eagleisbatman

ADK Agent-to-Agent (A2A) protocol integration. Use when building remote agent communication — exposing ADK agents as A2A servers or connecting to external A2A agents as clients.

ADK App pattern with plugins, event compaction, and resumability. Use when you need plugins (context filtering, debug logging), event summarization, or resumable long-running operations.

ADK artifact services for file storage. Use when agents need to save/load files, images, or binary data — InMemory, File, and GCS artifact backends.

ADK authentication and credentials. Use when adding auth to tools — API keys, bearer tokens, OAuth2 flows, OpenID Connect, service accounts, and credential storage services.

Catalog of all ADK built-in tools. Use when looking for pre-built tools to add to agents — search, memory, artifacts, transfer, grounding, and user interaction tools.

Implement ADK agent and tool callbacks. Use when adding lifecycle hooks — before/after agent execution, before/after tool calls, for logging, validation, conditional execution, or response modification.

ADK code execution backends. Use when agents need to write and run Python code — BuiltIn, Container, VertexAI, GKE, or local executors.

Deploy ADK agents to Cloud Run, Vertex AI Agent Engine, or GKE. Use when containerizing and deploying agents for production — covers Dockerfile, adk deploy CLI, and service configuration.

Write code the way an experienced human engineer writes it — minimal, direct, first-principles, no AI slop, no over-engineering. Use this skill for EVERY code generation, refactoring, or code review task, in any language. Trigger especially when the user says "maintainable", "clean", "simple", "no slop", "don't over-engineer", "production code", "like a human wrote it", or complains that generated code is bloated, over-abstracted, over-commented, or defensive. Also use when writing new modules, functions, scripts, API endpoints, or components from scratch.

Install hook-based engineering governance for agent-led projects. Use when the user says: 'govern this project', 'install governance hooks', 'agent governance', 'context bloat guard', 'hook-based engineering governance', 'stop agents ignoring instructions', or asks to make AGENTS.md / CLAUDE.md enforceable through hooks.

Full project onboarding: generates a lean CLAUDE.md, bootstraps LLM Wiki, links Obsidian vault, and installs eagle-skills (15 skills + 13 agents). Use when starting a new project, onboarding to a codebase, or when the user says: 'init claude', 'setup claude md', 'create claude.md', 'project init', 'eagle init', 'bootstrap this project', 'set up this repo for claude', 'add claude.md', 'onboard this project', 'install eagle skills'. Also trigger when you detect a project has no CLAUDE.md and the user is about to do significant work in it.

Use this skill to create project trackers, task lists, roadmaps, and Gantt charts as .xlsx files that open in Excel AND import cleanly into Google Sheets. Triggers on: 'project tracker', 'task tracker', 'create a Gantt chart', 'project plan', 'roadmap', 'timeline', 'sprint board', 'RAID log', 'who's doing what by when', 'track tasks with owners and dates', 'turn this into a tracker', or when the user lists tasks/owners/dates and wants them organized into a trackable, shareable sheet. Produces status dropdowns, status-colored Gantt bars, computed duration/%-complete, a today marker, and a small dashboard. Composes with eagle-clean-sheet styling. Do NOT use for ad-hoc data tables with no time/ownership dimension (use eagle-clean-sheet directly), or for live Google Sheets API integration.

Write like a human, not like an AI. Use this skill whenever the user asks for writing that sounds natural, authentic, specific, or not AI. Trigger on: human writing, make it sound human, less AI, no AI voice, ghost mode, no corporate tone, no AI slop, write like a journalist, write like a real person, degpt, README polish, article rewrite, email rewrite, report rewrite, or social post rewrite.

Route Spectral review requests to the correct Eagle specialist. Use when the user says spectral agents, spectral review, full spectrum review, run review specialists, review this PR with agents, choose the right review agents, or asks for code review without naming a specialist. Do not default to plan, investigate, or ship unless the user is planning, debugging, or shipping.

One-time global environment setup for Claude Code. Use when the user says: 'eagle bootstrap', 'setup my environment', 'eagle setup', 'first time setup', 'configure claude globally', 'install eagle environment', 'set up my machine for claude'. This skill enriches the global ~/.claude/CLAUDE.md with behavioral rules, installs the compact.sh token-saving hook, configures the Obsidian vault path, and confirms eagle-skills agents are installed. Run once per machine — safe to re-run (idempotent, skips what's already done).

Review and add new rules to compact-rules.json for the token-saving hook. Use when the user says: 'add compact rules', 'compact-add', 'add a compact rule', 'this command is too verbose', 'compact this command', 'grow compact database'.

Manage Eagle Mem feature verification and anti-regression guardrails. Use when: 'feature pending', 'verify feature', 'waive feature', 'feature verification', 'pending verifications', 'release blocked', 'feature guard', 'smoke test', 'what needs verification', 'mark feature verified', 'skip verification'. Uses the eagle-mem CLI.

View and sync Claude Code, Codex, Grok, and Antigravity memories, plans, tasks, and graph memory mirrored in Eagle Mem. Use when: 'eagle memories', 'show memories', 'sync memories', 'what does the agent remember', 'show plans', 'show tasks', 'mirror memories', 'onboard project', 'what did past sessions learn'. Uses the eagle-mem CLI.

Coordinate multi-agent work with Eagle Mem's durable orchestrator/worker lanes. Use when the user wants an orchestrator model, parallel lanes, Claude Code and Codex sharing worker status, worktree coordination, handoffs, or long-running implementation split across agents.

TaskAware Compact Loop — break complex work into tasks that survive context compaction. Use when: 'break this into tasks', 'create task plan', 'task loop', 'compact loop', work is too large for one context window, multi-step implementation.

Build or update a structured project overview for Eagle Mem. Use when: 'eagle overview', 'project overview', 'summarize this project', 'what is this project', 'update overview', or when SessionStart says no overview exists. Produces a multi-paragraph briefing.

Search Eagle Mem's persistent memory. Use when: 'eagle search', 'search memory', 'what did I do', 'find in memory', 'past sessions', 'what happened with', 'search my history', 'what do you remember about', 'show recent sessions', 'what files changed', 'memory stats'. Uses the eagle-mem CLI.