Automação

Scaffold, configure, and deploy custom AI agents with the Google Antigravity 2.0 SDK and agy CLI. Handles auth, AGENTS.md setup, skill installation, MCP server connections, parallel subagent workflows, and Managed Agents API calls. Use when the user wants to build or extend agents on the Antigravity 2.0 platform launched at Google I/O 2026.

Stress-tests an AZIMUTH output against the skill's own structural rules. Paste an AZIMUTH output and invoke to get a severity-rated diagnostic. Diagnoses only — does not rewrite. Use after any real AZIMUTH session to detect quality drift.

Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.

Use when validating rendered web pages, local dev servers, browser automation, screenshots, forms, auth sessions, or UI evidence with strict browser safety boundaries.

Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.

Programming guide for Reachy Mini robot using Python SDK v1.2.6 and REST API. Use when controlling Reachy Mini robots, programming movements (head/antennas/body), accessing sensors (camera/microphone/IMU), recording motions, building AI applications, deploying to Hugging Face, or using the daemon REST API. Covers SDK patterns, coordinate systems, interpolation methods, app management, and OpenAPI

Orchestrates the full preparation workflow for a ticket. Calls /flagrare:intake (which gathers context from Jira/Notion/Figma, grounds the brief in the codebase via /flagrare:codebase-explore, then asks codebase-informed clarifying questions), then hands the codebase-grounded brief to /flagrare:atdd-plan for a TDD-first implementation plan. Use when the user shares a ticket key (e.g. SKU-123), say

Use when diagnosing agent session history, interrupted tool loops, missing tool results, timing bottlenecks, or subagent trace correlation.

Use when optimizing agent runtime loops, card packs, MCP session lifecycle, tool-call count, or multi-agent orchestration patterns.

Audit therapy and behavioral health documentation platforms for clinical quality and regulatory compliance. Reviews SOAP, DAP, and BIRP note template structure, note completeness enforcement and timeliness deadlines, note locking and amendment/addendum workflows, DSM-5 diagnostic code completeness, ICD-10-CM crosswalk accuracy and annual update currency, diagnostic code validation and billing alig

会议纪要整理工作流：汇总指定时间范围内的会议纪要并生成结构化报告。当用户需要整理会议纪要、生成会议周报、回顾一段时间内的会议内容时使用。

Audit legal aid and public defense case management systems -- client intake workflows, Federal Poverty Level eligibility screening accuracy, conflict-of-interest checking, document assembly and e-filing integration, court deadline calculation with rule-based calendaring, pro bono attorney matching and CLE tracking, LSC Case Statistical Report generation, and access-to-justice gap analysis. Use whe