dx-estimate

Defaults

Read shared/provider-config.md for provider detection and tool mapping.

Read .ai/config.yaml:

• tracker.provider (or scm.provider for backward compat) — ado (default) or jira

If provider = ado:

• Organization: scm.org
• Project: scm.project

If provider = jira:

• Jira URL: jira.url
• Project Key: jira.project-key

You are a coordinator. You do NOT implement anything yourself. You delegate each analysis step to a subagent via the Agent tool, then synthesize results and post an estimation comment.

Argument

The argument is one work item ID — a numeric ADO ID (e.g., 2435084) or a Jira issue key.

If the user provides a full ADO URL like https://dev.azure.com/{org}/{project}/_workitems/edit/{id}, extract the numeric ID.

If no argument is provided, ask the user for the work item ID.

If more than one ID is given, estimate the first and tell the user to run /dx-estimate <id> once per remaining story. There is no batch mode: this skill has disable-model-invocation, so subagents cannot run it.

Execution Order

Step 1: fetch     → raw-story.md
Step 2: explain   → explain.md
Step 3: research  → research.md
Step 4: synthesize estimation + post ADO comment

Idempotent by default: Steps 1-3 check if output files already exist and are still valid before regenerating. Step 4 checks for an existing estimation comment (by signature) and updates it instead of duplicating.

Instructions

1. Dispatch steps 1–3 sequentially

For each step, use the Skill tool to invoke the skill in a fork. Wait for each to return before starting the next.

Step 1 — Fetch:

Invoke /dx-req <id> (Phase 1 only — fetch)

Print: Step 1/4 done — followed by the summary.

Step 2 — Explain:

Invoke /dx-req <id> (Phase 3 only — explain)

Print: Step 2/4 done — followed by the summary.

Step 3 — Research:

Invoke /dx-req <id> (Phase 4 only — research)

Print: Step 3/4 done — followed by the summary.