Using Skills

Skills are reusable knowledge packages that provide domain expertise, procedures, and reference material to agents. Unlike commands (which you invoke), skills are loaded automatically based on context.

Core Skills vs Reference Docs

The ADLC framework contains 35 Core Skills and 176 supporting reference documents:

• 35 Core Skills (files named SKILL.md): Active skills with trigger patterns in frontmatter. Loaded on-demand when you invoke matching commands or describe matching scenarios. These consume context only when activated.
• 176 Reference Docs: Supporting documentation bundled within skill directories (sub-patterns, validation protocols, examples). NOT loaded into context unless the parent skill activates them.

The landing page and CLAUDE.md show "35 Skills" — these are the active, trigger-matched capabilities. The reference docs provide depth when a skill is invoked.

How Skills Load

User types "CDK test" in chat
       |
MANIFEST.json matches trigger pattern "CDK"
       |
Loads: cdk-patterns skill + testing-orchestration-reference skill
       |
Agent receives domain knowledge for CDK testing

Skills load via three mechanisms:

Mechanism	Example	When
Trigger patterns	User says "Terraform" → loads terraform-patterns	Automatic
Agent reference	qa-engineer references testing-skill-framework	Agent invocation
Explicit @import	@.claude/skills/testing/autonomous-testing.md	Manual

Core Skills (20)

Always available across all projects.

Testing (6 skills)

Skill	Purpose
testing-skill-framework	Master testing methodology
testing-orchestration-reference	3-tier test orchestration
autonomous-testing	Self-directed test execution
visual-verification	Screenshot-based validation
docusaurus-testing	Documentation site testing
cross-validation-docs	Docs vs source accuracy

Development (6 skills)

Skill	Purpose
cdk-patterns	CDK construct patterns
terraform-patterns	Terraform module patterns
git-commit-helper	Commit message standards
skill-creator	Create new skills
mcp-builder	Build MCP integrations
artifacts-builder	Build deployable artifacts

Dashboards (5 skills)

Skill	Purpose
webapp-testing	Web app validation
dashboard-testing	Dashboard data validation
cross-validation-mcp-api	MCP vs API accuracy
marketplace-testing	Component catalog testing
design-token-validation	Design token consistency

Other (3 skills)

Skill	Purpose
invest-quality-gates	User story quality scoring
reflective-learning	Kolb Cycle + session reflection
operational-excellence	PDCA enforcement

Marketplace Skills (75)

Opt-in per-project. Browse at Component Marketplace.

Key categories:

• Product Management (65 skills) — PRDs, OKRs, personas, roadmaps, GTM
• Security (4 skills) — threat modeling, compliance
• Document Processing (3 skills) — PDF extraction, analysis
• Governance (1 skill) — regulatory compliance

Enable Marketplace Skills

// settings.local.json
{
  "skills": {
    "marketplace": ["product-management/*", "security/*"]
  }
}

Skill Anatomy

Every skill follows a 13-field frontmatter standard:

---
name: skill-name
description: "What this skill provides"
agent: [agent-that-uses-it]
context: fork          # isolated context
model: sonnet          # or opus
allowed-tools: [Read, Bash, Grep, Glob]
license: Apache-2.0
metadata:
  version: 1.0.0
  adlc_version: 3.7.1
visibility: public
track: public          # public | startup | enterprise
industries: []         # FSI, Energy, Telecom, Aviation
disclosure-level: full # full | partial | minimal
compatibility: "Claude Code 1.0+, ADLC 3.2+"
---

Which Skill Do I Need?

I need to...	Use this skill	Category	Trigger
Estimate infrastructure costs before deployment	finops/cost-optimization-patterns	FinOps	/finops:analyze, /terraform:cost
Build and test CDK stacks	cdk/cdk-patterns	CDK	/cdk:test, /cdk:synth
Debug CDK deployment errors	cdk/debugging-cdk-errors	CDK	CDK error messages
Test CDK infrastructure (3-tier)	cdk/testing-cdk-infrastructure	CDK	/cdk:test
Build Terraform modules	terraform skills	Terraform	/terraform:test, /terraform:synth
Run Playwright E2E tests	development/webapp-testing	Testing	/documentation:validate, E2E testing
Generate executive FinOps reports	reporting/executive-reporting	Reporting	/finops:report, persona reports
Cross-validate MCP vs native API	validation/mcp-cross-validation	Validation	MCP accuracy validation
Validate inventory across sources	validation/inventory-cross-validation	Validation	/inventory:lz-cross-validate
Set up Docker Compose environments	development/local-first-docker	Development	Docker, devcontainer setup
Create MCP server integrations	development/mcp-builder	Development	MCP server creation
Generate commit messages from diffs	development/git-commit-helper	Development	git commit preparation
Implement pytest enterprise patterns	pytest-enterprise	Testing	pytest, moto, fixtures
Run battle tests (L1-L4)	testing/battle-test	Testing	Pre-release validation
Validate CI workflows locally	testing/ci-local-validation	Testing	GitHub Actions validation
Create dashboard visualizations	dashboards/vizro-mcp-integration	Dashboards	/dashboards:generate
Test dashboard accuracy	dashboards/dashboard-testing	Dashboards	/dashboards:validate
Handle AWS Health events	aws/aws-health-event-triage	AWS	AWS Health notifications
Score EC2 for decommission	aws/ec2-scream-test	AWS	EC2 scream test scoring
Use AWS SDK patterns correctly	aws-boto3-patterns	AWS	boto3, multi-account ops
Manage FinOps parameters	finops/parameter-injection	FinOps	FinOps parameter parsing
Implement incremental collection	finops/incremental-collection	FinOps	Delta data collection
Apply industry compliance profiles	governance/industry-profiles	Governance	FSI, Energy, Telecom, Aviation
Sync CLI docs from registry	documentation/cli-docs-sync	Documentation	/documentation:sync-cli
Configure devcontainer profiles	development/devcontainer-profiles	Development	.devcontainer/ setup
Create skills and agents	development/skill-creator	Development	New component creation
Build HTML artifacts	development/artifacts-builder	Development	React/Tailwind artifacts
Orchestrate F2T2EA cycles	xops/f2t2ea-cycle-orchestrator	xOps	/xops:f2t2ea-cycle
Implement K3D clusters	k3d skills	Kubernetes	K3D cluster setup
Run ceremonies (standup/retro)	ceremonies skills	Ceremonies	/metrics:daily-standup
Manage sprint configuration	config skills	Config	Sprint settings
Optimize testing costs	testing/testing-cost-optimizer	Testing	Test infrastructure costs
Set up observability	observability skills	Observability	MELT telemetry, SLOs
Implement Azure patterns	azure skills	Azure	Azure operations
Manage security posture	security skills	Security	Security scanning, compliance

Tips

• Skills load in a forked context — they don't bloat the main conversation
• Use /speckit.improve to audit which skills consume the most tokens
• The reflective-learning skill is mandatory for retrospectives
• PM skills require explicit opt-in (65 skills = significant token budget)