MCP App StoreMCP App StoreThis skill enforces a context-loading gate for agents: it detects runtime mode (plugin, MCP, or adhoc), loads bootstrap rules or context files, executes required preparation steps, and prevents further actions until context is confirmed. It standardises how agents gather and verify the current workspace, docs, and tool instructions.
Use this skill at the start of planning or executing workflows where up-to-date context matters — onboarding new tasks, switching repositories, or running multi-step automation that depends on environment-specific prep. It is especially useful for agents operating as plugins or within MCP-style orchestrations.
docs/ and bootstrap hooks.Designed for agent platforms and orchestrators (Codex/Copilot-style assistants, Claude/Gemini CLI integrations) that can call a get_context_instructions tool or read workspace documentation. Useful wherever a hard gating of prep steps is required.
A purely instructional skill (no scripts) that guides agents to load execution context before acting. Three modes (Plugin, MCP, Adhoc) are clearly defined with step-by-step instructions. Specific to the GridDynamics Rosetta framework, limiting broad applicability. No security concerns whatsoever — no code, no network calls, no credentials.
Clean skill with no security issues. Instructions are clear and well-structured for mode detection, but usefulness is limited to a specific framework. No scripts included, so code quality reflects SKILL.md quality alone.
Reasoning
Structured 7-step meta-cognitive reasoning skill that guides analysis, decomposition, and confident decision-making with explicit caveats.
Rosetta Testing Specialist
Expert guidance for writing isolated, idempotent tests with 80%+ coverage and strict external-only mocking.
Solr Semantic Search Expert
Implement phrase-tagging semantic search in Apache Solr 9.x using concept tagging, taxonomies, and graph-based path resolution.
Subagent Contract
Defines the operational contract, boundaries, and escalation protocols for spawned subagents.
Sensitive Data Protection
Critical security skill for identifying, masking, and protecting PII, API keys, and other sensitive credentials during AI agent operations.
Starlark Dev
Create, debug, and test Kurtosis Starlark packages — write package structure, run dry-runs, and inspect plan execution for reliable orchestration.
Maestro Orchestrate
Orchestrates complex engineering workflows with enforced design and approval gates, child-agent delegation, and session state management.
Run Execute
Orchestrates execution of work items across modes (autopilot, confirm, validate) with scripted init/complete tooling, plan/test/report artifacts and strict gati
Caveman Compress
Compress natural-language memory files into a compact 'caveman' format to save LLM tokens while preserving code, links, and structure.
Execution Plan Splitter
Break large goals into 30/60/90-day execution plans with milestones, resource needs, and stop/go criteria for practical roadmaps.
Overnight — Autonomous Long-Running Coding
Orchestrates long-running coding goals: decomposes objectives into atomic tasks, dispatches isolated worktree workers, verifies acceptance criteria, and merges
Verifying Markdown Formatting
Checks Markdown files for structural and stylistic formatting issues (headings, lists, code blocks, links) and applies deterministic fixes.
Writing Implementation Plans
Generate detailed, engineer-ready implementation plans from design docs: file paths, step-by-step tasks, tests, and verification instructions.