メニュー
Automatically loads Wire engagement and release context at the start of a conversation. Fires when a .wire/ directory is present and context has not yet been established in the current session.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Generates a delivery-focused status report for a named Rittman Analytics client engagement. Anchored on SOW milestones and sprint cadence — not a relationship or commercial report. Reports milestone status (on track / at risk / slipping), tickets and MRs delivered, bugs raised and resolved, decisions owed by the client, cross-cutting risks, and client and team sentiment. Pulls from Fathom meeting transcripts, client Slack channels (external and internal), and Atlassian where available. Use when Mark asks for delivery status, project status, milestone status, sprint status, "where are we on [client]", "is [client] on track", or "what's slipping on [client]". Triggers on any client name (Client A, Client B, Client C, Client D, Client E, Barton Peveril, Client F, Client H, Client I, Client J) plus a delivery framing.
Proactive skill for building Dagster orchestration layers. Auto-activates when creating or modifying Dagster assets, schedules, sensors, or components, or when working on the orchestration artifact in a Wire project. Covers the assets-first pattern, dagster-dbt integration, automation (schedules, sensors, declarative automation), the component framework, and CLI usage (dg dev, dg launch, dg check, dg scaffold).
Proactive skill for answering business analytics questions using dbt's Semantic Layer, Discovery API, or direct SQL. Auto-activates when a user asks a data or metrics question against a dbt project (e.g. "What were total sales last quarter?", "Show me top customers by revenue"). Uses a 4-level escalation — Semantic Layer first, modified compiled SQL, model discovery, manifest analysis. Always exhausts all options before saying "cannot answer."
Proactive skill for generating Mermaid flowchart diagrams of dbt model lineage. Auto-activates when a user asks to visualise dbt model dependencies, create a lineage diagram, or show the dbt DAG. Uses MCP get_lineage tools first, then manifest.json parsing, then direct code parsing as fallbacks. Produces colour-coded diagrams matching Wire's naming conventions.
Proactive skill for validating dbt models against coding conventions. Auto-activates when creating, reviewing, or refactoring dbt models in staging, integration, or warehouse layers. Validates naming, SQL structure, field conventions, testing coverage, and documentation. Supports project-specific convention overrides and sqlfluff integration.
Proactive skill for creating dbt unit tests. Auto-activates when working with dbt model testing, mock inputs/outputs, or transformation validation. Covers the Model-Inputs-Outputs pattern, format selection (dict/CSV/SQL), BigQuery-specific caveats, and production deployment guidance.
| name | Engagement Context |
| description | Automatically loads Wire engagement and release context at the start of a conversation. Fires when a .wire/ directory is present and context has not yet been established in the current session. |
| triggers | ["Any message in a repository containing a .wire/ directory where engagement context has not yet been loaded","User begins discussing an engagement, release, or artifact without prior context in the conversation","User asks what to work on next, what the current status is, or what release is active"] |
Before proceeding with any work, append a one-line entry to .wire/execution_log.md (at engagement root, or within the active release if no engagement-root log exists):
| YYYY-MM-DD HH:MM | skill | engagement-context | activated | Context loaded for new conversation |
If .wire/execution_log.md does not exist, create it with the standard header first.
This skill fires automatically at the start of a conversation in any repository that contains a .wire/ directory, when the agent has not yet established engagement context. It is the replacement for the deprecated /wire:session-start command — context loading is now implicit, not explicit.
Do NOT fire this skill if:
Check .wire/releases/*/status.md (two-tier layout) or .wire/*/status.md (legacy layout). Sort by last modified; use the most recently modified.
If multiple releases exist, note them all. Use the most recently modified as the active release for the context summary.
Read .wire/engagement/context.md if present. Extract:
Read the active release status.md. Extract:
Output a brief, scannable context block before responding to the user's request:
## Wire Engagement Context
**Client**: [client_name] | **Release**: [release_name] ([release_type])
**Phase**: [current_phase] | **Last worked**: [date of last session history row, or "no prior sessions"]
**Status**: [X artifacts complete, Y in progress] — [brief 1-line state of play]
**Suggested next**: [next focus from last session, if any]
Keep this to 4–6 lines. Do not dump the entire status file. If there is no prior session history, say so in one line.
After outputting the context summary, immediately proceed with what the user asked for. Do not ask for permission to continue or offer a menu of options unless the user's request is ambiguous.
If the user asked a specific question or gave a specific instruction, answer it — do not replace their intent with a session plan. Reserve structured planning for /wire:session-plan.
Do not activate. Proceed normally without Wire context.
Output the context summary with "No prior sessions" for the last-worked field and suggest the first incomplete artifact as the natural next step.
List all releases in one line: "3 releases: 01-discovery (complete), 02-data-foundation (active), 03-dashboards (planned)." Focus the state detail on the most recently modified.
Load release state only. Note "No engagement context file found" in one line — non-blocking.
/wire:session-plan for that)