Skip to content
Skills Library
AI & agents · Automation

invoke

/invoke

Execute a composed workflow by name. Use when running predefined workflows, orchestrating multi-step processes, or delegating to workflow templates.

Licence
Apache-2.0
Last repository change
30.08.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
6
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 30.08.2026, without references to retired models or APIs.

Licence

Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.

What it does and when to use it

Execute a composed workflow by name. Use when running predefined workflows, orchestrating multi-step processes, or delegating to workflow templates.

Arguments

/invoke [workflow] [input] [options]
Original author description

Execute a composed workflow by name. Use when running predefined workflows, orchestrating multi-step processes, or delegating to workflow templates.

How it works

  1. Intent
  2. Inputs
  3. Procedure
  4. Output Contract
  5. Examples
  6. Verification
  7. Safety Constraints
  8. Composition Patterns
Original SKILL.md headings · 310 lines, 910 words
SKILL.md preview
---
name: invoke
description: Execute a composed workflow by name. Use when running predefined workflows, orchestrating multi-step processes, or delegating to workflow templates.
argument-hint: "[workflow] [input] [options]"
disable-model-invocation: false
user-invocable: true
allowed-tools: Read, Grep, Bash, Edit, Write
context: fork
agent: general-purpose
layer: COORDINATE
---

## Intent

Invoke a predefined workflow by name, passing input parameters and receiving aggregated results. This enables reuse of common capability compositions and supports hierarchical workflow organization.

**Success criteria:**
- Workflow executed according to definition
- All steps completed or gracefully failed
- Results aggregated and returned
- Execution trace available for debugging

**Compatible schemas:**
- `schemas/output_schema.yaml`
- `reference/workflow_catalog.yaml`

## Inputs

| Parameter | Required | Type | Description |
|-----------|----------|------|-------------|
| `workflow` | Yes | string | Workflow name from workflow catalog |
| `input` | No | object | Input parameters for workflow |
| `options` | No | object | Execution options (timeout, retry, etc.) |

## Procedure

1) **Resolve workflow**: Find workflow definition
   - Look up workflow in workflow_catalog.yaml
   - Validate workflow exists
   - Load workflow specification

2) **Validate inputs**: Check input against workflow schema
   - Verify required inputs provided
   - Validate input types
   - Apply defaults for missing optional inputs

3) **Initialize execution**: Set up workflow context
   - Create execution ID
   - Initialize step tracking
   - Set up data flow context

4) **Execute steps**: Run workflow steps in order
   - Execute each capability in sequence
   - Handle step dependencies
   - Propagate data between steps via store_as

5) **Handle failures**: Respond to step failures
   - Execute failure_modes actions
   - Attempt recovery if specified
   - Trigger rollback if needed

6) **Aggregate results**: Collect workflow outputs
   - Gather outputs from each step
   - Evaluate success criteria
   - Compute overall result

7) **Return results**: Provide complete execution record
   - Include all step outputs
   - Provide execution trace
   - Report success/failure

## Output Contract

Return a structured object:

```yaml
result:
  success: boolean  # Whether workflow completed successfully
  workflow: string  # Workflow that was executed
  output: any  # Primary workflow output
steps_executed:
  - step_id: string  # Capability name
    status: string  # success, failed, skipped
    output_key: string  # store_as value
    duration: string
execution:
  id: string  # Unique execution ID
  started_at: string  # ISO timestamp
  completed_at: string  # ISO timestamp
  duration: string  # Total execution time
failures:
  - step: string
    error: string
    recovery_attempted: boolean
evidence_anchors: ["workflow:step:output"]
```

### Field Definitions

| Field | Type | Description |
|-------|------|-------------|
| `result.success` | boolean | Whether workflow completed |
| `result.workflow` | string | Name of executed workflow |
| `result.output` | any | Final workflow output |
| `steps_executed` | array | Record of each step's execution |
| `execution` | object | Execution metadata |
| `failures` | array | Any failures encountered |

## Examples

### Example 1: Invoke World Model Build

**Input:**
```yaml
workflow: "world_model_build"
input:
  domain: "user authentication"
  constraints:
    scope: "backend services"
```

**Output:**
```yaml
result:
  success: true
  workflow: "world_model_build"
  output:
    world_state:
      world_id: "auth-model-001"
      entities: 12
      relationships: 18
    summary: "Authentication system model with 12 entities"
steps_executed:
  - step_id: "retrieve"
    status: "success"
    output_key: "retrieve_out"
    duration: "1.2s"
  - step_id: "observe"
    status: "success"
    output_key: "observe_out"
    duration: "2.5s"
  - step_id: "state"
    status: "success"
    output_key: "state_out"
    duration: "3.1s"
  - step_id: "transition"
    status: "success"
    output_key: "transition_out"
    duration: "2.8s"
  - step_id: "ground"
    status: "success"
    output_key: "ground_out"
    duration: "1.5s"
  - step_id: "simulate"
    status: "success"
    output_key: "simulate_out"
    duration: "4.2s"
  - step_id: "explain"
    status: "success"
    output_key: "explain_out"
    duration: "1.1s"
execution:
  id: "exec-20240115-001"
  started_at: "2024-01-15T10:00:00Z"
  completed_at: "2024-01-15T10:00:16Z"
  duration: "16.4s"
failures: []
evidence_anchors:
  - "workflow:world_model_build:retrieve_out"
  - "workflow:world_model_build:state_out"
```

### Example 2: Invoke with Failure Recovery

**Input:**
```yaml
workflow: "digital_twin_sync_loop"
input:
  world_state: "${previous_state}"
options:
  max_retries: 3
```

