Agent skill

Snowflake Deploy Medic

by jeremylongshore in jeremylongshore/tons-of-skills-marketplace

Review and safely diagnose Snowflake infrastructure and database deployments across the snowflakedb/snowflake Terraform 2.x provider, grants/state/imports, schemachange versioned and repeatable…

MITAuto-check passedDatabases

Install Snowflake Deploy Medic

skills CLI
$ npx skills add jeremylongshore/tons-of-skills-marketplace --skill snowflake-deploy-medic -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install jeremylongshore/tons-of-skills-marketplace snowflake-deploy-medic --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/jeremylongshore/tons-of-skills-marketplace.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/.curated/snowflake-deploy-medic .claude/skills/snowflake-deploy-medic && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
snowflake-deploy-medic
GitHub stars
2.8k
Token cost
~3.9k tokens
SKILL.md length
1,623 words
Files
12 (incl. scripts, references)
Skills in repo
3,342
Repo updated
First seen
Licence
MIT

At a glance

Review and safely diagnose Snowflake infrastructure and database deployments across the snowflakedb/snowflake Terraform 2.x provider, grants/state/imports, schemachange versioned and repeatable…

  • Works in 6 steps: Establish current toolchain and account… → Gate Terraform state and preview → Gate schemachange integrity → …
  • With Snowflake Terraform plan
  • SKILL.md covers Overview, Hard boundaries, Prerequisites and Instructions, plus 4 more sections
  • Runs Python scripts from its folder; calls terraform and python3

What it does

Snowflake Deploy Medic is an agent skill from jeremylongshore/tons-of-skills-marketplace. Review and safely diagnose Snowflake infrastructure and database deployments across the snowflakedb/snowflake Terraform 2.x provider, grants/state/imports, schemachange versioned and repeatable migrations, Snowflake CLI/drivers, and behavior-change releases. Use before a production deploy, when a plan wants to replace or revoke grants, state is unreadable, a migration checksum drifts, or a CLI/driver upgrade changes behavior. Produces a zero-change/plan verdict, ordered remediation, and tested rollback…

Its SKILL.md is about 3.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 14 other files, including scripts and reference files (for example `eval-spec.yaml`, `references/dbt-project-and-provider-migrations.md` and `references/schemachange-integrity.md`). Compatibility notes: Model-agnostic workflow; requires Python 3.10+; optional Snowflake CLI for live read-only evidence collection

It sits in Databases, covering Data warehousing, Infrastructure as code and Deployment. It works with Snowflake, Terraform and SQL. The repository describes itself as: Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com. The licence is MIT.

When your agent uses it

  • With Snowflake Terraform plan
  • Terraform state
  • Schemachange checksum
  • Repeatable migration

Example prompts

  • “Snowflake Terraform plan”
  • “grant import”
  • “terraform state”
  • “/snowflake-deploy-medic”

Requirements

  • Python 3
  • Compatibility (from SKILL.md): Model-agnostic workflow; requires Python 3.10+; optional Snowflake CLI for live read-only evidence collection
  • Pre-approved tools (allowed-tools): Read

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Establish current toolchain and account identity
  2. Gate Terraform state and preview
  3. Gate schemachange integrity
  4. Run the deterministic evidence classifier
  5. Produce the release decision
  6. Verify post-deploy invariants

What it can do on your machine

Read from SKILL.md and the folder at commit cfae287. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 4 files in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • terraform
    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

  • Compatibility

    Model-agnostic workflow; requires Python 3.10+; optional Snowflake CLI for live read-only evidence collection

    From compatibility in the SKILL.md frontmatter.

Context cost

Snowflake Deploy Medic loads about 3.9k tokens when it runs, and up to ~8.1k if it reads all its reference files. Until then it costs about 234 tokens; SKILL.md has 1,623 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~234
When it runs · the whole SKILL.md, loaded when a task matches
~3.9k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~8.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from jeremylongshore/tons-of-skills-marketplace at commit cfae287, republished under its MIT licence (© jeremylongshore). 1,623 words, ~3,924 tokens.

