Tilt Agent Skill

Use when checking deployment health, investigating errors, reading logs, or working with Tiltfiles. Queries Tilt resource status, logs, and manages dev environments.

15k tokens

context cost

the whole folder, loaded on every use

files

instructions only

copies elsewhere

how many repositories repackaged it

404

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/aiskillstore/marketplace --skill tilt

What comes with it

54 593 bytes besides the instruction

CLI_REFERENCE.md

TILTFILE_API.md

skill-report.json

The instruction itself

9 sections, as written by the author

Tilt

First Action: Check for Errors

Before investigating issues or verifying deployments, check resource health. Run errors first, separately from pending/in-progress — otherwise real failures get buried in 20+ pending lines:

# 1. Errors only — surface the buildHistory[0].error so you see WHY, not just THAT
tilt get uiresources -o json | jq -r '.items[] | select(.status.runtimeStatus == "error" or .status.updateStatus == "error") | "\(.metadata.name): runtime=\(.status.runtimeStatus) update=\(.status.updateStatus)\n  reason: \((.status.buildHistory[0].error // "(no buildHistory error; check tilt logs)") | gsub("\n"; " ") | .[0:240])"'

# 2. In-progress and pending — informational; an in-progress build may flip to error any moment
tilt get uiresources -o json | jq -r '.items[] | select(.status.updateStatus == "in_progress" or .status.updateStatus == "pending" or .status.runtimeStatus == "pending") | "\(.metadata.name): runtime=\(.status.runtimeStatus) update=\(.status.updateStatus)"'

# 3. Docker-compose container health — MISSED by the error filter above.
#    An `Up (unhealthy)` compose container keeps runtimeStatus=ok/update=ok, so
#    queries 1-2 never flag it; the red UI badge comes from healthStatus here.
tilt get uiresources -o json | jq -r '.items[] | select(.status.composeResourceInfo.healthStatus == "unhealthy") | "\(.metadata.name): compose healthStatus=unhealthy (HEALTHCHECK failing — service may still be up)"'

# 4. Quick status overview
tilt get uiresources -o json | jq '[.items[].status.updateStatus] | group_by(.) | map({status: .[0], count: length})'

If a resource is in_progress when you check, re-poll before declaring it healthy — it can transition straight to error with a populated buildHistory[0].error. The updateStatus field reflects only the *current* build attempt; the last error always lives in buildHistory[0].error even when updateStatus is none or not_applicable.

Docker-compose resources are a blind spot. Their runtimeStatus/updateStatus reflect only build/up state, NOT the container's docker HEALTHCHECK — so a probe-failing container (docker ps → Up (unhealthy)) reads runtimeStatus=ok and slips past queries 1-2, while the Tilt UI still reddens it. The authoritative signal is .status.composeResourceInfo.healthStatus (healthy / unhealthy / absent when the service has no healthcheck), which query 3 catches. These resources also have k8sResourceInfo: null (spec.type == "docker-compose"); to find *why* a probe fails, drop to docker: docker inspect <compose-project>-<svc> --format '{{json .State.Health}}' reads the probe's last exit code + output. A common cause is the healthcheck script invoking a CLI the image doesn't ship (e.g. curl/grpcurl removed in slimmed images) — the service is fine, the probe is broken.

Non-Default Ports

When Tilt runs on a non-default port, add --port:

tilt get uiresources --port 37035
tilt logs <resource> --port 37035

Resource Status

# All resources with status
tilt get uiresources -o json | jq '.items[] | {name: .metadata.name, runtime: .status.runtimeStatus, update: .status.updateStatus}'

# Single resource detail
tilt get uiresource/<name> -o json

# Wait for ready
tilt wait --for=condition=Ready uiresource/<name> --timeout=120s

Status values:

RuntimeStatus: ok, error, pending, none, not_applicable
UpdateStatus: ok, error, pending, in_progress, none, not_applicable

Logs

tilt logs <resource>
tilt logs <resource> --since 5m
tilt logs <resource> --tail 100
tilt logs --json                    # JSON Lines output

Trigger and Lifecycle

tilt trigger <resource>             # Force update
tilt up                             # Start
tilt down                           # Stop and clean up

Running tilt up

Follow zmx skill patterns — check for existing sessions, derive name from git root, use zmx run (not attach):

PROJECT=$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" || basename "$PWD")
SESSION="${PROJECT}-tilt"

if zmx list --short 2>/dev/null | grep -q "^${SESSION}$"; then
  echo "Tilt session already exists: $SESSION"
else
  zmx run "$SESSION" 'tilt up'
  echo "Started tilt in zmx session: $SESSION"
fi

Critical: Never Restart for Code Changes

Tilt live-reloads automatically. Never suggest restarting tilt up for:

Tiltfile edits
Source code changes
Kubernetes manifest updates

Restart only for: Tilt version upgrades, port/host changes, crashes, cluster context switches.

References

TILTFILE_API.md - Tiltfile authoring
CLI_REFERENCE.md - Complete CLI with JSON patterns
https://docs.tilt.dev/

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 aiskillstore/tilt 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.