**Output:**
```yaml
result:
  success: true
  workflow: "digital_twin_sync_loop"
  output:
    drift_detected: true
    actions_taken: 2
    verification: "PASS"
steps_executed:
  - step_id: "receive"
    status: "success"
    output_key: "receive_out"
    duration: "0.5s"
  - step_id: "detect"
    status: "success"
    output_key: "detect_out"
    duration: "1.2s"
  - step_id: "measure"
    status: "success"
    output_key: "measure_out"
    duration: "0.8s"
  - step_id: "plan"
    status: "success"
    output_key: "plan_out"
    duration: "2.1s"
  - step_id: "checkpoint"
    status: "success"
    output_key: "checkpoint_out"
    duration: "0.3s"
  - step_id: "mutate"
    status: "failed"
    output_key: "mutate_out"
    duration: "1.5s"
  - step_id: "mutate"
    status: "success"
    output_key: "mutate_out"
    duration: "1.2s"
  - step_id: "verify"
    status: "success"
    output_key: "verify_out"
    duration: "2.0s"
execution:
  id: "exec-20240115-002"
  started_at: "2024-01-15T11:00:00Z"
  completed_at: "2024-01-15T11:00:10Z"
  duration: "9.6s"
failures:
  - step: "mutate"
    error: "Connection timeout"
    recovery_attempted: true
evidence_anchors:
  - "workflow:digital_twin_sync_loop:verify_out"
```

### Example 3: Nested Workflow Invocation

**Input:**
```yaml
workflow: "digital_twin_bootstrap"
input:
  domain: "payment processing"
```

**Output:**
```yaml
result:
  success: true
  workflow: "digital_twin_bootstrap"
  output:
    world_model: "${world_model_out}"
    first_sync: "${sync_out}"
steps_executed:
  - step_id: "invoke"
    status: "success"
    output_key: "world_model_out"
    duration: "18.5s"
    nested_workflow: "world_model_build"
  - step_id: "invoke"
    status: "success"
    output_key: "sync_out"
    duration: "12.3s"
    nested_workflow: "digital_twin_sync_loop"
execution:
  id: "exec-20240115-003"
  started_at: "2024-01-15T12:00:00Z"
  completed_at: "2024-01-15T12:00:31Z"
  duration: "30.8s"
failures: []
evidence_anchors:
  - "workflow:digital_twin_bootstrap:world_model_out"
  - "workflow:digital_twin_bootstrap:sync_out"
```

## Verification

- [ ] Workflow name resolves to valid definition
- [ ] All required inputs provided
- [ ] Each step executed or skipped with reason
- [ ] Failures handled according to failure_modes
- [ ] Success criteria evaluated

**Verification tools:** Read (to verify workflow catalog)

## Safety Constraints

- `mutation`: false
- `requires_checkpoint`: false
- `requires_approval`: false
- `risk`: medium

**Capability-specific rules:**
- Workflow must exist in workflow_catalog.yaml
- Respect step-level safety constraints
- Propagate checkpoint requirements to mutating steps
- Do not modify workflow definitions at runtime
- Log all step executions for audit

## Composition Patterns

**Commonly follows:**
- `plan` - Invoke workflow to execute plan
- `decompose` - Invoke sub-workflows for sub-problems

**Commonly precedes:**
- `verify` - Verify workflow results
- `audit` - Record workflow execution
- `explain` - Explain workflow results

**Anti-patterns:**
- Avoid deeply nested invocations (max 3 levels)
- Never invoke workflows recursively
- Do not invoke without understanding workflow effects

**Workflow references:**
- See `reference/workflow_catalog.yaml#digital_twin_bootstrap` for nested invocation
- This capability is the entry point for all workflow execution
Files in this package (6)
  • SKILL.md 8 KB
  • reference/event_schema.yaml 4 KB
  • reference/transform_mapping_rawlog_to_observation.yaml 2 KB
  • reference/workflow_catalog.yaml 56 KB
  • reference/world_state_schema.yaml 11 KB
  • schemas/output_schema.yaml 1 KB

Versions

RepositoryScoreLicence
This page · synaptiai/agent-capability-standard100Apache-2.0
Alejo2075/claude-code-aws90MIT

Database snapshot: 13.11.2026 · package version 6f55d3d8f296 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100workflow-automation
    Workflow creation, execution, and template management. Automates complex multi-step processes with agent coordination. Use when: automating processes, creating reusable workflows, orchestrating multi-step tasks. Skip when: simple single-step tasks, ad-hoc operations.
  • 100orchestration-patterns
    Agentic orchestration patterns for long-running tasks. Implements evidence-based delivery and iterative agent loops. Use when managing multi-step work, coordinating workflows, or orchestrating PR workflows.
  • 90agent-workflow
    Create, update, run, resume, or continue agent workflows. Use when the user asks to create or fix workflow JSON, execute an existing workflow, run a workflow with a prompt, resume a workflow run, or continue the next node in a waiting multi-step workflow.
  • 100orchestrating-multi-agent-systems
    Execute orchestrate multi-agent systems with handoffs, routing, and workflows across AI providers. Use when building complex AI systems requiring agent collaboration, task delegation, or workflow coordination. Trigger with phrases like "create multi-agent system", "orchestrate…
  • 100orchestrating-multi-agent-systems
    Execute orchestrate multi-agent systems with handoffs, routing, and workflows across AI providers. Use when building complex AI systems requiring agent collaboration, task delegation, or workflow coordination. Trigger with phrases like "create multi-agent system", "orchestrate…
  • 100conductor
    Validate, run, and execute workflows; creating new workflows when explicitly asked. Use when orchestrating AI agents via YAML workflow files, executing an existing workflow, debugging execution, configuring routing between agents, setting up human-in-the-loop gates, or…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.