Download SKILL.mdSave it as .claude/skills/snowflake-deploy-medic/SKILL.md (or your agent's skills folder). This skill also uses 11 other files; get the full folder from GitHub.
name
snowflake-deploy-medic
description
Review and safely diagnose Snowflake infrastructure and database deployments across the snowflakedb/snowflake Terraform 2.x provider, grants/state/imports, schemachange versioned and repeatable migrations, Snowflake CLI/drivers, and behavior-change releases. Use before a production deploy, when a plan wants to replace or revoke grants, state is unreadable, a migration checksum drifts, or a CLI/driver upgrade changes behavior. Produces a zero-change/plan verdict, ordered remediation, and tested rollback requirements. It never applies, destroys, deploys, runs mutating SQL, or edits state/history automatically. Trigger with "Snowflake Terraform plan", "grant import", "terraform state", "schemachange checksum", "repeatable migration", "Snowflake CLI upgrade", "driver BCR", or "rollback Snowflake deploy". Use when a production change needs a current plan, migration-integrity, toolchain, or rollback gate.
allowed-tools
Read
compatibility
Model-agnostic workflow; requires Python 3.10+; optional Snowflake CLI for live read-only evidence collection
argument-hint
[redacted-deploy-evidence.json]
version
3.16.0
author
Jeremy Longshore <jeremy@intentsolutions.io>
license
MIT
tags
saas, snowflake, terraform, schemachange, deploy, migrations, bcr

Snowflake Deploy Medic

Overview

Snowflake deployment failures hide in the seams: a grant resource is declared as new although the remote grant already exists; provider state is truncated; a versioned migration was edited after application; a repeatable checksum change reruns unexpectedly; or a current CLI/driver behavior change is mistaken for a database defect. This skill creates one evidence-backed gate across those seams.

The deterministic classifier is scripts/analyze_deploy_evidence.py. It accepts a bounded schema-v2 projection plus its digest from an independent CI or artifact channel. It emits privacy-safe findings, a point-in-time zero-change status, ordered read-only checks, and post-deploy invariants. Nested receipt hashes detect internal inconsistency; they never substitute for trusted origin. Read references/terraform-provider-2x.md, references/schemachange-integrity.md, and references/zero-change-rollback.md for the relevant surface. Always verify current primary docs and release notes; the versions in a local receipt are observations, not timeless recommendations.

Hard boundaries

  • Never run terraform apply, terraform destroy, state editing, schemachange deploy, mutating snow sql, or Snowflake DDL/DML automatically.
  • Never hand-edit terraform.tfstate or CHANGE_HISTORY to make a plan green.
  • Never treat a valid plan with changes as a zero-change adoption; inspect every grant, ownership, replacement, destroy, and preview feature.
  • Never edit an applied versioned migration in place. A checksum mismatch is a release-blocking integrity signal; choose a new version, restore the exact applied content, or explicitly review a compensating path.
  • Never treat a repeatable checksum change as either an error or a free rerun: verify idempotence, intended scope, and current schemachange behavior.
  • Never freeze provider, CLI, driver, or BCR guidance to a version copied from this skill. Record current versions and check live release notes for the target account release window.
  • Redact backend credentials, tokens, private keys, passphrases, passwords, sensitive plan values, customer data, and presigned URLs from receipts.
  • Never execute Terraform, Snowflake, schemachange, a network client, or a shell from the classifier. It is a pure JSON reader and report writer.
  • Never treat a generic query-history receipt as deployment proof. It cannot establish a complete plan, state, migration, BCR, or affected-object denominator.

Prerequisites

Collect a timestamped receipt from the exact account, role, backend, and CI commit. Hash account, role, backend, workspace, object, address, operator, and owner identities before they enter the packet. Obtain the canonical packet SHA-256 independently from the trusted CI/artifact channel. The packet must include:

