技能目录

为 AI Agent 发现可复用技能。

按任务搜索真实的 GitHub 技能,并在使用前查看 Stars、信任、审计、分类和安装路径。

每个推荐都保留与其仓库、审计和安装路径的明确关联。

搜索结果: observation

英文目录

An orchestration platform for the development, production, and observation of data assets.

16K
Stars
87/100
信任
分类: automation审计

[CVPR2023] The official repo for OC-SORT: Observation-Centric SORT on video Multi-Object Tracking. OC-SORT is simple, online and robust to occlusion/non-linear motion.

1.1K
Stars
80/100
信任
分类: robotics-iot审计

Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.

34K
Stars
77/100
信任
分类: data-analysis审计

Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g. "get my model's eval score up", "improve this agent/harness", "tune this pipeline", "beat the baseline on this benchmark", "run a search over approaches and keep the best", "do an MLE-bench / Kaggle-style optimization", or any long-horizon "make this artifact better and don't just memorize the dev set" task. Trigger it even when the user doesn't say "Arbor" or "hypothesis tree" but describes repeated experiment-and-evaluate loops, branching exploration of competing ideas, or worries about a dev/test gap. Runs Claude itself as the coordinator with subagent executors in isolated git worktrees; for the standalone `arbor` CLI tool see references/arbor-upstream.md.

34K
Stars
77/100
信任
分类: research审计

Earth Observation Data Access Gateway

422
Stars
69/100
信任
分类: geo-science审计

Open, evidence-bounded GEO and SEO agent skill hub with reusable workflows for discovery, diagnosis, content, and measurement, packaged for AI agent runtimes.

74
Stars
69/100
信任
分类: marketing-growth审计

Claude Code skill for capturing and codifying learnings before session ends / context lost

16
Stars
65/100
信任
分类: utility审计

[ACL 2026 Oral] How far can VLMs go in understanding long-horizon action progress from just a single observation? A promising early exploration

104
Stars
69/100
信任
分类: robotics-iot审计

For a detached wiki ingester only. The main agent never loads this. Defines orientation protocol, page format, role guardrail, validator contract, manifest protocol, and deterministic completion contract. Loaded by the provider-aware runtime worker.

101
Stars
63/100
信任
分类: automation审计

Deep research and analysis workflow for codebases, technologies, domains, ideas, or data. Produces structured documentation with analytical frameworks, confidence-graded findings, and cited sources. Use when evaluating technologies, investigating domains, assessing feasibility, or analyzing codebases in depth.

88
Stars
61/100
信任
分类: research审计

Place a one-off welcome and onboarding call to a customer who just signed up, capture a structured result such as business type, goal, pain points, sentiment, and activation status, then write that result back to a CRM and queue a human follow-up task when the customer asks for one.

63
Stars
61/100
信任
分类: business审计