing workflow patterns and quality standards. Activate when working with tests, test files, test directories, code quality tools, coverage reports, or testing tasks. Includes zero-warnings policy, targeted testing during development, mocking patterns, and…

Ansible automation workflow guidelines. Activate when working with Ansible playbooks, ansible-playbook, inventory files (.yml, .ini), or Ansible-specific patterns.

Claude Code AI-assisted development workflow. Activate when discussing Claude Code usage, AI-assisted coding, prompting strategies, or Claude Code-specific patterns.

Guidelines for containerized projects using Docker, Dockerfile, docker-compose, container, and containerization. Covers multi-stage builds, security, signal handling, entrypoint scripts, and deployment workflows.

C# and .NET project workflow guidelines. Activate when working with C# files (.cs), .csproj, .NET projects, or C#-specific tooling.

YouTube video cache operations with Qdrant. Auto-checks cache when YouTube URLs detected. Provides semantic search, verification, ingestion, and archive access. Shows metadata by default, transcript on request.

Run Python code in lesson context with proper uv and venv handling for agent-spike project. Activate when user wants to run tests, demos, or CLI commands for lessons in lessons/ directories. Project-specific for agent-spike multi-agent learning.