Agent skill

Infrastructure As Code

by kid-sid in kid-sid/claude-spellbook

A skill your agent uses when writing Terraform for cloud resources, setting up remote state, structuring modules for reuse, managing multiple environments, reviewing a plan before apply, or…

MITAuto-check passedDevOps & Cloud

Install Infrastructure As Code

skills CLI
$ npx skills add kid-sid/claude-spellbook --skill infrastructure-as-code -a claude-code

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

GitHub CLI
$ gh skill install kid-sid/claude-spellbook infrastructure-as-code --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/kid-sid/claude-spellbook.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/infrastructure-as-code .claude/skills/infrastructure-as-code && 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
infrastructure-as-code
GitHub stars
189
Token cost
~3.2k tokens
SKILL.md length
598 words
Files
1
Skills in repo
54
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when writing Terraform for cloud resources, setting up remote state, structuring modules for reuse, managing multiple environments, reviewing a plan before apply, or…

  • Writing Terraform for cloud resources
  • SKILL.md covers When to Activate, Core Building Blocks, State Management and Module Structure, plus 6 more sections
  • Calls terraform; reaches github.com
  • Setting up remote state

What it does

Infrastructure As Code is an agent skill from kid-sid/claude-spellbook. Use when writing Terraform for cloud resources, setting up remote state, structuring modules for reuse, managing multiple environments, reviewing a plan before apply, or importing and resolving state drift.

Its SKILL.md is about 3.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in DevOps & Cloud, covering Infrastructure as code. It works with Terraform. The repository describes itself as: A curated collection of skills, prompts, and workflows that extend Claude's capabilities — your personal grimoire for AI-powered development. The licence is MIT.

When your agent uses it

  • Writing Terraform for cloud resources
  • Setting up remote state
  • Structuring modules for reuse
  • Managing multiple environments

Example prompts

  • “/infrastructure-as-code”

What it can do on your machine

Read from SKILL.md and the folder at commit a7c2ac9. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • terraform

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

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • github.com

    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.

Context cost

Infrastructure As Code loads about 3.2k tokens when it runs. Until then it costs about 57 tokens; SKILL.md has 598 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~57
When it runs · the whole SKILL.md, loaded when a task matches
~3.2k

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from kid-sid/claude-spellbook at commit a7c2ac9, republished under its MIT licence (© kid-sid). 598 words, ~3,187 tokens.

Download SKILL.mdSave it as .claude/skills/infrastructure-as-code/SKILL.md (or your agent's skills folder).
name
infrastructure-as-code
description
Use when writing Terraform for cloud resources, setting up remote state, structuring modules for reuse, managing multiple environments, reviewing a plan before apply, or importing and resolving state drift.

Infrastructure as Code

Terraform lets you define, provision, and version cloud infrastructure as declarative HCL code, enabling repeatable and reviewable infrastructure changes.

When to Activate

  • Writing Terraform for cloud resources (VPC, RDS, EKS, IAM, etc.)
  • Setting up a Terraform state backend
  • Creating a reusable Terraform module
  • Managing multiple environments (dev/staging/prod) with Terraform
  • Reviewing a terraform plan before applying
  • Dealing with state drift or importing existing resources

Core Building Blocks

hcl
# Provider — connects Terraform to a cloud API
terraform {
  required_version = ">= 1.7"
  required_providers {
    aws = {
      source  = "hashicorp/aws"
      version = "~> 5.0"
    }
  }
}

provider "aws" {
  region = var.aws_region
}

# Variable — parameterise configuration
variable "aws_region" {
  type        = string
  description = "AWS region to deploy into"
  default     = "us-east-1"

  validation {
    condition     = can(regex("^[a-z]{2}-[a-z]+-[0-9]$", var.aws_region))
    error_message = "Must be a valid AWS region code."
  }
}

# Local — computed values used inside the module
locals {
  name_prefix = "${var.environment}-${var.app_name}"
  common_tags = {
    Environment = var.environment
    ManagedBy   = "terraform"
    App         = var.app_name
  }
}

# Resource — a cloud resource
resource "aws_s3_bucket" "app_data" {
  bucket = "${local.name_prefix}-app-data"
  tags   = local.common_tags
}

# Data source — read existing resource without managing it
data "aws_ami" "amazon_linux" {
  most_recent = true
  owners      = ["amazon"]
  filter {
    name   = "name"
    values = ["al2023-ami-*-x86_64"]
  }
}

# Output — export values for other modules or humans
output "s3_bucket_arn" {
  value       = aws_s3_bucket.app_data.arn
  description = "ARN of the application data bucket"
}

State Management

Remote State Backend

State must be remote and locked — never store terraform.tfstate in git.

