review-proposals
审查并批准（或拒绝）来自审查指引监控代理的待处理更新建议，并将批准的变更 应用到业务领域配置中。当审查指引监控代理提出建议时使用，或当用户说 "审查审查指引建议""有哪些待处理的审查指引更新"或想逐一处理偏离驱动的审查指引变更时使用。
150 repo starsObserved in 1 repos
Agent Building
Agent Building skills
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
skill-creator-primer
You **MUST** load this skill before the skill-creator skill AND before making ANY change to, or conducting a review of ANY Agent Skill. Triggers include creating, editing, reviewing, or contributing to any part of an Agent Skill (description, frontmatter, body, references, scripts, trigger evals, conflicts, etc).
150 repo starsObserved in 1 repos
Agent Building
smart-question-generator
Takes aggregated ambiguity insights from the LLM synthesis stage and produces ≤5 ranked questions to surface to the user. Applies a two-layer anti-fabrication filter (pre-LLM exclusion of score<3 insights + post-LLM structural strip) so that Q&A surfaces only genuine ambiguities. Used as Stage 4 of the /gaai:bootstrap pipeline.
150 repo starsObserved in 1 repos
Agent Building
deploy-observability
Deploy, start, and update the Alibaba Cloud Observability MCP Server (阿里云可观测 MCP Server). Use this skill whenever the user mentions deploying, installing, starting, updating, or configuring the observability MCP server, Alibaba Cloud SLS/CMS MCP tools, or wants to connect Alibaba Cloud monitoring to their AI coding agent. Also trigger when the user says things like 'set up MCP server', 'install observability tools', 'deploy aliyun MCP', 'configure SLS MCP', or 'update MCP server tools'.
149 repo starsObserved in 1 repos
Agent Building
quark-torch-skill-sync
Detect upstream Quark changes that affect the skill system and classify required updates. Use when Quark docs, CLI flags, quantization templates, model support, or source behavior may have drifted from the skill contracts. Trigger for "check if skills are up to date", "sync skills with Quark", "has Quark changed", "update skills after Quark upgrade", or when debugging reveals a mismatch between skill instructions and actual Quark behavior.
148 repo starsObserved in 2 repos
Agent Building
subagent-dev
Этот скилл MUST быть вызван когда tasks.md готов и требуется автономное параллельное выполнение субагентами (implementer + reviewer на каждую задачу). SHOULD также вызывать для сложных задач с 5+ атомарными шагами. Do NOT использовать для планирования — используй brainstorm или write-plan; для одиночных задач — выполняй напрямую.
148 repo starsObserved in 2 repos
Agent Building
training-data-curation
Guidelines for creating high-quality datasets for LLM post-training (SFT/DPO/RLHF). Use when preparing data for fine-tuning, evaluating data quality, or designing data collection strategies.
148 repo starsObserved in 2 repos
Agent Building
nexus-model-eval
Grade LLM models on Nexus tool-use (the two-tool getTools/useTools protocol) with the live eval harness in tests/eval/. Use when asked to grade, benchmark, or evaluate one or more OpenRouter (or other provider) models for how well they drive Nexus tools — e.g. "grade google/gemma-4-31b-it" or "benchmark these models on our harness".
148 repo starsObserved in 1 repos
Agent Building