Total 54,636 skills, AI & Machine Learning has 9075 skills
Showing 12 of 9075 skills
Author, audit, and improve Grafana SKILL.md files against Anthropic's published Agent Skills guidance and the four-dimension rubric the grafana/skills CI gate uses (conciseness, actionability, workflow clarity, progressive disclosure). Applies the canonical SKILL.md structure (YAML frontmatter + body + references/ + scripts/ + assets/), the "pushy description" trigger pattern, the three-level progressive-disclosure model, and the validate-fix-rerun feedback loop. Use when creating a new skill in this repo, when reviewing a skill PR, when a skill's Tessl review score is below 75 (the merge gate), when a skill's description isn't getting picked up by agents, when restructuring a long SKILL.md into a bundle, or when the user asks how to write, improve, optimize, audit, or fix a skill - even if they don't say "skill" explicitly (e.g. "this isn't triggering", "Tessl scored this 72", "split this doc").
Read-only root-cause analysis for a tracker issue. Identifies the bug's location and the minimal change surface so the next agent can implement the fix without re-exploring the repo. Outputs a short summary, the files that need to change, and the proposed approach.
Simulate a collaborative dev team session where multiple role-based personas (PM, Architect, Developer, QA) respond to the same problem together in one session. Use when designing a feature, reviewing a proposal, or onboarding a new initiative and you want multi-role perspective without switching agents manually.
Add one optional external Codex critique after the existing council has produced a decision draft. Use when an ambiguous, high-consequence decision would benefit from a separate model invocation's attempt to break the synthesis. Requires explicit consent before sending the compact draft and disagreement to OpenAI, labels same-provider reviews honestly, and marks the review absent when the adapter is unavailable.
Default guidance for building AI agents. Use for generic requests to build, create, scaffold, design, architect, or implement an AI agent, agent app, tool-calling agent, durable agent, multi-agent system, or scheduled agent. Not for code-review or incident-investigation agent products.
Implement a set of GitHub issues in parallel - triage or take an explicit issue list, group by file-conflict, create a worktree per lane, delegate to sub-agents, open a PR per lane; never merges. Use when asked to implement issues, work the backlog, or pick up multiple issues in parallel.
MLflow 3 GenAI agent evaluation. Use when writing mlflow.genai.evaluate() code, creating @scorer functions, using built-in scorers (Guidelines, Correctness, Safety, RetrievalGroundedness), building eval datasets from traces, setting up trace ingestion and production monitoring, aligning judges with MemAlign from domain expert feedback, or running optimize_prompts() with GEPA for automated prompt improvement.
Train ML models on Databricks. Use for: classification/regression/deep-learning (XGBoost, scikit-learn, LightGBM, PyTorch) with Optuna, @prod/@challenger aliases, batch scoring (spark_udf for plain models, fe.score_batch for feature-store-backed), custom PyFunc, custom ResponsesAgent (LangGraph + UC Function/Vector Search); UC feature tables + FeatureLookup + point-in-time joins + Lakebase online store; declarative Feature Views (create_feature, DeltaTableSource, RollingWindow/SlidingWindow/TumblingWindow, materialize_features, streaming Kafka features). NOT for: endpoint ops (databricks-model-serving), MLflow evaluation (databricks-mlflow-evaluation).
Bounded, evidence-driven Loop Engineering for Codex and Claude Code. Use to design, run, resume, or audit a coding loop that requires repeated implementation and verification, multi-agent routing, checkpoint recovery, measurable improvement, deterministic budgets, or explicit stop conditions.
Calculate MFU (Machine FLOP Utilization) for operators like matmul/GEMM/FlashAttention on Ascend NPU, providing clear formulas and derivation process Use this skill when the user wants to: (1) calculate MFU for matrix operations, (2) analyze operator performance efficiency, (3) understand hardware utilization, (4) optimize operator implementation Trigger: user mentions "MFU", "machine flop utilization", "operator FLOPs", "matmul performance", "GEMM efficiency", "Ascend MFU", "算子MFU", "算力利用率", "矩阵乘效率", "GEMM性能", "FlashAttention性能"
Load for any work involving Baseten - deploying/operating models on Dedicated Inference (Truss, custom Docker servers, TRT-LLM engines, Chains), calling hosted Model APIs, running Training jobs (SFT/RL/LoRA), or Model Frontier Gateway.
Inspect multiple reference or benchmark videos shot by shot, record observable visual and audio evidence independently for each source, then synthesize their recurring short-form style grammar, one-off details, imitation boundaries, and generator risks in one human-readable Markdown report. Use before image prompt construction, video request architecture, Seedance workflow creation, or batch media generation when reference footage defines the desired production language.