Hf Space Recovery Agent Skill

Diagnose and recover failing or stuck Hugging Face Space deployments for OpenEnv environments. Use when deploying envs from `envs/` to the Hub (`openenv` namespace with version suffixes), when Spaces are in `BUILDING`/`APP_STARTING`/`RUNTIME_ERROR`, or when release collections need to be reconciled after targeted redeploys.

2k tokens

context cost

the whole folder, loaded on every use

files

instructions only

copies elsewhere

how many repositories repackaged it

2474

stars on the repo

on the repository, not the skill itself

Install

one command, takes just this skill from the repository

npx skills add https://github.com/huggingface/OpenEnv --skill hf-space-recovery

What comes with it

2 870 bytes besides the instruction

references/troubleshooting.md

The instruction itself

9 sections, as written by the author

HF Space Recovery

Use this skill to recover OpenEnv Hub deployments quickly with minimal blast radius.

Execute This Workflow

1) Confirm release tuple

Use a single release tuple across all commands:

Namespace: openenv
Version: vX.Y.Z
Space suffix: -vX-Y-Z

Default to a version suffix and treat unsuffixed Spaces as legacy.

2) Snapshot runtime status

Collect all versioned spaces and isolate non-running ones:

hf spaces ls --author openenv --limit 500 --expand=runtime \
  | jq -r '.[] | select(.id|test("-v[0-9]+-[0-9]+-[0-9]+$")) \
    | [.id, .runtime.stage, (.runtime.raw.errorMessage // "")] | @tsv' \
  | sort

Treat RUNNING and SLEEPING as healthy. Triage everything else.

3) Classify and extract signal

RUNTIME_ERROR: read traceback from .runtime.raw.errorMessage.
BUILD_ERROR: read build error text from runtime info, then patch Dockerfile/deps.
APP_STARTING longer than 10 minutes: inspect event stream and metrics before changing code.

hf spaces info openenv/<space-id> --expand=runtime
curl -sS -m 10 https://huggingface.co/api/spaces/openenv/<space-id>/events | sed -n '1,140p'
curl -sS -m 10 -i https://huggingface.co/api/spaces/openenv/<space-id>/metrics | sed -n '1,120p'

Read references/troubleshooting.md for symptom-to-fix mappings.

4) Apply minimal fix and targeted redeploy

Prefer targeted redeploys over full-fleet pushes:

scripts/prepare_hf_deployment.sh \
  --hf-namespace openenv \
  --env <env_name> \
  --skip-collection

Use openenv CLI as a supplement, not a replacement, for release triage:

Validate env layout quickly (uv run openenv validate ...) when applicable.
Keep release deploys on scripts/prepare_hf_deployment.sh to preserve suffix/pinning behavior.

5) Unstick runtime when code is already good

If Space remains in APP_STARTING with no actionable error:

uv run --with huggingface_hub python - <<'PY'
from huggingface_hub import HfApi
api = HfApi()
api.restart_space("openenv/<space-id>", factory_reboot=True)
PY

If still stuck, force recreation as last resort:

hf repo delete openenv/<space-id> --repo-type space
scripts/prepare_hf_deployment.sh --hf-namespace openenv --env <env_name> --skip-collection

6) Verify and close

Verify both runtime stage and health endpoint:

hf spaces info openenv/<space-id> --expand=runtime
curl -sS -m 10 https://<space-subdomain>.hf.space/health

Then verify fleet-wide:

hf spaces ls --author openenv --limit 500 --expand=runtime \
  | jq -r '.[] | select(.id|test("-v[0-9]+-[0-9]+-[0-9]+$")) \
    | select(.runtime.stage!="RUNNING" and .runtime.stage!="SLEEPING") \
    | [.id, .runtime.stage] | @tsv' | sort

7) Reconcile collection

When targeted deploys are done, update collection membership for the same version:

python3 scripts/manage_hf_collection.py \
  --version vX.Y.Z \
  --collection-namespace openenv \
  --space-id openenv/<space-id>

Add one --space-id per redeployed space.

Other skills for the same job

different authors, same section of the catalogue

Azure Kubernetes Automatic Readiness

by microsoft

vendor ×3

Assess Kubernetes workloads and cluster configuration for AKS Automatic compatibility. Identifies incompatibilities, generates fixes, and guides migration from AKS Standard to AKS Automatic. WHEN: migrate to AKS Automatic, check AKS Automatic readiness, validate manifests for Automatic, assess cluster for Automatic compatibility, fix deployment for Automatic compatibility, identify AKS Automatic migration blockers, is my cluster ready for AKS Automatic.

Discovers available Azure OpenAI model capacity across regions and projects. Analyzes quota limits, compares availability, and recommends optimal deployment locations based on capacity requirements. USE FOR: find capacity, check quota, where can I deploy, capacity discovery, best region for capacity, multi-project capacity search, quota analysis, model availability, region comparison, check TPM availability. DO NOT USE FOR: actual deployment (hand off to preset or customize after discovery), quota increase requests (direct user to Azure Portal), listing existing deployments.

Interactive guided deployment flow for Azure OpenAI models with full customization control. Step-by-step selection of model version, SKU (GlobalStandard/Standard/ProvisionedManaged), capacity, RAI policy (content filter), and advanced options (dynamic quota, priority processing, spillover). USE FOR: custom deployment, customize model deployment, choose version, select SKU, set capacity, configure content filter, RAI policy, deployment options, detailed deployment, advanced deployment, PTU deployment, provisioned throughput. DO NOT USE FOR: quick deployment to optimal region (use preset).

Unified Azure OpenAI model deployment skill with intelligent intent-based routing. Handles quick preset deployments, fully customized deployments (version/SKU/capacity/RAI policy), and capacity discovery across regions and projects. USE FOR: deploy model, deploy gpt, create deployment, model deployment, deploy openai model, set up model, provision model, find capacity, check model availability, where can I deploy, best region for model, capacity analysis. DO NOT USE FOR: listing existing deployments (use foundry_models_deployments_list MCP tool), deleting deployments, agent creation (use agent/create), project creation (use project/create).

Intelligently deploys Azure OpenAI models to optimal regions by analyzing capacity across all available regions. Automatically checks current region first and shows alternatives if needed. USE FOR: quick deployment, optimal region, best region, automatic region selection, fast setup, multi-region capacity check, high availability deployment, deploy to best location. DO NOT USE FOR: custom SKU selection (use customize), specific version selection (use customize), custom capacity configuration (use customize), PTU deployments (use customize).

This skill should be used when working with LaminDB, an open-source data framework for biology that makes data queryable, traceable, reproducible, and FAIR. Use when managing biological datasets (scRNA-seq, spatial, flow cytometry, etc.), tracking computational workflows, curating and validating data with biological ontologies, building data lakehouses, or ensuring data lineage and reproducibility in biological research. Covers data management, annotation, ontologies (genes, cell types, diseases, tissues), schema validation, integrations with workflow managers (Nextflow, Snakemake) and MLOps platforms (W&B, MLflow), and deployment strategies.

Latch platform for bioinformatics workflows. Build pipelines with Latch SDK, @workflow/@task decorators, deploy serverless workflows, LatchFile/LatchDir, Nextflow/Snakemake integration.

Run Python code in the cloud with serverless containers, GPUs, and autoscaling. Use when deploying ML models, running batch processing jobs, scheduling compute-intensive tasks, or serving APIs that require GPU acceleration or dynamic scaling.

17k tokens

How to use it

Copy the folder

Take huggingface/hf-space-recovery from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.