DevOps & Infra

kunanonj Skill

Comprehensive Cloudflare platform skill covering Workers, Pages, storage (KV, D1, R2), AI (Workers AI, Vectorize, Agents SDK), feature flags (Flagship), networking (Tunnel, Spectrum), security (WAF, DDoS), and infrastructure-as-code (Terraform, Pulumi). Use for any Cloudflare development task. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

kunanonj Skill

Build sandboxed applications for secure code execution. Load when building AI code execution, code interpreters, CI/CD systems, interactive dev environments, or executing untrusted code. Covers Sandbox SDK lifecycle, commands, files, code interpreter, and preview URLs. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

kunanonj Skill

When building applications on Cloudflare Workers or with frameworks that deploy to Cloudflare Workers, strongly prefer retrieval and fetching documentation over training data.

kunanonj Skill

Operate Railway infrastructure: sign up for or sign in to a Railway account, create projects, provision services and databases, manage object storage buckets, deploy code, configure environments and variables, manage domains, troubleshoot failures, check status and metrics, set up Railway agent tooling, and query Railway docs. Use this skill whenever the user mentions Railway, signing up, creating

kunanonj Skill

> Use when the user wants to provision infrastructure or third-party services using Stripe Projects. Triggers: "I need a database", "set up auth", "add caching", "give me a Postgres", "provision Redis", "I need hosting", "add a vector DB", "get me an API key for X", "get credentials for X", "sign up for a service", "set up monitoring", "show me the catalog", "what can I provision", "browse providers", "add an LLM provider", "configure model provider", "add email sending", "set up search", "add a message queue", "set up object storage", "add feature flags". Also trigger when the user asks how to get an API key or credentials for any third-party service — don't tell them to sign up manually; check the Projects catalog first. Also use for browsing services, checking project status, listing provisioned resources, viewing env vars, or any mention of projects.dev or adding/provisioning/connecting a cloud service.

kunanonj Skill

Use only when the user explicitly types `/orchestrate <goal>` to decompose a large task, spawn a tree of parallel cloud-agent workers/subplanners/verifiers via the Cursor SDK, and collect structured handoffs; do not invoke autonomously.

fridrichmethod Bundle

Frames the phasing/imputation pipeline before any tool runs: phasing and imputation are one Li-Stephens copying HMM (recombination is the transition, mutation the emission, the genetic map and Ne set the rates), imputation's honest output is a dosage with a self-estimated quality (INFO/R2/DR2) not a hard genotype, and the stages are ordered and each fails silently (QC, align build and strand to the panel, phase, impute per chromosome, filter by INFO/R2 plus a MAF floor, carry dosages to GWAS). Covers the strategy fork (array vs low-coverage WGS plus genotype-likelihood imputation), why the panel ancestry is the prior, and why a flipped strand or build mismatch destroys accuracy without an error. Use when deciding a genotyping strategy, sequencing the pipeline, choosing array vs low-coverage WGS, or diagnosing silently-wrong imputation. Mechanics route to reference-panels, haplotype-phasing, genotype-imputation, imputation-qc; read-backed phasing is long-read-sequencing/haplotype-phasing.

fridrichmethod Bundle

Out-of-core DataFrame for billion-row data via lazy evaluation and memory-mapped files. Use when data exceeds RAM (10 GB–TB) for fast aggregation, filtering, virtual columns, and visualization without loading. Supports HDF5, Arrow, Parquet, CSV with cloud (S3, GCS, Azure). Built-in ML transformers (scaling, PCA, K-means). In-memory: polars; distributed: dask.

fridrichmethod Bundle

Fast in-memory DataFrame with lazy evaluation, parallel execution, Arrow backend. Use for tabular data in RAM (1–100 GB) when pandas is too slow. Expression API: select, filter, group_by, joins, pivots, window. Lazy mode enables predicate/projection pushdown. Reads CSV, Parquet, JSON, Excel, DBs, cloud. Larger-than-RAM: Dask; GPU: cuDF.