  1. A preflight record with operator, UTC timestamp, account/backend/workspace identity, state lock/backup, affected-object inventory, plan, BCR, and rollback checks. A green plan does not waive this gate.
  2. Terraform source and locked provider version, Terraform/runtime version, backend/workspace identity (without secrets), and parseable state status.
  3. Saved terraform plan -detailed-exitcode output: exit code, change count, resource actions, replacements/destroys, grant/ownership changes, and preview features.
  4. For existing grants/objects, the intended resource address, remote identity, import evidence, and post-import plan result.
  5. An itemized BCR inventory for the account release window: each ID/source, immutable source snapshot hash, externally established item count, affected surface, owner, and verified/mitigated/not-applicable disposition.
  6. An affected-object inventory reconciled to plan addresses (empty and explicitly verified for a zero-change plan), plus a verified point-in-time state backup receipt with location, capture time, and SHA-256.
  7. Schemachange version, migration commit, exact script filename/type/version, stored and current checksums, change-history status, dry-run/verify output, and out-of-order policy if relevant. Bind a nonempty repository-script denominator, a current observed projection of the relevant rows, and the append-only CHANGE_HISTORY count/hash; repeated R/A executions make those counts differ.
  8. Snowflake CLI, connector/driver, Terraform, schemachange, and runtime versions plus current release-note/BCR sources reviewed.
  9. A zero-change receipt when exit code is 0 and changes are 0, tied to the saved plan hash and verified affected-object count. Otherwise, a rollback or forward-fix test against this exact plan/migration set, including owner, preconditions, validation, and stop condition.
  10. A hash-bound provider migration-segment inventory and a verified denominator for affected dbt Project objects, including the 2026_06 live-version BCR when applicable.
  11. Exactly one account/plan-bound post-change invariant per changed plan resource; process exit status is never the verification result.

Missing evidence is an explicit finding. A successful command from a different role, account, or environment is not a deployment receipt.

Instructions

Step 1: Establish current toolchain and account identity

Record the installed versions and lockfiles. Read the live provider registry, Snowflake CLI/client-driver release notes, and current behavior-change notes for the target account release window. Do not rely on a cached blog post or a generic “latest” label. Keep auth read-only and least-privileged; use key pair/OAuth/ workload identity/external-browser mechanisms without exposing secrets.

The pack's generic query collector may support diagnosis, but it is not positive evidence for this gate. A raw query receipt, a self-asserted hash, or a receipt with truncation_possible: true cannot prove a complete affected-object or dependency inventory. Build the schema-v2 projection in trusted CI from sanitized terraform show -json, backend metadata, lock-file selection, repository migration inventory, CHANGE_HISTORY, official BCR status/items, and exact tool versions.

Step 2: Gate Terraform state and preview

Validate that state parses and belongs to the intended backend/workspace. Preserve a backend version/lock receipt before refreshing. Run only the reviewed read-only plan with detailed exit status:

  • exit 0 and changes=0: candidate zero-change receipt;
  • exit 2: valid preview with changes, requiring review;
  • any other non-zero value: plan failed, not a safe preview.

For a grant adoption, declare the intended address and use the current provider's documented import identity. Refresh and require a zero-change plan. Inspect grant scope, future grants, role/object ownership, managed access, privilege removals, and provider normalization. Never destroy a live dependency graph to avoid an import.

For provider 2.x preview resources/features, read the exact current support boundary and release notes. A green plan does not make preview behavior stable. See references/terraform-provider-2x.md. Record every migration-guide segment between the locked source and target provider versions. Each segment receipt must bind its source, versions, affected addresses, immutable source snapshot, state-move boundary, disposition, and canonical SHA-256. Segments must advance monotonically without gaps, cycles, or synthetic multi-minor leaps. Empty means explicitly verified not applicable, not “not checked.”

If dbt Project objects are in scope, inventory their deployed/staged code hashes, current and target version model, supported runtime, behavior-change disposition, and rollback artifact. The pending live-version behavior changes the rollback model; see references/dbt-project-and-provider-migrations.md.

Show full SKILL.md (612 more words)Show less
Step 3: Gate schemachange integrity

Separate migration types:

  • V...__...sql: versioned, tracked once; checksum drift blocks deployment until the applied content is reconciled.
  • R__...sql: repeatable; checksum changes intentionally cause a rerun, so prove idempotence and scope before approval.
  • A__...sql: always-run; review side effects and cost on every deploy.

Compare repository content to the actual CHANGE_HISTORY row. Check duplicate version names and branch ordering. Use current verify/dry-run behavior and review upgrade notes for checksum normalization regressions before changing the tool version. Never alter history by hand. See references/schemachange-integrity.md.

