MCP servers and skills: search, filter by where they run, and compare.
Build and run evaluators for AI/LLM applications using Phoenix.
OfficialSkillApache-2.0★ 40k in collectionNo key
Local runs on your computer · Local + Cloud also runs on Conduit’s servers · Hosted is run by its author, you connect by URL
Use when converting an existing benchmark, rubric, verifier, task YAML/JSON, or domain check into SkillEvaluator BYOG/BYOT custom evaluation.
in the skill textwants to: - bring an existing benchmark into SkillEvaluator - turn a rubric into `evals/grader.py` or `evals/grader.sh` - add custom metrics beside the default evaluator metrics - convert task files
OfficialSkillApache-2.0★ 564 in collectionNo key
Debug LLM applications using the Phoenix CLI. Fetch traces, analyze errors, structure trace review with open coding and axial coding, inspect datasets, review experiments, query annotation configs, an
in the skill textwhat to do after instrumenting an app, building failure taxonomies, choosing what evals to write, or asking "what's going wrong", "what kinds of mistakes
OfficialSkillApache-2.0★ 40k in collectionNo key
Improve AI application with evaluation-driven development. Define eval criteria, instrument the application, build golden datasets, observe and evaluate application runs, analyze results, and produce
in the skill textSKILL when the user asks to set up QA, add tests, add evals, evaluate, benchmark, fix wrong behaviors, improve quality, or do quality assurance for any
OfficialSkillMIT★ 40k in collectionNo key
Skills, MCP servers, Custom Agents, Agents.md for SDKs to ground Coding Agents
in the skill textAgent Skills  from remote stores. Do NOT use for fetching data with existing sources, model i
in the skill textprivate) - Python 3.10+ ## Workspace Use the directory containing `pyproject.toml`. For Harbor evals, write to `/workspace/output/` preserving paths. Never read `evals/targets/`. ## Instructions > **Python Environment:** Always use
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Creates, edits and benchmarks Agent Skills, with evals and description tuning for better triggering.
OfficialSkillApache-2.0No key
INVOKE THIS SKILL when building, testing, or deploying Managed Deep Agents in LangSmith. Walks a user through their first agent end to end — interviewing them about what they want to build, mapping it
in the skill textskills, memory, identity, tools, MCP servers, connections, middleware, sandboxes, schedules, channels, and evals; the mda CLI; GitHub deployments; and Context Hub. # Managed Deep Agents ## Overview Managed
OfficialSkillMIT★ 1.3k in collectionNo key
Campaign mode prunes one subsystem's whole test surface in one PR: one core area such as packages/eve/src/execution , one tier slice such as the dev server scenario suites, or one package such as pack
in the skill textcases at shared core boundaries, its scenario suites, and its `e2e/` fixture evals. Done when every test file and e2e eval the subsystem owns belongs
OfficialInstructionsApache-2.0★ 5.6k in collectionNo key
Create Earth2Studio prognostic (time-stepping forecast) model wrappers. Do NOT use for diagnostic models, data sources, or installation.
in the skill textrepo` | Full checkout at `/workspace/repo` | | Local clone | Directory with `pyproject.toml` | **Never read `evals/targets/`** — grader references only. ### Reference Files Load on demand during the matching step: | File
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Use this skill when the user wants to deploy, run, debug, tear down, or call the REST API of the RTVI-CV 2D detection / tracking microservice. Trigger when the user says things like 'deploy rtvi-cv',
in the skill textscript by name. ## Examples Worked end-to-end examples are kept under `evals/` (each `*.json` manifest contains a runnable scenario) and inline in the per-workflow
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Filesystem RAG benchmarks: corpus/, train.json, evaluate_rag.py (RAGAS quality). Not for prod monitoring, latency/throughput benchmarking (use rag-perf), or evals outside this repo layout.