fridrichmethod Bundle

Pipeline maestro

fridrichmethod Bundle

End-to-end alternative splicing analysis from FASTQ to differential splicing results. Aligns with STAR 2-pass mode, performs junction QC, runs rMATS-turbo for differential analysis, and generates sashimi visualizations. Use when performing comprehensive splicing analysis from raw RNA-seq data.

fridrichmethod Bundle

Proposal-first scientific writing pipeline, installed under the compatibility trigger researchwrite and the repository package name nature-proposal-writer. Use for composing, revising, or auditing research proposals, opening reports, research plans, and evidence-grounded scientific writing. Three modes (compose/revise/hybrid) with a four-layer QA pipeline. Enforces evidence-before-prose, argument-before-sections, and contracts-before-paragraphs.

fridrichmethod Bundle

Access AlphaFold DB's 200M+ predicted structures by UniProt ID. Download PDB/mmCIF, analyze pLDDT/PAE, bulk-fetch proteomes via Google Cloud. For experimental structures use PDB; for prediction use ColabFold or ESMFold.

dingxingdi Bundle

Use this skill when the user wants code-agent data for realistic end-to-end data engineering, analytics, or ELT (Extract, Load, Transform) tasks spanning infrastructure configurations, multiple tools, and intermediate files. Trigger it for requests like 'create a full ELT workflow from Postgres to Snowflake', 'generate DBT-style models', 'make multi-step analytics tasks', 'set up Airbyte and Terraform pipelines', or 'chain SQL and Python across a complex project'. Do not use for single-query SQL authoring.

ashutoshsrivastava17 Skill

Design, build, and debug data pipelines for ETL/ELT, data ingestion, transformation, and orchestration. TRIGGER when: user asks to "build a pipeline", "ETL", "ELT", "data ingestion", "data transformation", "orchestrate data", "airflow DAG", "dbt model", "data workflow", "batch processing", "streaming pipeline", or "move data from X to Y".

ashutoshsrivastava17 Skill

Validate ETL/ELT pipelines end-to-end: source-to-target mapping verification, row count reconciliation, data type validation, transformation logic testing, and regression testing. Produce a validation report with pass/fail status per check. TRIGGER when: user says /etl-validation, "validate ETL", "test pipeline", "data pipeline validation", "source to target testing", or "ETL reconciliation".

ashutoshsrivastava17 Skill

Design, review, or troubleshoot CI/CD pipelines for mobile apps — build automation, code signing, test automation, artifact distribution, and release management across Flutter, Android, and iOS. Covers Fastlane, Codemagic, Bitrise, and GitHub Actions. TRIGGER when: user says /mobile-ci-cd, asks about mobile build automation, needs to set up code signing in CI, or wants to automate mobile app releases.

ashutoshsrivastava17 Skill

Analyze deals in the sales pipeline using MEDDPICC/BANT qualification frameworks, risk assessment, win probability scoring, and recommended next steps to advance or disqualify opportunities. TRIGGER when: user says /deal-analysis, "analyze this deal", "deal review", "qualify this opportunity", "score this deal", "deal health check", "should we pursue this", or "what's the win probability".

ashutoshsrivastava17 Skill

Build sales forecasts using pipeline analysis, historical win rates, weighted probability scoring, and scenario modeling for revenue projections. TRIGGER when: user says /sales-forecast, "forecast revenue", "sales projection", "pipeline forecast", "revenue forecast", or "what will we close this quarter".

ashutoshsrivastava17 Skill

Design, review, or troubleshoot CI/CD pipelines — build stages, test automation, deployment strategies (blue-green, canary, rolling), rollback procedures, and security scanning. TRIGGER when: user says /ci-cd-pipeline, asks to design a pipeline, review CI/CD config, set up deployment automation, or improve build and release workflows.

