Showing 51091–51120 of 77200 skills
Pass/fail check of a simulated N-week execution: calendar, weekly runs, isolation, no LLO contact. Static.
dimagi-internal/ace
Write one week's program review from labs' saved run and stock reads: progress, supply, actions.
dimagi-internal/ace
Grade a weekly program review against labs' own figures for that week (LLM judge).
dimagi-internal/ace
Edit an existing labs solicitation: extend its deadline, rewrite its text or criteria, change its visibility, or close or reopen it. Use when asked to change a published solicitation. Needs its id.
dimagi-internal/ace
Seed a private labs solicitation with synthetic responses and the ACE winner. Optional step; needs a solicitation id.
dimagi-internal/ace
Move a labs contract's goods and money: shipment, receipt, invoice, payment, confirmation. Needs contracts.
dimagi-internal/ace
Pass/fail check, from labs' three-way match, that each contract was received and paid for what arrived.
dimagi-internal/ace
Run one week of a labs programme's stock: transfers, distributions, counts and the week's reads.
dimagi-internal/ace
Pass/fail check of one labs stock week: flows balance, movements read back. Static.
dimagi-internal/ace
Run a labs programme's tender through quotes, award and contract. Needs a program id with supply-chain setup done.
dimagi-internal/ace
Pass/fail check, from a fresh labs read, that a tender ended in one award and one matching contract per line.
dimagi-internal/ace
Set up a labs programme's supply chain: who runs it, the team, commodities, items, stores and suppliers. Needs a program id.
dimagi-internal/ace
Pass/fail check, against a fresh labs read, that a programme's supply-chain setup landed. Static, no LLM.
dimagi-internal/ace
Find orphaned Connect programs, opportunities, payment units, and invites; deactivate or delete the safe ones. Needs a live-set from sweep-live-set.
dimagi-internal/ace
Find orphaned items under ACE's Drive root and trash the ones you approve. Needs a live-set from sweep-live-set.
dimagi-internal/ace
Find orphaned CommCare HQ apps in the ACE domain and soft-delete the ones you approve. Needs a live-set from sweep-live-set.
dimagi-internal/ace
Find orphaned connect-labs workflows, pipelines, synthetic data, and solicitations and clean them up. Needs a live-set from sweep-live-set.
dimagi-internal/ace
List every identifier still referenced by visible ACE opps in Drive: the keep-list every orphan sweep diffs against.
dimagi-internal/ace
Find orphaned OCS chatbots, pipelines, collections, and sessions and delete per-opp clones; the template is protected. Needs a live-set from sweep-live-set.
dimagi-internal/ace
Prune old ACE runs in Drive: keep the newest N per opp and trash the rest after approval.
dimagi-internal/ace
Check whether an opportunity's LLOs are hitting milestones on schedule and email a nudge to any that are behind.
dimagi-internal/ace
Internal /ace:run step — Grade the LLO onboarding email draft.
dimagi-internal/ace
Internal /ace:run step — Grade the FLW quick-reference card.
dimagi-internal/ace
Generate a new ace-web video program (spec.yaml + run-001) from a Connect program page URL using the 60s-campaign-overview template. Thin wrapper around video-spec-generate: sets source=<program_url> and template_id=60s-campaign-overview, then delegates all generation logic there. Owns one artifact: the new program's spec.yaml in Drive.
dimagi-internal/ace
Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates. Use when defining or revising an agent's tool set, action space, or observation format.
oberconcejo/VS-CODE
Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing. Use when planning or executing engineering work that agents will carry out end to end.
oberconcejo/VS-CODE
Generates Angular code and provides architectural guidance. Trigger when creating projects, components, or services, or for best practices on reactivity (signals, linkedSignal, resource), forms, dependency injection, routing, SSR, accessibility (ARIA), animations, styling (component styles, Tailwind CSS), testing, or CLI tooling.
oberconcejo/VS-CODE
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
oberconcejo/VS-CODE
Build a source-derived writing style profile from real posts, essays, launch notes, docs, or site copy, then reuse that profile across content, outreach, and social workflows. Use when the user wants voice consistency without generic AI writing tropes.
oberconcejo/VS-CODE
Try to break a piece of UI by feeding it worst-case data — long names, unbreakable emails, one-letter names, missing fields, huge counts, zero items, long labels, non-Latin text, emoji, extreme numbers — then render it behind a "Demo data / Worst case" toggle and report everything that broke, with the fix for each. Use when the user asks to stress-test, break, or find edge cases in a component or screen, or to "try the worst case". For visual design critique use emil-design-eng; for motion use review-animations.
oberconcejo/VS-CODE