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Use to deploy the vss-behavior-analytics service standalone (entrypoint, config-source, optional calibration). Not for the full warehouse deploy.
in the skill textlives in `references/`. ## Examples Worked end-to-end examples are kept under `evals/` (each `*.json` manifest contains a runnable scenario). Run a Tier-3 evaluation
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Use to deploy the vss-video-analytics-api REST service standalone (config-source, data-log bind, Elasticsearch, optional Kafka). Not for full warehouse deploy.
in the skill textlives in `references/`. ## Examples Worked end-to-end examples are kept under `evals/` (each `*.json` manifest contains a runnable scenario). Run a Tier-3 evaluation
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Use this skill when reading video-analytics metrics, incidents, alerts, and sensor data via the VA-MCP server (port 9901). Not for live VLM or incident-range narrative reports.
in the skill texttop-to-bottom. ## Examples Worked end-to-end examples are kept under `evals/` (each `*.json` manifest contains a runnable scenario) and inline in the per-workflow
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Use this skill when deploying standalone RT-VLM dense captioning or calling its REST API (uploads, captions, streams, chat-completions, Kafka). Not for VSS profile deploy or video-search ingestion.
in the skill textconcrete helper. ## Examples Worked end-to-end examples are kept under `evals/` (each `*.json` manifest contains a runnable scenario) and inline in the per-workflow `curl
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Use to run AutoMagicCalib on local MP4s, RTSP, or the bundled sample dataset, and to deploy vss-auto-calibration when needed. Do not use for non-AMC calibration or runtime analytics.
in the skill textselected input mode. ## Examples Worked end-to-end examples are kept under `evals/` (each `*.json` manifest contains a runnable scenario) and inline in the per-workflow
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Stage 3 of Clinical ASR Flywheel. Score a NeMo manifest, produce the five-section KER leaderboard (by-ipa_source diagnostic). Not for ASR auth (/riva-asr).
in the skill textCritical Workflow Rules section below before answering.** This SKILL.md is self-contained — `evals/`, `references/`, and `assets/` are pointers, not load-bearing. Answer methodology questions from this
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Use this skill to run top-level VSS fusion search on archived video, or to ingest video files / RTSP streams for search. Do NOT use for ad-hoc visual Q&A (use vss-ask-video), live captioning (use vss-
in the skill textlives in `references/`. ## Examples Worked end-to-end examples are kept under `evals/` (each `*.json` manifest contains a runnable scenario) and inline in the per-workflow
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Use to summarize a recorded video via the LVS summarization microservice (HITL-gated) with a VLM fallback. Not for report generation or live RTSP captioning.
in the skill textlives in `references/`. ## Examples Worked end-to-end examples are kept under `evals/` (each `*.json` manifest contains a runnable scenario) and inline in the per-workflow
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Use for VSS alert workflows — real-time monitoring, Alert-Bridge subscriptions, Slack notifications, incident queries, camera onboarding. Not for non-alert analytics.
in the skill textscript by name. ## Examples Runnable end-to-end scenarios live under `evals/` (each `*.json` manifest); inline `curl` blocks appear in each workflow below. Replay with
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Get RED metrics + service maps + frontend RUM + AI/LLM monitoring out of Grafana Cloud — Application Observability (`traces_spanmetrics_*` from OTel traces, p50/p95/p99 latency, exemplar-to-trace, tra
in the skill textcorrelation), and AI Observability via OpenLIT (token / cost / latency, GPU, hallucination + toxicity evals). Use when standing up APM for a service, wiring an Alloy OTLP receiver
OfficialSkillApache-2.0★ 285 in collectionNo key
Use cultivar to test your Agent Skills and Docs by running them in sandboxes, and across different agents.
OfficialSkillMIT★ 42No key
Use this skill when exposing a Docker Agent as a server (MCP, HTTP API, A2A, ACP, or OpenAI-compatible chat), distributing an agent via an OCI registry with `docker agent share`, or measuring agent qu
in the skill textexists; without it, an existing local config is left untouched. ### Evaluating agents - Evals live in an `evals/` directory next to the agent config by default; each
OfficialSkillApache-2.0★ 561 in collectionNo key
Who stands behind it
Who stands behind it
