Explore skills
Showing 38491–38520 of 71536 skills
Grade whether every Learn and Deliver build was actually released so Connect can read deliver units. Needs the HQ app ids.
dimagi-internal/ace
Stars: 1Claude CodeCodexPass/fail structural and install-time checks on released Learn and Deliver CCZs. Use after a release, before Connect reads the apps.
dimagi-internal/ace
Stars: 1Claude CodeCodexInternal /ace:run step — Review the built apps as CommCare apps; route defects to builder, brief or platform.
dimagi-internal/ace
Stars: 1Claude CodeCodexRun app smoke recipes on a local Android emulator and capture per-step screenshots (e.g. for a training deck). Needs Maestro recipes and released apps.
dimagi-internal/ace
Stars: 1Claude CodeCodexTurn PDD user journeys into Maestro test recipes with real selectors from a Nova-built app. Needs the app-journeys doc and the Nova app.
dimagi-internal/ace
Stars: 1Claude CodeCodexInternal /ace:run step — Grade FLW app UX from screenshots against the journeys.
dimagi-internal/ace
Stars: 1Claude CodeCodexCopy a completed ACE run into another ace-web workspace and rebuild its assets in that workspace's own HQ space and Connect orgs, so outside reviewers see it without other runs. No invites (that is release). Use before an external review.
dimagi-internal/ace
Stars: 1Claude CodeCodexRecord a Coach chat, ACE as the worker. Use for demo footage.
dimagi-internal/ace
Stars: 1Claude CodeCodexCapture and publish common Connect platform screenshots for training deck common modules. Manual trigger only — not part of /ace:run.
dimagi-internal/ace
Stars: 1Claude CodeCodexUpgrade the pinned Connect/CommCare APK end to end — release lookup, calibrate, flip every pin, activate, verify, roll back. Use when a new APK becomes ACE's default.
dimagi-internal/ace
Stars: 1Claude CodeCodexCapture the per-Connect-version baseline of "how Connect works" screenshots reused across every training deck. Manual, cross-opp.
dimagi-internal/ace
Stars: 1Claude CodeCodexInternal /ace:run step — Grade the run's Connect opportunity setup against its PDD.
dimagi-internal/ace
Stars: 1Claude CodeCodexCreate or reuse a Connect program matched to a PDD's delivery archetype and record its id. Needs an approved PDD.
dimagi-internal/ace
Stars: 1Claude CodeCodexInternal /ace:run step — Grade the run's Connect program setup against its PDD.
dimagi-internal/ace
Stars: 1Claude CodeCodexSay and defend what a round of spend buys in a place (deaths averted, cost per death, multiple of GiveWell's bar): Connect's own programs (the CHC, MBW and KC models, in Labs' cost-effectiveness explorer), and what reaching everyone in chosen places would cost. Use when a funder asks the expected return, or before a BOTEC goes into a pitch.
dimagi-internal/ace
Stars: 1Claude CodeCodexInternal /ace:run step — Grade a closed run end to end; recommend improvements.
dimagi-internal/ace
Stars: 1Claude CodeCodexInternal /ace:run step — Re-grade a cycle-grade report for self-grade inflation.
dimagi-internal/ace
Stars: 1Claude CodeCodexInternal /ace:run step — Render a per-run decisions.yaml into a prose Google Doc at one stable URL per run.
dimagi-internal/ace
Stars: 1Claude CodeCodexSync human edits from the per-run decisions.gdoc back into decisions.yaml. Human-triggered via /ace:step decisions-sync; not part of the orchestrator's automatic phase loop.
dimagi-internal/ace
Stars: 1Claude CodeCodexCross-check a targeting figure against outside data and write its defence. Use before a number reaches a funder or a published document.
dimagi-internal/ace
Stars: 1Claude CodeCodexStand up a demo dataset and live labs dashboard, from a brief (de-novo synthetic) or a real opp (clone), and return the dashboard URL. Also run by /ace:demo.
dimagi-internal/ace
Stars: 1Claude CodeCodexInternal /ace:run step — Pass/fail check that a demo dataset handoff is live.
dimagi-internal/ace
Stars: 1Claude CodeCodexWrite a funder-tuned DDD narrative (why-brief + spec) whose scenes render a live labs dashboard. Needs a demo dashboard URL. Also run by /ace:demo.
dimagi-internal/ace
Stars: 1Claude CodeCodexAudit the ACE plugin's internal structure for drift between the three sources of truth — agent frontmatter, lib/artifact-manifest.ts, and agents/orchestrator-reference.md § State Schema. Reports unclaimed manifest producers, orphan SKILL.md directories, missing skill files, phase-vocab mismatches, and state-schema parity gaps.
dimagi-internal/ace
Stars: 1Claude CodeCodexPropose a marketplace EOI round's evaluation criteria from its submissions; saved to labs on approval. Needs the round slug.
dimagi-internal/ace
Stars: 1Claude CodeCodexAI-review a marketplace EOI round's responses on its labs criteria and write a shortlist doc. Needs the round slug.
dimagi-internal/ace
Stars: 1Claude CodeCodexInternal /ace:run step — Method reference for calibrating -eval rubrics against ground truth.
dimagi-internal/ace
Stars: 1Claude CodeCodexCapture a reviewer's feedback verbatim, stamp each change made in response, and render "where did my comment go?". Use when an expert reviews an ACE artifact (gdoc comments, an email, a meeting) and ACE will act on it.
dimagi-internal/ace
Stars: 1Claude CodeCodexFork an existing ACE run at a phase or skill boundary via ace-web, copying upstream artifacts into a new run. Use to A/B test a skill change or re-run a phase tail without overwriting a run.
dimagi-internal/ace
Stars: 1Claude CodeCodexPut draft emails in a Google Doc as email blocks. A person clicks a block's Gmail icon to open it as a filled-in Gmail draft. Use for any Doc of emails a human will send.
dimagi-internal/ace
Stars: 1Claude CodeCodex