「pip」の検索結果

Use when creating, editing, reviewing, packaging, or organizing AI-agent skills and deciding whether a skill should be text-only, script-backed, or backed by an ML/specialist pipeline.

日本語の概要は準備中です。原文の説明を表示しています。

Configures Codemagic CI/CD pipelines for Flutter using `codemagic.yaml`. Use when setting up automated Flutter builds on Codemagic, configuring iOS code signing without Fastlane Match, deploying to App Store Connect or Google Play from Codemagic, caching pub dependencies in Codemagic, setting up encrypted environment variable groups, running tests with Codemagic's test dashboard, or choosing between Codemagic and GitHub Actions + Fastlane for a Flutter CI/CD pipeline.

日本語の概要は準備中です。原文の説明を表示しています。

Design multi-stage CI/CD pipelines with approval gates, security checks, and deployment orchestration. Use when architecting deployment workflows, setting up continuous delivery, or implementing GitOps practices.

日本語の概要は準備中です。原文の説明を表示しています。

Build GitLab CI/CD pipelines with multi-stage workflows, caching, and distributed runners for scalable automation. Use when implementing GitLab CI/CD, optimizing pipeline performance, or setting up automated testing and deployment.

日本語の概要は準備中です。原文の説明を表示しています。

Assess pipeline layer state, detect prerequisite blockers, classify audit status, and persist remediation plan

日本語の概要は準備中です。原文の説明を表示しています。

Scoring rubrics for all 5 pipeline layers (Vision, Architecture, IA, BE, FE). Use when auditing specs, running self-checks, or remediating ambiguity gaps.

日本語の概要は準備中です。原文の説明を表示しています。

Decompose validated idea-brief.md into 4–8 per-feature PRDs with screens nested. Use after kta-idea-pipeline. Triggers — write PRD, decompose features, feature breakdown, screen list, MVP scope to PRD, post-idea-validation, per-feature PRD, product requirements document, generate PRDs.

日本語の概要は準備中です。原文の説明を表示しています。

End-to-end Android indie idea workflow — feature-build phase only (no monetization). Phased — discover (if no idea) → generate 2 candidates → refine scope (offline/online, sharing, MVP vs full, core-value features) → risk/reward/tradeoff analysis when scoping down → emit idea brief. Use for greenfield app concepts, new feature ideation, idea discovery, or pre-design discovery before writing a design document. Triggers — new app idea, feature concept, indie dev brainstorm, validate idea, refine idea, what should I build, find an app idea, idea pipeline, I have no idea, help me find an app idea, scope down, MVP scoping, core value features.

日本語の概要は準備中です。原文の説明を表示しています。

Turborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines, dependsOn, caching, remote cache, the "turbo" CLI, --filter, --affected, CI optimization, environment variables, internal packages, monorepo structure/best practices, and boundaries. Use when user: configures tasks/workflows/pipelines, creates packages, sets up monorepo, shares code between apps, runs changed/affected packages, debugs cache, or has apps/packages directories.

日本語の概要は準備中です。原文の説明を表示しています。

Use when working with Circleci — circleCI pipeline and workflow management. Covers pipeline status, workflow analysis, job logs, credit usage monitoring, orb management, and project configuration. Use when checking CI status, investigating build failures, analyzing credit consumption, or managing CircleCI orbs.

日本語の概要は準備中です。原文の説明を表示しています。

Use when working with Bitbucket Deep — bitbucket deep platform management covering repository inventory, Pipelines CI/CD monitoring, pull request analysis, branch permission auditing, deployment environment tracking, and workspace member management. Use when auditing repository configurations, investigating pipeline failures, reviewing branch restrictions, or managing workspace access.

日本語の概要は準備中です。原文の説明を表示しています。

Use when working with Azure Devops — azure DevOps comprehensive management. Covers pipelines, boards, repositories, artifacts, test plans, work item tracking, and release management. Use when checking pipeline status, managing work items, investigating build failures, or auditing Azure DevOps project configurations.

日本語の概要は準備中です。原文の説明を表示しています。

Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g. "get my model's eval score up", "improve this agent/harness", "tune this pipeline", "beat the baseline on this benchmark", "run a search over approaches and keep the best", "do an MLE-bench / Kaggle-style optimization", or any long-horizon "make this artifact better and don't just memorize the dev set" task. Trigger it even when the user doesn't say "Arbor" or "hypothesis tree" but describes repeated experiment-and-evaluate loops, branching exploration of competing ideas, or worries about a dev/test gap. Runs Claude itself as the coordinator with subagent executors in isolated git worktrees; for the standalone `arbor` CLI tool see references/arbor-upstream.md.

日本語の概要は準備中です。原文の説明を表示しています。

Generate read-only MongoDB queries (find) or aggregation pipelines using natural language, with collection schema context and sample documents. Use this skill whenever the user asks to write, create, or generate MongoDB queries, wants to filter/query/aggregate data in MongoDB, asks "how do I query...", needs help with query syntax, or discusses finding/filtering/grouping MongoDB documents. Also use for translating SQL-like requests to MongoDB syntax. Does NOT handle Atlas Search ($search operator), vector/semantic search ($vectorSearch operator), fuzzy matching, autocomplete indexes, or relevance scoring - use search-and-ai for those. Does NOT analyze or optimize existing queries - use mongodb-query-optimizer for that. Does NOT handle aggregation pipelines that involve write operations. Requires MongoDB MCP server.

日本語の概要は準備中です。原文の説明を表示しています。

Set up an isolated Python environment for SageMaker / AWS work, with the right Python version and current boto3. Use this skill whenever Python code will be executed for a SageMaker deployment, training job, or any AWS automation — including when about to run `pip install`, when about to invoke `boto3`, when creating or activating a virtualenv, or when the user asks to "set up the environment". Never use system Python and never `pip install` into it. Always isolate. This skill prevents the most common failure modes: wrong Python version, dependency conflicts, and stale SDKs.

日本語の概要は準備中です。原文の説明を表示しています。

DevSecOps IA — Expert en intégration sécurité dans les pipelines CI/CD (SAST, DAST, SCA, container scanning, compliance automation)

日本語の概要は準備中です。原文の説明を表示しています。

Expert en CRM avancé (HubSpot, Salesforce, pipeline, automation, reporting, contexte DZ, intégrations, data quality)

日本語の概要は準備中です。原文の説明を表示しています。

CRM Specialist IA — Expert en CRM (HubSpot, Salesforce, Supabase CRM, pipelines, automation).

日本語の概要は準備中です。原文の説明を表示しています。

Data Engineer IA — Expert en pipelines de données (ETL, data lakes, dbt, Airflow, streaming). Construit des pipelines fiables, scalables et auditable.

日本語の概要は準備中です。原文の説明を表示しています。

Expert en CI/CD pipeline v2 (GitHub Actions, GitLab CI, Jenkins, ArgoCD, progressive delivery)

日本語の概要は準備中です。原文の説明を表示しています。

Expert en pipelines CI/CD (GitHub Actions, GitLab CI, Jenkins, ArgoCD, progressive delivery)

日本語の概要は準備中です。原文の説明を表示しています。

AI Workflow Automation IA — Expert en automatisation de workflows IA (n8n AI nodes, LangChain, Dify, Flowise, pipelines custom)

日本語の概要は準備中です。原文の説明を表示しています。

GitHub Actions, GitLab CI, Jenkins, and automated deployment pipelines

日本語の概要は準備中です。原文の説明を表示しています。

Complete end-to-end MLOps pipeline orchestration from data preparation through model deployment.

日本語の概要は準備中です。原文の説明を表示しています。