Results for “planning-pipeline”

Agent profile for handle CI/CD, environments, build pipelines, deployment topology, secrets, and operational readiness. Use when Codex needs a specialist agent perspective for planning, implementation, review, debugging, validation, or handoff in this domain.

Configurable pipeline orchestrator for sequencing stages

Designs and implements production-grade ML pipeline infrastructure: configures experiment tracking, creates orchestration DAGs, builds feature store schemas, deploys model registries, and automates retraining and validation workflows.

Fork, sanitize, and package private projects for safe public release through a three-stage pipeline.

Design or repair a CI/CD pipeline with well-ordered parallel stages, lockfile-keyed caching, quality gates, and build-once artifact promotion.

Use when a researcher asks where to start, which project skill fits the current stage of a study, or in what order literature scoping, source access, vault upkeep, drafting, citation verification, disclosure, and review response should run.

Auto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk and runs them sequentially with auto-decisions using 6 decision principles. (gstack)

Designs and implements CI/CD pipelines with automated testing, build automation, deployment, and rollback strategies.

Diseña y optimiza pipelines de CI/CD para GitHub Actions y GitLab CI, incluyendo automatización de tests, linting, builds y deploys.

CI/CD Pipeline Architect

Audits Python + BigQuery pipelines for cost safety, idempotency, and production readiness, returning a structured report with exact patch locations.

Profile a DeepStream pipeline with Nsight Systems and derive its configs from the measurement.

Coordinate multi-stage edge research pipelines from candidate detection through strategy design, review, revision, and export.

Composite skill — safely refactor a module end-to-end with sequencing, parallel implementation, post-refactor cleanup, and rationale capture. Chains refactor-plan (phased plan + rollback) → three-man-team (architect/builder/reviewer in parallel) → fix-the-suite post-refactor → adr-write → docs-sync. Use for non-trivial refactors that need both careful sequencing and durable record.

Revenue operations analyst specializing in pipeline health diagnostics, deal velocity analysis, forecast accuracy, and data-driven sales coaching. Turns CRM data into actionable pipeline intelligence that surfaces risks before they become missed quarters.

ML pipeline design — data versioning, experiment tracking, deployment patterns, drift monitoring. Use when building an ML pipeline from data to deployment, setting up MLOps tooling (DVC, MLflow, model registry), choosing deployment patterns (shadow, canary, A/B), or designing monitoring for drift and degradation.

Use for the search-planning stage of a literature review, when database lanes and language layers must be chosen, when DOI coverage policy is unclear, or when inclusion and exclusion criteria need drafting before any source is read; not for running the screening and PRISMA pipeline of a formal review, which is prisma-scoping-review-pipeline.

Orchestrate the complete post-first-draft polishing pipeline for an academic LaTeX paper by invoking five existing skills in fixed order: (1) paper-polish, (2) paper-self-revise, (3) paper-style, (4) paper-polish again, (5) reference-verify. Trigger when user says "paper pipeline" / "paper-pipeline" / "论文流水线" / "全流程打磨" / "一条龙打磨" / "初稿打磨" / "full polish pipeline" / "run the whole pipeline", or wants the entire post-draft polishing sequence run on a paper folder. Use this skill whenever the user asks for several paper-finishing steps (polish + revise + style + reference check) on one manuscript in one go, even if they don't name every individual skill.

Designs and implements CI/CD pipelines, automating build, test, and deployment processes with security scanning and deployment strategies.

Weekly pipeline health analysis with velocity metrics, stage distribution, forecasting, and actionable recommendations

Detect stack and generate CI/CD pipeline configs. Usage: /pipeline <detect|generate> [options]

CI/CD pipeline setup — GitHub Actions, testing, linting, deployment. Use when setting up CI from scratch, adding GitHub Actions, automating tests, wiring up deployment, or improving an existing build pipeline.

Proposal strategist and pipeline orchestrator — routes multimodal briefs through intake, research, pricing, and generation with guided check-ins or autonomous mode. Use when the user wants to run a full proposal pipeline, start a new proposal, resume an in-progress run, record win/loss outcomes, or get routed to the right proposal workflow. Triggers: 'run a proposal', 'proposal pipeline', 'start a new proposal', 'guided proposal mode', 'autonomous proposal', 'record proposal outcome', 're-price Acme brief', 'where is my proposal', 'proposal orchestrator'.

End-to-end source processing -- seed, reduce, process all claims through reflect/reweave/verify, archive. The full pipeline in one command. Triggers on "/pipeline", "/pipeline [file]", "process this end to end", "full pipeline".

编写、修改、审查 .cnb.yml 流水线配置，诊断构建失败原因并优化性能。

Design, implement, and validate reproducible machine-learning pipelines spanning data preparation, training, evaluation, registry, and deployment gates. Use when the user requests an ML pipeline, needs to turn model scripts into an orchestrated workflow, or provides pipeline components that must be connected safely.

Design and implement CI/CD pipelines and automation — fast checks on every PR, safe releases, and repeatable workflows. Load when setting up GitHub Actions (or similar), adding pre-merge gates, automating releases, or the user asks "add CI", "set up workflows", "automate checks", "CD pipeline". Not for one-off local scripts (use task-specific tooling).

Identifies, assesses, and mitigates risks at every phase of a development pipeline.

Auto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk and runs them sequentially with auto-decisions using 6 decision principles. Surfaces taste decisions (close approaches, borderline scope, codex disagreements) at a final approval gate. One command, fully reviewed plan out. Use when asked to "auto review", "autoplan", "run all reviews", "review this plan automatically", or "make the decisions for me". Proactively suggest when the user has a plan file and wants to run the full review gauntlet without answering 15-30 intermediate questions. (gstack) Voice triggers (speech-to-text aliases): "auto plan", "automatic review".

Pipeline Intelligence

Orchestrates an end-to-end video production pipeline from source footage to a rough cut or final packaged video, with staged gates, resume support, and progress tracking.