Skills

aid-design-data-pipeline

Frontmatter

name — aid-design-data-pipeline
description — Develop a data-pipeline design as a DESIGN SEED in .aid/design/data-pipeline.md — the source, the transform, the sink, and the schedule. Use this skill when where the data comes from, what happens to it, and where it lands are still open questions. Grounded in the Knowledge Base (.aid/knowledge/) and the project source. It WRITES NO production code and NO KB document — realize the seed into the built pipeline with /aid-create-data-pipeline once it is ready. Produced by the aid-architect agent and independently verified by aid-reviewer (full verify). Allocates a work-NNN folder.
allowed-tools — Read, Glob, Grep, Bash, Write, Edit, Agent
argument-hint — <subject> — the data pipeline to design (source, transform, sink, schedule)

Definition: canonical/skills/aid-design-data-pipeline/SKILL.md

Flow

flowchart TB
  classDef aidNode color:#fff
  classDef aidEntry fill:#166534,stroke:#14532d,color:#fff
  classDef aidExit fill:#991b1b,stroke:#7f1d1d,color:#fff
  classDef aidDecision fill:#92400e,stroke:#78350f,color:#fff
  classDef aidLoopBack fill:#1e3a8a,stroke:#1e3a8a,color:#fff
  classDef aidStep fill:#1a2035,stroke:#d4a853,color:#f1f5f9
  n1(["INTAKE"])
  n2["DESIGN"]
  n3["VERIFY"]
  n4["PRESENT<br/>hard stop -- the user decides"]
  n5(["DONE"])
  n1 --> n2
  n2 --> n3
  n3 -.-> n2
  n3 --> n4
  n4 --> n5
  class n1 aidEntry
  class n2 aidStep
  class n3 aidLoopBack
  class n4 aidStep
  class n5 aidExit
  class n1 aidNode
  class n2 aidNode
  class n3 aidNode
  class n4 aidNode
  class n5 aidNode

Source fragments

Every node in the chart above, in chart order, with the exact canonical/ text it was derived from.

1 · INTAKE · entry

## State: INTAKE

1. **Require a subject.** Empty argument -> ask one bootstrapping question ("What data
   pipeline do you want to design -- its source, transform, sink, and schedule?") and wait.
2. **Allocate** through the Work Initiation Gate exactly as the contract's Allocation rule
   requires (`canonical/skills/aid-design/SKILL.md` INTAKE step 4 is the shape), with
   `initiator: aid-design-data-pipeline`. `phase` is not driven.
3. **Acquire `.aid/design/`** per the contract, then read `.aid/design/data-pipeline.md` if
   a prior seed exists -- re-invocation iterates it rather than starting over.
4. **Classify complexity** for the `aid-architect` dispatch (verifier tier >= producer).

Source: canonical/skills/aid-design-data-pipeline/SKILL.md#L34-L43 · full step: canonical/skills/aid-design-data-pipeline/SKILL.md#L34-L45

2 · DESIGN · step

## State: DESIGN

Dispatch **`aid-architect`** (clean context, tiered) to write or iterate
`.aid/design/data-pipeline.md` in the seed shape the contract fixes (`design-seed.md`;
feature-002 §4), grounded in `.aid/knowledge/` and the project source plus any seed read
in INTAKE. What this artifact's seed must settle: **the source, the transform, the sink,
and the schedule**; its `## Destination` names where the built pipeline lands. **Never
writes `.aid/knowledge/` and never writes production code** -- the `design` invariant
(`design-lifecycle.md`).

Source: canonical/skills/aid-design-data-pipeline/SKILL.md#L49-L57 · full step: canonical/skills/aid-design-data-pipeline/SKILL.md#L49-L59

3 · VERIFY · loop-back

## State: VERIFY

**Full verify**, as `design-lifecycle.md` defines it. Not clean -> loop to DESIGN; the
3-cycle circuit breaker there escalates to IMPEDIMENT + `lifecycle: Blocked`.

Source: canonical/skills/aid-design-data-pipeline/SKILL.md#L63-L66 · full step: canonical/skills/aid-design-data-pipeline/SKILL.md#L63-L68

4 · PRESENT — hard stop — the user decides · step

## State: PRESENT (hard stop -- the user decides)

Set `lifecycle: Paused-Awaiting-Input`. Present the seed clearly. Assert no resolution --
the user iterates (re-invoke this skill) or realizes it now (`/aid-create-data-pipeline`).

Source: canonical/skills/aid-design-data-pipeline/SKILL.md#L72-L75 · full step: canonical/skills/aid-design-data-pipeline/SKILL.md#L72-L77

5 · DONE · exit · UNSPECIFIED

## State: DONE

Set `lifecycle: Completed`, `updated` now, append a `## Lifecycle History` row. The seed
persists at `.aid/design/data-pipeline.md`; consumption happens at
`/aid-create-data-pipeline`.

Source: canonical/skills/aid-design-data-pipeline/SKILL.md#L81-L85 · full step: canonical/skills/aid-design-data-pipeline/SKILL.md#L81-L85

Report an issue with this page →