dimagi-internal

Produce a domain-expert-facing before/after (pre-post) Google Doc for a DDD narrative iteration, and read the expert's edits back. Pull the verbatim CURRENT narration from canopy-web, apply reviewer feedback into a PROPOSED next version, publish a scannable side-by-side doc a non-engineer can review, then read their suggestion-mode edits via the structured Doc. Use when iterating a Connect DDD narrative on expert feedback (e.g. RF Surveys / Sophie), when asked to "make a before/after of the narration", "iterate the narrative on <expert>'s feedback", or "let <expert> sign off on the language".

Apply the two HQ-layer standing-instruction settings Nova can't set at build time — camera-only photo capture (appearance="acquire" on Deliver image uploads) and grid menu display on every module — to the deployed draft apps, then resolve the matching Phase-3 residuals. Runs between app-deploy and app-release.

Build the CommCare Learn (training) app from the PDD via Nova's /nova:autobuild. Captures nova_app_id and writes a structure summary.

Render a training deck spec.yaml into a Google Slides deck via the 14-stencil ACE template. Produces a presentable Slides URL.

Phase 3 § Step 2.8 — structural + install-time QA on the released Learn + Deliver CCZs. Downloads each CCZ via commcare_download_ccz, parses the zip + suite.xml + form XMLs, verifies form counts + Connect-marker presence match the Nova blueprint, then runs commcare-cli `validate` + `play` as install-time runtime gates. AVD-free, Connect-free — purely CCHQ-side. Halts loud on mismatch.

Run app smoke recipes against a local AVD and capture per-step screenshots for the training deck. Per-opp content only.

Generate a training deck spec.yaml from PDD, app summaries, screenshot manifests, and a template bundle. The spec is the source of truth for the training deck — training-deck-render produces Google Slides from it.

ACE's pre-send review — invokes the fleet-wide `canopy:agent-turn-review` discipline, then adds ACE's specifics. Run before EVERY outbound reply / deliverable / PR.

Use this skill when iterating on a live workflow in labs — reading JSX, editing render code, pushing it back — via the connect_labs MCP. Triggers on phrases like "pull workflow", "fix the workflow UI", "edit workflow X", "update the render code on workflow N", "clone this workflow", "make this a template". Do NOT use for editing seed template .py files in the repo (use workflow-templates for that).

Use this skill ONLY when authoring a new SEED template — a Python file in connect_labs/workflow/templates/ that ships with labs and scaffolds new workflows via workflow_create_from_template. For editing a live workflow instance in labs (the common case), use workflow-author instead. For editing a live pipeline schema, use pipeline-author.

Use when composing or editing a labs "surface" — a card landing page at /labs/p/<slug> — via the connect_labs MCP. Triggers on "build a program hub", "make a landing page for program/opp X", "add an audit card", "create a pages surface".

Deploy the labs environment to AWS via GitHub Actions. Use when the user wants to deploy, release, or push changes to the labs environment.

Use when the user wants to set up or refresh their labs MCP Personal Access Token (PAT). Triggers on "set up labs mcp", "I need a labs token", "configure claude for labs", "my labs token expired", "connect me to labs". Opens the labs UI to approve a new token, receives it via a localhost callback, and registers a `connect_labs` MCP server in Claude Code via `claude mcp add --scope user`.

Use this skill when iterating on a live pipeline in labs — editing schemas, previewing sample rows, saving changes — via the connect_labs MCP. Triggers on phrases like "add a field to pipeline X", "change the aggregation on", "preview pipeline", "why is pipeline N returning wrong data". Do NOT use for workflow JSX edits (use workflow-author for that).

Add or update environment variables in the AWS ECS Fargate deployment. Use when the user wants to add env vars, secrets, or update task definitions for the labs environment.