REPLACE-WITH-WORKFLOW-NAME

Skill Name

Standalone install? If this session was not initialized by the TAO skill bank plugin, run the tao-setup skill first (host preflight, credentials, cross-skill discovery).

High-level description of what this workflow accomplishes end-to-end.

External dependencies

Plus everything the sub-skills require — see "Related skills" below.

Related skills

This workflow invokes:

• tao-skill-bank:<skill-1> —
• tao-skill-bank:<skill-2> —
• tao-skill-bank:<platform> — platform execution

Quick start

Default run

> Run the <workflow-name> workflow on <user-data-description>.

The orchestrator collects inputs, validates them, then dispatches the stages below.

With custom KPI / parameters

> Run the <workflow-name> workflow with KPI <metric < target>, max_iterations=3.

Resume after crash

> Resume the in-progress <workflow-name> run at <storage_root>.

State persists in <storage_root>/<state_file>.json — orchestrator reads on startup.

Inputs

Stages

Stage 1:

• Skill: tao-skill-bank:<skill>
• Input:
• Output:
• Condition: when this stage runs (always / conditional)

Stage 2:

(similar structure)

Storage layout

<storage_root>/
├── stage_1_output/
└── stage_2_output/

Iteration control (if applicable)

• Termination condition: KPI / metric / turn count.
• State management: how iteration N's output flows into iteration N+1.
• Checkpointing: how to resume after a crash.

Instructions

When the user asks to run this workflow, follow these steps in order:

Step 1 — Gather inputs

Confirm with the user:

1. <input-1>: Path / value.
2. <input-2>: Path / value (optional, default <value>).

Verify inputs exist:

ls <path>

Step 2 — Run the pipeline

Dispatch each stage in order. Read each sub-skill's SKILL.md for its specific invocation.

Step 3 — Report results

After completion, report metrics + output path to the user.

Known pitfalls