AWS (S3 + DynamoDB lock):

hcl
terraform {
  backend "s3" {
    bucket         = "my-org-terraform-state"
    key            = "services/payment-service/terraform.tfstate"
    region         = "us-east-1"
    encrypt        = true
    dynamodb_table = "terraform-locks"  # partition key: LockID (String)
  }
}

GCP (GCS):

hcl
terraform {
  backend "gcs" {
    bucket = "my-org-terraform-state"
    prefix = "services/payment-service"
  }
}
State Commands
bash
terraform state list                      # list all managed resources
terraform state show aws_s3_bucket.data   # inspect a resource's state
terraform state mv OLD_ADDR NEW_ADDR      # rename without destroying
terraform state rm aws_s3_bucket.old      # remove from state (doesn't destroy)
terraform force-unlock LOCK_ID            # release a stuck lock

State file security: The state file contains sensitive values (RDS passwords, private keys). Ensure S3 bucket has:

  • Versioning enabled (recover from bad apply)
  • Server-side encryption
  • Block public access
  • Access restricted to CI role + team IAM role only

Module Structure

modules/
└── rds-postgres/
    ├── main.tf        # resources
    ├── variables.tf   # inputs
    ├── outputs.tf     # outputs
    └── README.md      # usage docs (required for shared modules)
Module Example
hcl
# modules/rds-postgres/variables.tf
variable "instance_class" {
  type    = string
  default = "db.t3.medium"
}
variable "db_name"      { type = string }
variable "subnet_ids"   { type = list(string) }
variable "vpc_id"       { type = string }
variable "tags"         { type = map(string); default = {} }

# modules/rds-postgres/outputs.tf
output "endpoint"   { value = aws_db_instance.this.endpoint }
output "db_name"    { value = aws_db_instance.this.db_name }
output "secret_arn" { value = aws_secretsmanager_secret.db_password.arn }

# Consuming the module
module "payment_db" {
  source = "../../modules/rds-postgres"

  db_name        = "payments"
  instance_class = "db.t3.large"
  subnet_ids     = module.vpc.private_subnet_ids
  vpc_id         = module.vpc.vpc_id
  tags           = local.common_tags
}
Module Versioning
hcl
# Pin to a Git tag (preferred for shared modules)
module "rds" {
  source = "git::https://github.com/my-org/tf-modules.git//rds-postgres?ref=v2.1.0"
}

# Terraform Registry
module "vpc" {
  source  = "terraform-aws-modules/vpc/aws"
  version = "~> 5.0"
}

Environment Strategy

infra/
├── modules/
│   ├── vpc/
│   └── rds-postgres/
└── environments/
    ├── dev/
    │   ├── main.tf          # calls modules
    │   ├── terraform.tfvars # dev-specific values
    │   └── backend.tf       # dev state backend
    ├── staging/
    │   └── ...
    └── prod/
        └── ...

Pros: complete isolation, different providers per env, easy to cd into. Cons: some code duplication across environments.

Workspace (alternative)
bash
terraform workspace new dev
terraform workspace select staging
terraform workspace list

Use terraform.workspace in HCL:

hcl
locals {
  instance_type = terraform.workspace == "prod" ? "db.r6g.xlarge" : "db.t3.medium"
}

Decision: Use directory-per-environment for significant infrastructure differences between envs. Use workspaces only for identical infrastructure with minor variable differences.

tfvars per Environment
hcl
# environments/prod/terraform.tfvars
aws_region     = "us-east-1"
environment    = "prod"
instance_class = "db.r6g.xlarge"
min_capacity   = 3
max_capacity   = 20

Plan/Apply Workflow

bash
# 1. Init (first time, or after source changes)
terraform init

# 2. Format and validate
terraform fmt -recursive
terraform validate

# 3. Plan — save output for reproducible apply
terraform plan -out=tfplan -var-file=terraform.tfvars

# 4. Policy check (optional, using OPA/Conftest)
terraform show -json tfplan | conftest test -

# 5. Apply from the saved plan (no re-planning)
terraform apply tfplan

# 6. Verify
terraform state list
CI Pipeline Integration
yaml
# .github/workflows/terraform.yml
jobs:
  plan:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - uses: hashicorp/setup-terraform@v3
        with:
          terraform_version: "1.7.0"
      - uses: aws-actions/configure-aws-credentials@v4
        with:
          role-to-assume: arn:aws:iam::123456789:role/terraform-plan
          aws-region: us-east-1
      - run: terraform init
      - run: terraform plan -out=tfplan
      - run: terraform show -json tfplan > tfplan.json
      - name: Policy check
        run: conftest test tfplan.json --policy policies/
      - uses: actions/upload-artifact@v4
        with:
          name: tfplan
          path: tfplan

