Skills Reference

Skills are the atomic capabilities of the WASP agent. The LLM calls skills using XML-like syntax: <skill>skill_name(param="value")</skill>.

Capability Levels

Every skill is assigned a capability level that controls auditing, risk assessment, and rate limiting:

Level	Examples	Audit	Risk Check	Rate Limit
SAFE	calculate, datetime	No	No	Unlimited
MONITORED	web_search, fetch_url, browser	No	No	Unlimited
CONTROLLED	reminders, gmail, task_manager	Yes	No	Unlimited
RESTRICTED	shell, python_exec, http_request, file_ops	Yes	Yes	Unlimited
PRIVILEGED	broker (Docker commands)	Yes	Yes	20/hour

Built-in Skills

Web & Research

Skill	Capability	Description
web_search	MONITORED	DuckDuckGo search, returns 5-10 results with snippets
fetch_url	MONITORED	HTTP GET with CSS selector support, 12k output cap
scrape	MONITORED	Extract structured data from web pages
browser	MONITORED	Full Chromium browser (click, type, screenshot, login, JS)

Browser skill actions: navigate, click, type, screenshot, capture, get_text, scroll, get_links, execute_js

Named browser sessions for persistent state:

browser(action="navigate", url="https://...", session="my_session")

Code & System

Skill	Capability	Description
python_exec	RESTRICTED	Execute Python code in subprocess, 60s timeout, 8k output
shell	RESTRICTED	Execute shell commands, 60s default / 120s max timeout
calculate	SAFE	Mathematical calculations

File Operations

Skill	Capability	Description
read_file	RESTRICTED	Read any file in the container
write_file	RESTRICTED	Write any file in the container

Files accessible under /data/ (persistent volume mounts).

Communication & Calendar

Skill	Capability	Description
gmail	CONTROLLED	Read inbox, send email, search, reply
create_reminder	CONTROLLED	Create time-based reminders (fires via scheduler)
task_manager	CONTROLLED	Create/list/update/delete recurring tasks

Data & APIs

Skill	Capability	Description
http_request	RESTRICTED	HTTP GET/POST/PUT/DELETE/PATCH with custom headers
subscribe	CONTROLLED	RSS feed and price alert subscriptions

Memory & Knowledge

Skill	Capability	Description
memory	CONTROLLED	Search and store in episodic/semantic memory
knowledge_graph	CONTROLLED	Query entities and relationships

Agent Management

Skill	Capability	Description
agent_manager	CONTROLLED	Create, list, pause, resume, archive sub-agents

Actions: create, list, get, pause, resume, archive

Self-Improvement

Skill	Capability	Description
self_improve	PRIVILEGED	Read, propose, apply, patch, install on own source code
skill_manager	PRIVILEGED	Create, edit, toggle, delete skills at runtime

self_improve actions: read, propose, list, apply, reject, patch, install

skill_manager actions: create, list, edit, toggle, delete

Integrations

Skill	Capability	Description
integration	CONTROLLED	Invoke any registered integration connector

Parallel Execution

Skills can run in parallel by using <parallel> blocks:

<parallel>
  <skill>web_search(query="BTC price")</skill>
  <skill>web_search(query="ETH price")</skill>
  <skill>fetch_url(url="https://api.coinbase.com/v2/prices/BTC-USD/spot")</skill>
</parallel>

All skills in a parallel block execute concurrently via asyncio.gather().

Custom Python Skills

Create custom skills via skill_manager:

skill_manager(
  action="create",
  name="my_skill",
  description="Does something custom",
  params="input_text,max_length",
  code="
class MySkillSkill(SkillBase):
    def definition(self):
        return SkillDefinition(
            name='my_skill',
            description='Does something custom',
            parameters=[
                SkillParameter(name='input_text', type='string', required=True),
                SkillParameter(name='max_length', type='integer', required=False),
            ]
        )

    async def execute(self, input_text: str, max_length: int = 500) -> SkillResult:
        result = input_text[:max_length]
        return SkillResult(output=result)
"
)

Custom skills are stored in /data/skills/<slug>/skill.py and survive container restarts.

Skill Registration

Skills are registered at startup in src/skills/builtin/__init__.py:

registry.register(WebSearchSkill())
registry.register(BrowserSkill())
registry.register(PythonExecSkill())
# ... etc

Each skill must implement SkillBase:

• definition() → SkillDefinition — metadata, parameters, examples
• async execute(**params) → SkillResult — execution logic

Anticipatory Simulation

Before executing RESTRICTED or PRIVILEGED skills, the agent runs an anticipatory simulation:

• The LLM predicts the consequences of the action
• Result is appended to skill output as [ANTICIPATORY SIMULATION]:
• Helps the agent course-correct before irreversible actions

Skill Output Format

SkillResult(
    output="...",   # Human-readable output (max 8k chars)
    error=None,     # Error message if failed
    metadata={},    # Optional structured data
)