Loading...
Loading...
Found 1,832 Skills
Review or re-review a PR by number in an isolated worktree. Runs the `om-code-review` skill — or, for spec-only design PRs, a specification review — submits approve/request-changes, manages pipeline labels. On changes-requested, the autofix loop (fix/test/validate/re-review until merge-ready) runs on the automation's own PRs or with --autofix; other authors' PRs get review + handoff only. Usage - /om-auto-review-pr <PR-number> [--autofix]
Design or verify automated build, test, quality-gate, release, deployment, and post-deployment checks, including failure evidence and stop or rollback conditions. Do not use it for branch, commit, or tag history, or infer product correctness from a green pipeline alone.
Programmatic GLB/glTF 3D model compression library with a multi-phase pipeline, skinned-model awareness, and custom glTF-Transform transforms. Use when integrating compression into application code, building custom pipelines, or using individual transforms.
Turn a novel into a fully playable game on the selected target platform. Orchestrates the whole adaptation pipeline — requirements intake, gameable deconstruction, concept selection, world and visual design, target-runtime build, and evidence-based QA — for a novel in any language. Use for novel to game, story to game, book to game, adapt this novel into a game, turn this book into a playable prototype, make an interactive story or text adventure from this novel. NovelToGame Main Entry. Convert original novels, split libraries, or oh-story writing projects in any language into games that are based on the original works and fully playable on the target platform. Orchestrate gameable deconstruction, concept selection, game and visual design, target runtime environment construction, and evidence-based quality verification. Suitable for requirements such as novel-to-game conversion, turning a book into a game, adapting a novel into an interactive novel/interactive narrative/text adventure game, etc.
Build repeatable sales processes from prospecting through closing. Master qualification frameworks (BANT/MEDDIC), objection handling, pipeline management, discovery questions, and closing techniques for B2B and B2C sales.
Use when designing or modifying Elasticsearch ingest pipelines, including single-path parsing, branching logic, sub-pipelines, enrichment processors, and robust on_failure handling.
Author and maintain Eve manifest files (.eve/manifest.yaml) for services, environments, pipelines, workflows, and secret interpolation. Use when changing deployment shape or runtime configuration in an Eve-compatible repo.
Autonomous audit-to-fix pipeline — find issues, classify, fix, test, commit
Configure GitLab CI/CD pipelines and runners for automated building, testing, and deployment. Create .gitlab-ci.yml configurations, manage runners, and implement DevOps workflows. Use when working with GitLab repositories or self-hosted GitLab instances.
End-to-end orchestrator that turns findings from ANY input (audit spreadsheet, code/security review, QA report, meeting notes, a pasted list of issues) into an Azure DevOps backlog of linked work items. Drives the six sibling ado-backlog skills in order with safety gates. Trigger whenever the user says "turn this audit/spreadsheet/review/list of issues into ADO work items", "create a backlog from these findings", "file these as ADO tickets/bugs/stories", "import this xlsx/csv into Azure DevOps", "make work items from this report", or hands you a source document and asks for it to land in ADO. This is the headline, one-shot entry point (/ado-backlog:run wraps it). Prefer this over running the sub-skills piecemeal when the user wants the whole pipeline. Not for editing existing items individually — use ado-create-work-items.
Deterministic orchestration graph runtime - declarative DAG pipelines with journal-based crash recovery
Goal-driven conductor for the whole idea-to-published-paper lifecycle. Takes a research idea plus experiments and a target ("submit to NeurIPS 2026", or "help me pick a venue") and runs a goal->plan->execute->verify->reflect loop. It plans the stages, invokes the right lifecycle skills in order (literature-review, write-abstract, preflight-check, simulate-reviewers, and the rest), checkpoints with the author before each stage, and re-verifies the live CFP via parse-cfp rather than trusting a cached profile. Use when a researcher says "take my idea to a submitted paper", "run the whole pipeline", "orchestrate the paper for venue X", "what's the plan from here", or "what's done and what's next". Copilot, not autonomous author. It stops to ask at every stage gate, never fabricates results or citations, and never submits. Trigger words - orchestrate, pipeline, end to end, whole paper, idea to submission.