  apply:
    needs: plan
    if: github.ref == 'refs/heads/main'
    environment: production   # requires approval in GitHub
    steps:
      - uses: actions/download-artifact@v4
        with: { name: tfplan }
      - run: terraform apply tfplan

Common Resource Patterns

VPC Networking (AWS)
hcl
module "vpc" {
  source  = "terraform-aws-modules/vpc/aws"
  version = "~> 5.0"

  name = "${local.name_prefix}-vpc"
  cidr = "10.0.0.0/16"

  azs              = ["us-east-1a", "us-east-1b", "us-east-1c"]
  private_subnets  = ["10.0.1.0/24", "10.0.2.0/24", "10.0.3.0/24"]
  public_subnets   = ["10.0.101.0/24", "10.0.102.0/24", "10.0.103.0/24"]

  enable_nat_gateway = true
  single_nat_gateway = var.environment != "prod"  # save cost in non-prod

  tags = local.common_tags
}
IAM Role + Policy (least privilege)
hcl
resource "aws_iam_role" "app_role" {
  name = "${local.name_prefix}-app"

  assume_role_policy = jsonencode({
    Version = "2012-10-17"
    Statement = [{
      Effect    = "Allow"
      Principal = { Service = "ec2.amazonaws.com" }
      Action    = "sts:AssumeRole"
    }]
  })
  tags = local.common_tags
}

resource "aws_iam_role_policy" "app_policy" {
  name = "app-policy"
  role = aws_iam_role.app_role.id

  policy = jsonencode({
    Version = "2012-10-17"
    Statement = [
      {
        Effect   = "Allow"
        Action   = ["s3:GetObject", "s3:PutObject"]
        Resource = "${aws_s3_bucket.app_data.arn}/*"
      },
      {
        Effect   = "Allow"
        Action   = ["secretsmanager:GetSecretValue"]
        Resource = aws_secretsmanager_secret.db_password.arn
      }
    ]
  })
}
RDS Instance
hcl
resource "aws_db_instance" "postgres" {
  identifier        = "${local.name_prefix}-postgres"
  engine            = "postgres"
  engine_version    = "16.2"
  instance_class    = var.db_instance_class
  allocated_storage = 100
  storage_encrypted = true

  db_name  = var.db_name
  username = "app"
  password = random_password.db.result

  db_subnet_group_name   = aws_db_subnet_group.this.name
  vpc_security_group_ids = [aws_security_group.rds.id]

  backup_retention_period = var.environment == "prod" ? 30 : 7
  deletion_protection     = var.environment == "prod"
  skip_final_snapshot     = var.environment != "prod"

  tags = local.common_tags
}

Drift Detection and Import

Detect Drift
bash
terraform plan   # shows resources that diverged from state

Any ~ (update) or -/+ (replace) on a resource you haven't changed = drift.

Import Existing Resources
bash
# Import by resource address and cloud ID
terraform import aws_s3_bucket.legacy my-existing-bucket

# After import, write matching HCL or Terraform will show a diff
moved Block (safe refactoring)
hcl
# Rename a resource without destroying it
moved {
  from = aws_s3_bucket.data
  to   = aws_s3_bucket.app_data
}

See also: ci-cd, containerization, security

Red Flags

  • Storing terraform.tfstate in git — state files contain plaintext secrets (RDS passwords, private keys); use an S3+DynamoDB or GCS backend with server-side encryption from day one
  • Running terraform apply directly without a saved plan — terraform apply without -out=tfplan re-plans at apply time; what was reviewed in the PR and what actually runs can differ if state changed between plan and apply
  • Using terraform apply -auto-approve in CI on the production environment — auto-approve bypasses the human gate; production applies must require explicit approval via a GitHub environment protection rule
  • Module pinned to main or with no version constraint — source = "git::...?ref=main" means any upstream commit silently changes your infrastructure; pin to a specific git tag or Terraform registry version
  • IAM policy with "Action": "*" or "Resource": "*" — wildcard actions on all resources violates least privilege; scope to the exact actions and resource ARNs the role actually needs
  • terraform state rm used to "fix" a drift problem — removing a resource from state without destroying it creates orphaned cloud resources that accumulate cost and may introduce security gaps; use moved blocks or terraform import instead
  • Deleting a Terraform resource block to decommission a resource — removing the block from HCL causes terraform plan to show a destroy; validate intent with terraform plan and add lifecycle { prevent_destroy = true } on stateful resources
  • Sharing a single state file across all environments — one bad apply in staging can corrupt or lock the production state; each environment must have its own state file with its own backend key
Show full SKILL.md (119 more words)Show less