Step 4: Run the deterministic evidence classifier
bash
python3 "${CLAUDE_SKILL_DIR}/scripts/analyze_deploy_evidence.py" \
  --input ./snowflake-deploy-evidence.json \
  --as-of '<current-utc-evaluation-timestamp>' \
  --trusted-bundle-sha256 'sha256:<digest-from-trusted-ci-or-artifact-channel>'

The explicit --as-of value prevents wall-clock-dependent output. A clean verdict is PASS_AS_OF, expires at that exact timestamp, and is never permission to apply. Expected findings include:

  • TRUSTED_BUNDLE_DIGEST_MISSING_OR_MISMATCHED, EVIDENCE_CONTEXT_INVALID_OR_STALE, PLAN_RECEIPT_UNVERIFIABLE, PLAN_EXIT_ACTION_CONTRADICTION, TERRAFORM_STATE_UNREADABLE_OR_UNBOUND;
  • GRANT_IMPORT_REQUIRED, DESTRUCTIVE_PLAN_CHANGE, AFFECTED_OBJECT_DENOMINATOR_UNVERIFIED;
  • VERSIONED_CHECKSUM_DRIFT, REPEATABLE_CHANGE_DETECTED, ALWAYS_MIGRATION_UNREVIEWED, MIGRATION_DENOMINATOR_UNVERIFIED;
  • PROVIDER_PREVIEW_FEATURE, PROVIDER_PREVIEW_DENOMINATOR_UNVERIFIED, PROVIDER_MIGRATION_DENOMINATOR_UNVERIFIED, DEPLOY_TOOLCHAIN_UNVERIFIED;
  • BCR_INVENTORY_UNVERIFIED, DBT_PROJECT_DENOMINATOR_UNVERIFIED, PREFLIGHT_DENOMINATOR_UNVERIFIED, STATE_BACKUP_RECEIPT_UNVERIFIABLE;
  • ROLLBACK_RECEIPT_UNVERIFIABLE, POST_CHANGE_INVARIANTS_UNVERIFIED, ZERO_CHANGE_RECEIPT_UNVERIFIABLE.

The script is pure and connector-neutral. It reports findings from supplied evidence; it does not call Terraform, schemachange, Snowflake CLI, or Snowflake.

Step 5: Produce the release decision

Return a receipt containing scope/identity, current toolchain sources, zero-change or plan verdict, grant/import/state findings, migration checksum findings, BCR review, and rollback status. For each finding distinguish observed, derived, unknown, and hypothesis. Name the exact next read-only check and the approval boundary for any later mutation.

Step 6: Verify post-deploy invariants

After a separately approved deployment, collect fresh evidence. The preflight classifier validates only the invariant plan; it does not claim to execute or verify post-deploy checks. Reconcile the saved state/plan, grant addresses, migration history, toolchain/BCR receipt, observed invariant results, and rollback/forward-fix validation in a separate operator-reviewed receipt.

Output format

  • Identity: hashed account, role, backend/workspace, repository commit, collection timestamp, and explicit UTC observation window.
  • Toolchain: exact observed versions and links/dates for current docs/BCRs.
  • Terraform: state parseability, detailed exit code, zero-change status, grant/import/ownership/replacement risks.
  • Preflight: operator/timestamp, BCR inventory, affected objects, and state backup receipt reconciled to the same account and saved plan.
  • Migrations: V/R/A classification, checksum/history comparison, collision or out-of-order risk, and idempotence evidence.
  • Decision: BLOCKED or PASS_AS_OF; neither authorizes apply.
  • Rollback: tested strategy for this exact change set and stop condition.
  • Zero-change receipt: saved-plan hash, verified object count, issuance time, and explicit issued status when the plan is truly zero-change.
  • Invariants: checks required after the approved deployment.

Error Handling

If the JSON receipt is malformed, the classifier exits with code 2; correct the receipt instead of reading a partial verdict. If state, plan, change history, toolchain, or BCR evidence is missing, emit an explicit unknown/blocking finding. If the account, backend, role, or repository commit cannot be established, stop at identity verification. If a user asks to auto-apply, destroy, deploy, mutate SQL, or edit state/history, return the reviewed read-only checks and approval boundary instead. A successful CLI command from another environment is not proof of this deployment.

