Skip to main content

​
Skills

Skills are system prompt extensions that get injected into an agent’s prompt during task execution. They teach agents specialized behaviors, guardrails, and output formats.

​
How Skills Work

When an agent has skills assigned, their content is injected as <skill> blocks in the system prompt. The agent’s LLM reads these instructions and follows them during execution. 
[SKILLS AVAILABLE]
You have access to the following skill playbooks. Activate them when the user's
request matches each skill's "When to Activate" criteria.

<skill name="Network Probe" category="DEVOPS">
  # Network Probe
  ## When to use this skill
  - Task involves ping, HTTP checks, DNS resolution...
  ## Instructions
  1. Always use -c flag with ping...
  ## Guardrails
  - Never ping more than 10 times per host...
</skill>
[END SKILLS AVAILABLE]

​
Built-in Skills

Crewship ships with five built-in skills, defined in cmd/crewship/seeddata/builtin/skills.yaml and loaded at startup by cmd/crewship/seeddata/skills.go:

Network Probe

Network diagnostics: ping, HTTP checks, DNS resolution, speed tests. Category: DEVOPS.

File Crafter

File and directory creation, CSV generation, data formatting. Category: CODING.

Web Scraper

Web content fetching, HTML/JSON parsing, API data extraction. Category: RESEARCH.

Script Runner

Python and Bash script creation, execution, and output capture. Category: CODING.

System Inspector

Container environment inspection, tool inventory, resource mapping. Category: DEVOPS.

​
Skill Structure

Every skill has three key sections:

​
When to use this skill

Describes the conditions under which the agent should apply this skill. Uses keyword matching against the task description.

​
Instructions

Step-by-step guidance for how to perform the skill. These are concrete, actionable instructions the LLM follows.

​
Guardrails

Safety constraints and limits. For example:
  • “Never ping more than 10 times per host”
  • “Only fetch from public, well-known URLs”
  • “Write only to /tmp/“

​
SKILL.md Format

Skills use a YAML frontmatter + markdown content format: 
---
name: "my-skill"
display_name: "My Custom Skill"
version: "1.0.0"
description: "What this skill does"
category: "CODING"
icon: "terminal"
---

# My Custom Skill

## When to use this skill
- Task involves...

## Instructions
1. First step...
2. Second step...

## Output Format
- Save results to...

## Guardrails
- Never do...
Import via the API endpoint POST /api/v1/workspaces/{id}/skills/import with the SKILL.md content as the body.

​
Skill Categories

CategoryDescription
CODINGCode generation, file operations, scripting
AUTOMATIONWorkflow automation
DATAData processing, analysis
DEVOPSInfrastructure, monitoring, deployment
WRITINGDrafting and editing prose
RESEARCHResearch, fact-finding
PMProduct / project management
DESIGNUX, visual, design tasks
SUPPORTCustomer support, help desk
SECURITYSecurity review, threat work
FINANCEFinance, accounting
OPSOperations, runbooks
SALESSales automation
CUSTOMUser-defined category

​
Skill Assignment

Skills are assigned to specific agents. The seed data maps agents to skills based on their role. 
Engineering crew:
  tomas (Lead):   network-probe, script-runner, file-crafter
  viktor:         script-runner, file-crafter
  nela:           file-crafter, web-scraper
  martin:         network-probe, system-inspector

Quality crew:
  eva (Lead):     script-runner, file-crafter
  daniel:         script-runner
  petra:          file-crafter, script-runner
  jakub:          system-inspector

DevOps crew:
  ondrej (Lead):  network-probe, system-inspector
  radek:          network-probe, system-inspector

Research crew:
  lucie (Lead):   web-scraper, script-runner
  filip:          web-scraper, script-runner

​
Creating Custom Skills

1

Write the SKILL.md file

Create a markdown file with YAML frontmatter defining the skill metadata and content body with activation conditions, instructions, and guardrails.
2

Import the skill

Use the API or UI to import the skill into your workspace.
3

Assign to agents

Assign the skill to the agents that should use it. An agent can have multiple skills assigned.

​
Skill Sources

SourceDescription
BUNDLEDShips with Crewship
MANAGEDCreated and maintained by workspace admins
MARKETPLACEInstalled from the skill marketplace
CUSTOMUser-created within a workspace

​
Verification Status

Marketplace skills go through a verification pipeline:
StatusMeaning
UNVERIFIEDNot yet reviewed
PENDING_REVIEWSubmitted for review
VERIFIEDApproved and safe to use
REJECTEDFailed review
DEPRECATEDNo longer maintained
Skills are injected into the system prompt, so they consume token budget. Keep skills focused and concise — a skill with 500 words of instructions is more effective than one with 2000 words of edge cases.

​
Invocation telemetry

Every time an agent actually uses one of its assigned skills, Crewship records it. This is what lets the skill-review sweep distinguish a skill that is genuinely in use from one that is just assigned and forgotten. The orchestrator watches the agent’s tool-call stream. When a tool call maps to one of the agent’s enabled skills — either a Skill tool call whose input names the skill’s slug, or a tool whose name is an assigned slug — the platform, in a single transaction:
  • inserts one row into skill_invocations (an append-only audit log: which skill, which agent, which workspace, when, and the exit code);
  • bumps the skill’s denormalised counters: usage_count, last_used_at, and — when the call reported a non-zero exit code — error_count;
  • emits a skill.invoked entry to the Crew Journal (payload carries skill_id, skill_slug, agent_id, tool_name, exit_code, and the post-increment usage_count).
Recording is best-effort and off the hot path — it runs in a bounded background worker, so a busy agent is never slowed by telemetry, and a tool call that does not correspond to an assigned skill is silently ignored. A non-skill tool (e.g. Read, Bash) never produces an invocation row. The skill-review routine reads the skill_invocations aggregate (count + error count over a lookback window) to decide whether an assigned skill is still earning its place in the system prompt. Filter the journal Timeline on skill.invoked to see, per agent, exactly which skills are pulling their weight.

​
What’s Next

Orchestration

Create multi-agent missions with task delegation and workflow templates.

Templates

Deploy pre-configured crews with built-in skill assignments.

CLI Reference

Import, assign, and manage skills via the CLI.

API Reference

Skills API endpoints for programmatic access.