Checklist

  • Remote state backend configured (S3+DynamoDB or GCS) — state never committed to git
  • State S3 bucket has versioning, encryption, and public access blocked
  • All resources tagged with environment, app, and managed_by = "terraform"
  • Infrastructure split into reusable modules with variables.tf and outputs.tf
  • Modules pinned to specific versions (git tag or registry version constraint)
  • terraform plan -out=tfplan used — apply from saved plan, not a re-plan
  • Policy checks (OPA/Conftest) run on plan JSON before apply
  • Production apply requires human approval (GitHub environment protection)
  • IAM roles follow least privilege — no "*" actions or resources in policy
  • Deletion protection enabled on RDS and other stateful prod resources
  • moved blocks used for resource renames — never destroy-and-recreate
  • terraform plan run after every manual change to detect drift

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

Files

Just SKILL.md in skills/infrastructure-as-code of kid-sid/claude-spellbook.

Open the folder on GitHubat commit a7c2ac9

Compare with similar skills

Infrastructure As Code 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.

Infrastructure As Code compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Infrastructure As Code this skillkid-sid/claude-spellbook189—~3.2kAutomated safety check: PassMIT
Terraform and OpenTofu Guideagentscope-ai/QwenPaw35k6 repos~4.2kAutomated safety check: PassApache-2.0
Terraform Skillantonbabenko/terraform-skill2.4k1 repos~5.1kAutomated safety check: PassApache-2.0
Senior DevOps Toolkitmaslennikov-ig/claude-code-orchestrator-kit2596 repos~1.1kAutomated safety check: NotesCustom licence
Cloudflarehodgef/apiker1277 repos~2.2kAutomated safety check: PassMIT
Terravision Cloud Diagramspatrickchugh/terravision1.6k—~5.6kAutomated safety check: NotesAGPL-3.0-only

Similar skills

  • Terraform and OpenTofu Guide

    agentscope-ai/QwenPaw

    Guidance for writing and testing Terraform and OpenTofu code: module structure, naming, test approaches, CI/CD workflows, state handling and security scanning.

    35k GitHub starsUsed in 6 repos~4.2k tokens
    DevOps & CloudAuto-check passed
  • Terraform Skill

    antonbabenko/terraform-skill

    A skill your agent uses when writing, reviewing, or debugging Terraform/OpenTofu modules, tests, CI, scans, or state ops - diagnoses failure mode (identity churn, secrets, blast radius, CI drift…

    2.4k GitHub starsUsed in 1 repo~5.1k tokens
    DevOps & CloudAuto-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…

    259 GitHub starsUsed in 6 repos~1.1k tokens
    DevOps & CloudAuto-check: notes
  • Cloudflare

    hodgef/apiker

    Comprehensive Cloudflare platform skill covering Workers, Pages, storage (KV, D1, R2), AI (Workers AI, Vectorize, Agents SDK), feature flags (Flagship), networking (Tunnel, Spectrum), security (WAF…

    127 GitHub starsUsed in 7 repos~2.2k tokens
    DevOps & CloudAuto-check passed
  • Terravision Cloud Diagrams

    patrickchugh/terravision

    Draw cloud architecture diagrams for AWS, Azure or GCP with the official provider icon sets, using TerraVision.

    1.6k GitHub stars~5.6k tokensUpdated today
    DevOps & CloudAuto-check: notes
  • Cloudflare

    dmmulroy/cloudflare-skill

    Comprehensive Cloudflare platform skill covering Workers, Pages, storage (KV, D1, R2), AI (Workers AI, Vectorize, Agents SDK), networking (Tunnel, Spectrum), security (WAF, DDoS), and…

    728 GitHub stars~1.6k tokensUpdated 8 mo ago
    DevOps & CloudAuto-check passed

More from kid-sid/claude-spellbook

All 54 skills in this repo
  • Accessibility

    kid-sid/claude-spellbook

    A skill your agent uses when building or reviewing UI components for keyboard and screen reader compatibility, adding ARIA to custom widgets, auditing a page for WCAG AA conformance, or preparing…