Examples

Existing grant adoption

When Terraform wants to create a grant that already exists, classify GRANT_IMPORT_REQUIRED. Declare the intended address, use the current provider's documented import identity, refresh, and require a zero-change plan. Do not hand- edit terraform.tfstate or destroy the database to force adoption.

Versioned drift plus repeatable change

When a V... checksum differs from CHANGE_HISTORY, block the release and restore the applied content or create a new migration. When an R__... checksum changes, review the intentional rerun and idempotence separately. Never update the history table by hand to silence either finding.

References

© jeremylongshore, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 11 other files (scripts, references) in skills/.curated/snowflake-deploy-medic of jeremylongshore/tons-of-skills-marketplace.

  • SKILL.md
  • eval-spec.yaml
  • references/dbt-project-and-provider-migrations.md
  • references/schemachange-integrity.md
  • references/source-notes.md
  • references/terraform-provider-2x.md
  • references/toolchain-bcr.md
  • references/zero-change-rollback.md
  • scripts/analyze_deploy_evidence.py
  • scripts/fixtures/clean-preview.json
  • scripts/fixtures/unsafe-deploy.json
  • scripts/test_analyze_deploy_evidence.py

Open the folder on GitHubat commit cfae287

Compare with similar skills

Snowflake Deploy Medic next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Snowflake Deploy Medic compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Snowflake Deploy Medic this skilljeremylongshore/tons-of-skills-marketplace2.8k—~3.9kAutomated safety check: PassMIT
Google Cloud Storage Basicsgoogle/skills21k—~2.8kAutomated safety check: PassApache-2.0
Senior DevOps Toolkitmaslennikov-ig/claude-code-orchestrator-kit2606 repos~1.1kAutomated safety check: NotesCustom licence
Spa Create Configsplunk/splunk-platform-automator138—~3.5kAutomated safety check: PassProprietary
Google Agents CLI Observabilitypifferologo/cloud-agents-cli1291 repos~2.5kAutomated safety check: PassApache-2.0
APIOps Deployment for Azure APIMthomast1906/github-copilot-agent-skills202—~3.6kAutomated safety check: PassMIT

Similar skills

  • Official

    Stores, retrieves, and manages data as objects in Cloud Storage on Google Cloud (also known colloquially as GCS) buckets.

    21k GitHub stars~2.8k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Senior DevOps Toolkit

    maslennikov-ig/claude-code-orchestrator-kit

    Comprehensive DevOps skill for CI/CD, infrastructure automation, containerization, and cloud platforms (AWS, GCP, Azure). Includes pipeline setup…

    260 GitHub starsUsed in 6 repos~1.1k tokens
    DevOps & CloudAuto-check: notes
  • Spa Create Config

    splunk/splunk-platform-automator

    A skill your agent uses when creating or updating splunkconfig.yml, designing Splunk Enterprise lab topology, multisite IDXC, SHC layout, architecture plan before config, or AWS Terraform block for…

    138 GitHub stars~3.5k tokensUpdated 5 days ago
    DevOps & CloudAuto-check passed
  • Google Agents CLI Observability

    pifferologo/cloud-agents-cli

    This skill should be used when the user wants to "set up tracing", "monitor my ADK agent", "configure logging", "add observability", "debug production traffic", or needs guidance on monitoring…

    129 GitHub starsUsed in 1 repo~2.5k tokens
    DevOps & CloudAuto-check passed
  • APIOps Deployment for Azure APIM

    thomast1906/github-copilot-agent-skills

    Supplies Bicep and Terraform templates, CI/CD pipeline patterns and phased promotion plans for deploying Azure API Management with APIOps workflows.

    202 GitHub stars~3.6k tokensUpdated 3 days ago
    DevOps & CloudAuto-check passed
  • Deploying

    GoogleCloudPlatform/race-condition

    Guides deployment of Race Condition to a GCP project. An agent skill from GoogleCloudPlatform/race-condition.

    234 GitHub stars~3k tokensUpdated 6 days ago
    DevOps & CloudAuto-check passed

More from jeremylongshore/tons-of-skills-marketplace

All 3,342 skills in this repo
  • Performing Security Code Review

    jeremylongshore/tons-of-skills-marketplace

    Execute this skill enables AI assistant to conduct a security-focused code review using the security-agent plugin.