ashutoshsrivastava17 Skill

Review sales pipeline health with stage distribution analysis, velocity metrics, conversion rates, stuck deal identification, forecast accuracy tracking, and actionable recommendations for pipeline improvement. TRIGGER when: user says /pipeline-review, "review pipeline", "pipeline health", "pipeline analysis", "how's the pipeline", "forecast review", "pipeline check", "deal flow review", or "pipeline report".

ashutoshsrivastava17 Skill

Review cloud security posture — IAM, network controls, encryption, logging, compliance, and misconfiguration detection. TRIGGER when: user says /cloud-security or asks about cloud security assessment.

ashutoshsrivastava17 Skill

Review and optimize cloud infrastructure costs — resource utilization analysis, right-sizing, reserved capacity, spot/preemptible usage, and savings recommendations. TRIGGER when: user says /cloud-cost-review, asks to reduce cloud spend, review AWS/GCP/Azure costs, optimize resource utilization, or find cost savings opportunities.

ashutoshsrivastava17 Skill

Prepare partner Quarterly Business Reviews with joint metrics, pipeline contribution, integration health, and relationship assessment. Structure for bilateral executive review with actionable outcomes. TRIGGER when: user says /partner-qbr, "partner QBR", "partner review", "partner quarterly review", "alliance review", "partnership review", or "partner business review".

ashutoshsrivastava17 Skill

Design container strategies — image optimization, orchestration selection, security scanning, registry management, and resource limits. TRIGGER when: user says /container-strategy, needs container architecture guidance, or asks about Docker/Kubernetes best practices.

ashutoshsrivastava17 Skill

Analyze spending patterns, identify cost reduction opportunities, and build optimization plans across operational, cloud, vendor, and headcount costs. TRIGGER when: user says /cost-optimization, "reduce costs", "cut spending", "optimize budget", "cost savings", or "where can we save money".

ashutoshsrivastava17 Skill

Design and evaluate RAG (Retrieval-Augmented Generation) pipelines — define retrieval strategies, chunking approaches, embedding selection, reranking, evaluation metrics, and optimization techniques. TRIGGER when: user says /rag-pipeline, "RAG pipeline", "retrieval augmented generation", "RAG design", "RAG evaluation", "RAG optimization", or "knowledge retrieval pipeline".

ashutoshsrivastava17 Skill

Design deployment strategies — blue-green, canary, rolling, feature flags, with rollback procedures and validation gates. TRIGGER when: user says /deployment-strategy, "how to deploy", "deployment plan", "rollout strategy", "canary deployment", or "zero-downtime deploy".

ashutoshsrivastava17 Skill

Automate reporting workflows with data source mapping, transformation logic, scheduling, distribution channels, error handling, and long-term maintenance plans for reliable recurring reports. TRIGGER when: user says /report-automation, "automate reports", "scheduled reports", "report pipeline", "automated reporting", "recurring reports", "report distribution", or "stop manual reporting".

sethdford Skill

Optimize infrastructure and operational costs without sacrificing performance or reliability. Use when managing cloud budgets or improving unit economics.

sethdford Skill

GitHub Actions, GitLab CI, Jenkins; stages, artifacts, caching, and deployment automation.

sethdford Skill

Define merge strategies (squash, rebase, merge commits) that balance history clarity with practical workflow. Use when setting CI/CD merge policies.

sethdford Skill

Design batch and streaming data pipelines. Plan ingestion, transformation, quality checks, and failure recovery. Use when building ETL/ELT systems or data infrastructure.

sethdford Skill

Terraform, CloudFormation, reproducible infrastructure, version control, and IaC best practices.

sethdford Skill

Configure and deploy Static Application Security Testing (SAST) tools to find vulnerabilities in source code during development.

sethdford Skill

Plan tooling investments that multiply team productivity (CI/CD, linters, debuggers, profilers, test frameworks). Use in roadmapping or when choosing development tools.