    189 GitHub stars~3.2k tokensUpdated 2 mo ago
    Auto-check passed
  • Agentex

    kid-sid/claude-spellbook

    A skill your agent uses when building, wiring, or debugging an Agentex agent — choosing agent type, configuring acp.py and manifest.yaml, using adk.messages or adk.state, or resolving…

    189 GitHub stars~2.2k tokensUpdated 2 mo ago
    Auto-check: notes
  • AI Engineer

    kid-sid/claude-spellbook

    A skill your agent uses when building production LLM applications — designing RAG pipelines, choosing vector databases, implementing agent orchestration, optimizing cost, or adding AI safety…

    189 GitHub stars~3.7k tokensUpdated 2 mo ago
    Auto-check passed
  • Angular

    kid-sid/claude-spellbook

    A skill your agent uses when building or refactoring Angular applications — choosing between signals, RxJS, and NgRx for state, configuring routing with guards and lazy loading, optimizing change…

    189 GitHub stars~5k tokensUpdated 2 mo ago
    Auto-check passed
  • API Design

    kid-sid/claude-spellbook

    A skill your agent uses when designing new REST endpoints, reviewing an existing API contract, adding pagination or filtering, planning a versioning strategy, or building a public or partner-facing…

    189 GitHub stars~3.6k tokensUpdated 2 mo ago
    Auto-check passed
  • Auth

    kid-sid/claude-spellbook

    A skill your agent uses when implementing login flows, issuing or validating JWTs, setting up OAuth2/OIDC with a provider, designing role-based or attribute-based access control, securing API…

    189 GitHub stars~3.2k tokensUpdated 2 mo ago
    Auto-check passed

Works with

Categories

Questions about Infrastructure As Code

What does Infrastructure As Code do?

A skill your agent uses when writing Terraform for cloud resources, setting up remote state, structuring modules for reuse, managing multiple environments, reviewing a plan before apply, or…. Infrastructure As Code is an agent skill from kid-sid/claude-spellbook. Use when writing Terraform for cloud resources, setting up remote state, structuring modules for reuse, managing multiple environments, reviewing a plan before apply, or importing and resolving state drift.

When should I use Infrastructure As Code?

Infrastructure As Code fits situations like: writing Terraform for cloud resources; setting up remote state; structuring modules for reuse; managing multiple environments.

How do I install Infrastructure As Code in Claude Code?

Run `npx skills add kid-sid/claude-spellbook --skill infrastructure-as-code -a claude-code`. Or copy the skill folder (skills/infrastructure-as-code in kid-sid/claude-spellbook) into .claude/skills/infrastructure-as-code in your project. Claude Code loads it when a task matches its description.

How do I install Infrastructure As Code in Codex?

Run `npx skills add kid-sid/claude-spellbook --skill infrastructure-as-code -a codex`. Or copy the skill folder (skills/infrastructure-as-code in kid-sid/claude-spellbook) into .agents/skills/infrastructure-as-code in your project. Codex loads it when a task matches its description.

Can I use Infrastructure As Code 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 kid-sid/claude-spellbook --skill infrastructure-as-code -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/infrastructure-as-code, .gemini/skills/infrastructure-as-code, .github/skills/infrastructure-as-code and .opencode/skills/infrastructure-as-code in your project.

What does Infrastructure As Code need to run?

Going by SKILL.md and its folder, Infrastructure As Code needs the command-line tools its instructions call (terraform).

Does Infrastructure As Code access the network?

SKILL.md names 1 domain. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Infrastructure As Code 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. Review the folder before installing.

What licence does Infrastructure As Code use?

Infrastructure As Code is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Infrastructure As Code use?

About 3.2k tokens (SKILL.md is roughly 13k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Infrastructure As Code?

Skills that share tags, products or a category with Infrastructure As Code: Terraform and OpenTofu Guide (agentscope-ai/QwenPaw, 35k stars), Terraform Skill (antonbabenko/terraform-skill, 2.4k stars), Senior DevOps Toolkit (maslennikov-ig/claude-code-orchestrator-kit, 259 stars) and Cloudflare (hodgef/apiker, 127 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Infrastructure As Code?

kid-sid (a GitHub user) maintains it in kid-sid/claude-spellbook, which has 189 GitHub stars. The repository holds 54 skills in this directory. The repository was last updated on August 5, 2026.

Source: kid-sid/claude-spellbook on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.