一键导入
invoke
Execute a composed workflow by name. Use when running predefined workflows, orchestrating multi-step processes, or delegating to workflow templates.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Execute a composed workflow by name. Use when running predefined workflows, orchestrating multi-step processes, or delegating to workflow templates.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Analyze a task description to detect required capabilities from the ontology, identify gaps, and synthesize a valid workflow automatically. Trigger: "discover capabilities", "what capabilities do I need", "analyze task", "synthesize workflow"
Establish cause-effect relationships between events or states. Use when analyzing root causes, mapping dependencies, tracing effects, or building causal models.
Produce a comprehensive audit trail of actions, tools used, changes made, and decision rationale. Use when recording compliance evidence, tracking changes, or documenting decision lineage.
Identify capability gaps and propose new skills with prioritization. Use when analyzing missing capabilities, planning skill development, performing ontology expansion, or assessing coverage.
Create a safety checkpoint marker before mutation or execution steps. Use when about to modify files, execute plans, or perform any irreversible action. Essential for the CAVR pattern.
Assign labels or categories to items based on characteristics. Use when categorizing entities, tagging content, identifying types, or labeling data according to a taxonomy.
| 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 |
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:
Compatible schemas:
schemas/output_schema.yamlreference/workflow_catalog.yaml| 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.) |
Resolve workflow: Find workflow definition
Validate inputs: Check input against workflow schema
Initialize execution: Set up workflow context
Execute steps: Run workflow steps in order
Handle failures: Respond to step failures
Aggregate results: Collect workflow outputs
Return results: Provide complete execution record
Return a structured object:
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 | 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 |
Input:
workflow: "world_model_build"
input:
domain: "user authentication"
constraints:
scope: "backend services"
Output:
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"
Input:
workflow: "digital_twin_sync_loop"
input:
world_state: "${previous_state}"
options:
max_retries: 3
Output:
result:
success: true
workflow: "digital_twin_sync_loop"
output:
drift_detected: true
actions_taken: 2
verification: "PASS"
steps_executed:
- step_id: "receive"
status: "success"
output_key: "receive_out"
duration: "0.5s"
- step_id: "detect"
status: "success"
output_key: "detect_out"
duration: "1.2s"
- step_id: "measure"
status: "success"
output_key: "measure_out"
duration: "0.8s"
- step_id: "plan"
status: "success"
output_key: "plan_out"
duration: "2.1s"
- step_id: "checkpoint"
status: "success"
output_key: "checkpoint_out"
duration: "0.3s"
- step_id: "mutate"
status: "failed"
output_key: "mutate_out"
duration: "1.5s"
- step_id: "mutate"
status: "success"
output_key: "mutate_out"
duration: "1.2s"
- step_id: "verify"
status: "success"
output_key: "verify_out"
duration: "2.0s"
execution:
id: "exec-20240115-002"
started_at: "2024-01-15T11:00:00Z"
completed_at: "2024-01-15T11:00:10Z"
duration: "9.6s"
failures:
- step: "mutate"
error: "Connection timeout"
recovery_attempted: true
evidence_anchors:
- "workflow:digital_twin_sync_loop:verify_out"
Input:
workflow: "digital_twin_bootstrap"
input:
domain: "payment processing"
Output:
result:
success: true
workflow: "digital_twin_bootstrap"
output:
world_model: "${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 tools: Read (to verify workflow catalog)
mutation: falserequires_checkpoint: falserequires_approval: falserisk: mediumCapability-specific rules:
Commonly follows:
plan - Invoke workflow to execute plandecompose - Invoke sub-workflows for sub-problemsCommonly precedes:
verify - Verify workflow resultsaudit - Record workflow executionexplain - Explain workflow resultsAnti-patterns:
Workflow references:
reference/workflow_catalog.yaml#digital_twin_bootstrap for nested invocation