    2.8k GitHub starsUsed in 2 repos~1.3k tokens
    Auto-check: notes
  • Adapting Transfer Learning Models

    jeremylongshore/tons-of-skills-marketplace

    Build this skill automates the adaptation of pre-trained machine learning models using transfer learning techniques.

    2.8k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Agent Context Loader

    jeremylongshore/tons-of-skills-marketplace

    Execute proactive auto-loading: automatically detects and loads agents.md files.

    2.8k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Aggregating Performance Metrics

    jeremylongshore/tons-of-skills-marketplace

    Aggregate and centralize performance metrics from applications, systems, databases, caches, and services.

    2.8k GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • Analyzing Capacity Planning

    jeremylongshore/tons-of-skills-marketplace

    Execute this skill enables AI assistant to analyze capacity requirements and plan for future growth.

    2.8k GitHub stars~947 tokensUpdated today
    Auto-check passed
  • Analyzing Database Indexes

    jeremylongshore/tons-of-skills-marketplace

    Process use when you need to work with database indexing. An agent skill from jeremylongshore/tons-of-skills-marketplace.

    2.8k GitHub stars~2k tokensUpdated today
    Auto-check passed

Questions about Snowflake Deploy Medic

What does Snowflake Deploy Medic do?

Review and safely diagnose Snowflake infrastructure and database deployments across the snowflakedb/snowflake Terraform 2.x provider, grants/state/imports, schemachange versioned and repeatable…. Snowflake Deploy Medic is an agent skill from jeremylongshore/tons-of-skills-marketplace.x provider, grants/state/imports, schemachange versioned and repeatable migrations, Snowflake CLI/drivers, and behavior-change releases.

When should I use Snowflake Deploy Medic?

Snowflake Deploy Medic fits situations like: with Snowflake Terraform plan; terraform state; schemachange checksum; repeatable migration.

How do I install Snowflake Deploy Medic in Claude Code?

Run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill snowflake-deploy-medic -a claude-code`. Or copy the skill folder (skills/.curated/snowflake-deploy-medic in jeremylongshore/tons-of-skills-marketplace) into .claude/skills/snowflake-deploy-medic in your project. Claude Code loads it when a task matches its description.

How do I install Snowflake Deploy Medic in Codex?

Run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill snowflake-deploy-medic -a codex`. Or copy the skill folder (skills/.curated/snowflake-deploy-medic in jeremylongshore/tons-of-skills-marketplace) into .agents/skills/snowflake-deploy-medic in your project. Codex loads it when a task matches its description.

Can I use Snowflake Deploy Medic in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill snowflake-deploy-medic -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/snowflake-deploy-medic, .gemini/skills/snowflake-deploy-medic, .github/skills/snowflake-deploy-medic and .opencode/skills/snowflake-deploy-medic in your project.

What does Snowflake Deploy Medic need to run?

Going by SKILL.md and its folder, Snowflake Deploy Medic needs Python for the scripts in its folder and the command-line tools its instructions call (terraform and python3). Our summary lists: Python 3. Its frontmatter pre-approves these tools: Read. Compatibility (from SKILL.md): Model-agnostic workflow; requires Python 3.10+; optional Snowflake CLI for live read-only evidence collection.

Does Snowflake Deploy Medic access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Snowflake Deploy Medic safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Snowflake Deploy Medic use?

Snowflake Deploy Medic is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Snowflake Deploy Medic use?

About 3.9k tokens (SKILL.md is roughly 16k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 4.2k tokens, read only when the agent opens those files.

What are the alternatives to Snowflake Deploy Medic?

Skills that share tags, products or a category with Snowflake Deploy Medic: Google Cloud Storage Basics (google/skills, 21k stars), Senior DevOps Toolkit (maslennikov-ig/claude-code-orchestrator-kit, 260 stars), Spa Create Config (splunk/splunk-platform-automator, 138 stars) and Google Agents CLI Observability (pifferologo/cloud-agents-cli, 129 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Snowflake Deploy Medic?

jeremylongshore (a GitHub user) maintains it in jeremylongshore/tons-of-skills-marketplace, which has 2,827 GitHub stars. The repository holds 3,342 skills in this directory. The repository was last updated on October 10, 2026.

Source: jeremylongshore/tons-of-skills-marketplace on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.