Skills
Skills are specialized knowledge packages that give agents domain expertise. Think of the difference between tools and skills this way: tools let an agent do things (call an API, send an email), while skills teach an agent how to think about a domain (sales methodology, incident triage, cloud architecture).
How Skills Work
Skills follow the Anthropic Agent Skills specification. They are markdown-based knowledge bundles that agents load on-demand when they encounter a relevant situation.
For example, when a sales agent encounters a pricing objection, it loads the sales-objection-handling skill and gets the LAER framework, response scripts, and competitor battlecards -- all without that knowledge taking up space in every single conversation.
The Three-Level System (Progressive Disclosure)
Skills use progressive disclosure to minimize context usage:
| Level | What Loads | When | Token Cost |
|---|---|---|---|
| Level 1 | Name and short description only | Always (in system prompt) | ~100 tokens |
| Level 2 | Full instructions, frameworks, templates | When the agent activates the skill | Up to ~5,000 tokens |
| Level 3 | Detailed reference files (guides, battlecards, examples) | When the agent needs specific depth | On demand |
This means agents carry awareness of all their skills at minimal cost, and only load the heavy content when they actually need it.
Skills vs Tools
| Aspect | Tools | Skills |
|---|---|---|
| Purpose | Do things (API calls, calculations) | Know things (expertise, frameworks) |
| Output | Action results (data, side effects) | Guidance (instructions, templates) |
| Loading | Always available | Loaded on-demand (progressive disclosure) |
| Format | API integrations | Markdown + reference files |
Available Skills
MeetLoyd ships with 110+ first-party skills across these categories:
Engineering and Cloud
| Skill | Description |
|---|---|
| coding-agent | Full-stack development with sandboxed execution |
| aws-architect | AWS Solutions Architect -- Well-Architected Framework, IaC, cost optimization |
| azure-architect | Azure Solutions Architect -- Bicep, Entra ID, AKS |
| gcp-architect | GCP Solutions Architect -- Cloud Run, GKE, BigQuery, Terraform |
| multi-cloud-architect | Multi-cloud and hybrid -- Kubernetes, Terraform, vendor lock-in mitigation |
| terraform | Terraform/OpenTofu IaC, modules, state management, CI/CD |
| kubernetes | Deployments, Helm charts, RBAC, networking, troubleshooting |
| postgresql | Query optimization, indexing, replication, PL/pgSQL |
| kafka | Event streaming, Kafka Streams, Connect, Schema Registry |
Enterprise IT
| Skill | Description |
|---|---|
| servicenow | ITSM/ITOM, AI Agents, Now Assist, CMDB |
| okta | Identity, SSO/SAML, OAuth 2.0, MFA, Zero Trust |
| datadog | Observability, APM, logs, metrics, Bits AI |
| pagerduty | Incident management, SRE Agent, on-call, escalations |
| splunk | Log management, SPL queries, SIEM, threat detection |
| grafana | Dashboards, PromQL, Loki, Tempo, alerting |
| vault | HashiCorp Vault secrets management, dynamic credentials, PKI |
Sales and Marketing
| Skill | Description |
|---|---|
| sales-objection-handling | B2B SaaS objections with LAER framework, 25+ patterns |
| strategic-narrative | Andy Raskin framework, positioning, category creation |
| growth-hacking | Viral loops, experimentation, PLG, AARRR metrics |
| inbound-marketing | Content strategy, SEO, lead nurturing, automation |
| google-ads | Search, Display, Performance Max, Smart Bidding |
| linkedin-ads | ABM campaigns, Lead Gen Forms, B2B targeting |
| content-management | LinkedIn, Twitter/X, blog, content calendar |
| pr-communications | Press releases, media relations, crisis comms |
CRM and Billing
| Skill | Description |
|---|---|
| salesforce | Apex, LWC, SOQL, Einstein AI, Flow |
| hubspot | CRM/Marketing APIs, workflows, Breeze AI |
| stripe | Payments, subscriptions, Connect, Checkout |
| zuora | Subscriptions, revenue recognition (ASC 606), quote-to-cash |
SaaS Business
| Skill | Description |
|---|---|
| saas-metrics | LTV/CAC, NRR, Rule of 40, cohort analysis |
| saas-pricing | Value-based pricing, freemium, packaging |
| saas-valuation | ARR multiples, DCF, comps, fundraising benchmarks |
Web Development
| Skill | Description |
|---|---|
| laravel | Laravel PHP (11/12), Eloquent, Blade, queues, FrankenPHP |
| drupal | CMS development, modules, themes, Twig, Entity API |
| dsfr | French Government Design System (RGAA compliance) |
AI Development
| Skill | Description |
|---|---|
| openai-agents | OpenAI Agents SDK, multi-agent systems, handoffs |
| crewai | CrewAI orchestration, agent crews, task delegation |
| anthropic-mcp | MCP server development, tools, resources |
| ml-training | PyTorch, fine-tuning, hyperparameter optimization |
| llm-finetuning | LoRA, QLoRA, DPO, ORPO, evaluation strategies |
Productivity
| Skill | Description |
|---|---|
| spreadsheets | Excel and Sheets -- XLOOKUP, QUERY, pivot tables, Apps Script |
| presentations | Slides and PowerPoint -- deck design, data viz, narrative |
| jira | JQL queries, Atlassian Intelligence, Rovo AI, automation |
| indesign | Adobe InDesign -- enterprise PDFs, whitepapers, reports |
Skill Discovery
Agents can browse the skill catalog and request skills they need. Skills are also suggested automatically when integrations are connected or during team onboarding. See Skill Discovery for details.
Assigning Skills
Via the Dashboard
The easiest way to manage agent skills:
- Open Agent Settings (edit an agent)
- Scroll to the Skills section
- Click Assign Skill to browse available skills
- Click a skill to assign it
- Use the toggle to enable/disable a skill without removing it
- Click the delete icon to unassign a skill completely
The skills section shows each assigned skill with its category, description, and enabled state.
Via Loyd
Ask Loyd:
"Give the sales agent the objection-handling skill"
From the Store
- Go to Store > Skills
- Browse or search for skills
- Click Subscribe (skills are subscription-based)
- Assign to agents from the dashboard
Creating Custom Skills
Skill Structure
A custom skill follows this directory layout:
my-skill/
├── SKILL.md # Required: frontmatter + instructions
├── references/ # Optional: detailed reference docs
│ ├── GUIDE.md
│ └── EXAMPLES.md
└── assets/ # Optional: images, diagrams
SKILL.md Format
The SKILL.md file has YAML frontmatter followed by the skill content:
| Frontmatter Field | Description |
|---|---|
| name | Unique skill identifier |
| description | What the skill does (max 1024 chars) -- this is the Level 1 text |
| license | License type (e.g., MIT) |
| metadata.author | Author name |
| metadata.version | Semantic version |
| metadata.category | Category for browsing |
| metadata.tags | Keywords for search |
The body of the file contains:
- When to Use section -- tells the agent when to activate the skill (and when NOT to)
- Main Content -- instructions, frameworks, templates, decision trees
- Reference Files -- links to detailed reference documents in the
references/directory
Best Practices for Custom Skills
| Practice | Why |
|---|---|
| Clear triggers | Tell the agent exactly when to activate and when NOT to ("Activate when customer mentions pricing. Do NOT activate for general product questions.") |
| Structured content | Use tables, decision trees, and templates -- not walls of text |
| Actionable templates | Provide copy-paste response templates with placeholders |
| Reference files for depth | Keep main instructions concise, put detailed content in references |