Claude Skills by tools-only

Update all skill documentation and other docs with new ID format examples.

Used by /flow-next:prime to scan for CI/CD, PR templates, issue templates, and workflow automation. Do not invoke directly.

Used by /flow-next:prime to scan for CI/CD, PR templates, issue templates, and workflow automation. Do not invoke directly.

Eight pillars for comprehensive codebase assessment. Pillars 1-5 measure **agent readiness** (fixes offered). Pillars 6-8 measure **production readiness** (reported only). ---

DAIV uses SWE AI agents to automate various development workflows in your GitLab and GitHub repositories. Each agent is designed for specific tasks and can work independently or collaborate with other agents to provide comprehensive development assistance. ---

DAIV uses SWE AI agents to automate various development workflows in your GitLab and GitHub repositories. Each agent is designed for specific tasks and can work independently or collaborate with other agents to provide comprehensive development assistance. ---

Slash commands provide command-based interactions with DAIV directly from issues and merge/pull requests. They are useful for common tasks and information requests. ---

Initialize the Conductor environment in a new project - creates conductor/ directory structure

Configure ShellCheck for a project with configuration file, pre-commit hooks, and CI integration.

To install `notte` locally, run the following commands: ```sh uv sync --dev --all-extras uv run pre-commit install ``` `notte` uses `patchright` to automate browser interactions. If you haven't already, you'll need to install the browsers you want to use, e.g. using chromium: ```sh uv run patchright install --with-deps chromium ``` Copy the `.env.example` file to `.env` and fill in your API keys. Note that by default, `notte` uses `groq/llama-3.3-70b-versatile`. So you need to set the `GROQ_A...

You are a senior Security Reviewer with 10+ years of experience in cybersecurity, application security testing, and compliance validation. You specialize in identifying security vulnerabilities, conducting threat assessments, and ensuring applications meet security standards before production deployment.

In Strands, building a system with multiple agents or complex tool chains can be approached in several ways. The three primary patterns you'll encounter are Graph, Swarm, and Workflow. While they all aim to solve complex problems, they have differences in their structures, execution workflows, and use cases. To best help you decide which one is best for your problem, we will discuss them from core concepts, commonalities, and differences.

The `InteractionsEvaluator` is designed for evaluating interactions between agents or components in multi-agent systems or complex workflows. It assesses each interaction step-by-step, considering dependencies, message flow, and the overall sequence of interactions.

This document defines the standard operating procedures for managing Strands Agents Lambda layers across all AWS regions, Python versions, and architectures.

Constrain how and when tools are executed.

This reference provides regex patterns and search strategies for detecting secrets in repositories.

> Audit date: 2026-02-02 > Audited by: Claude Opus 4.5 > Sample size: 10 skills out of 65 total > Reference standard: CLAUDE.md project instructions (Skill Authorship Standards) ---

> Conducted: 2026-02-02 > Scope: Workflow commands, command docs, guides, YAML definitions, and cross-references > Method: Full read of all files in scope, cross-referencing YAML definitions against docs ---

Automate release notes generation from commits/PRs. Use conventional commits or PR labels to categorize changes.

Unique Molecular Identifiers (UMIs) are random sequences added to molecules before PCR amplification. They enable distinguishing PCR duplicates from biological duplicates, crucial for accurate quantification in RNA-seq, targeted sequencing, and single-cell applications.

CNVkit is the standard tool for detecting copy number variants from targeted sequencing (exome, gene panels). It uses both on-target and off-target reads to infer copy number across the genome.

End-to-end workflow for biomarker discovery combining feature selection, model training with nested cross-validation, interpretation, and validation. Produces a validated biomarker panel with an accompanying classifier.

End-to-end workflow for label-free proteomics analysis from MaxQuant/DIA-NN output to differential protein abundance.

This workflow processes ATAC-seq data from raw FASTQ files to accessibility peaks, with optional differential analysis and transcription factor footprinting.

This guide covers creating reproducible Jupyter notebooks with parameterization for automated analysis pipelines.

This workflow processes single-cell RNA-seq data from 10X Genomics Cell Ranger output to annotated cell types. It supports both Seurat (R) and Scanpy (Python) implementations.

Structural variants (SVs) are genomic alterations typically >50bp that include deletions, insertions, inversions, duplications, and translocations. Short-read SV calling uses paired-end and split-read information to detect these events.

Complete gene regulatory network inference workflow from processed single-cell data to regulon discovery and perturbation simulation. Supports RNA-only analysis with pySCENIC (GRNBoost2 + RcisTarget + AUCell) and multiome analysis with SCENIC+ for enhancer-driven GRNs. Includes CellOracle for in silico perturbation simulation.

Basecalling converts raw Nanopore signal data (FAST5/POD5) to nucleotide sequences. Dorado is the current production basecaller and should be used for all new analyses. Guppy is deprecated and no longer receiving updates.

GATK provides a robust, best-practices CNV calling workflow. It uses principal component analysis to denoise samples against a panel of normals and integrates allelic information for improved accuracy.

Polishing improves assembly accuracy by using additional sequencing data to correct errors. Essential for long-read assemblies which have higher raw error rates.

Complete time-course expression analysis workflow from expression matrix to temporal patterns and pathway enrichment. Covers temporal differential expression (limma splines or DESeq2 LRT), Mfuzz soft clustering of expression profiles, optional circadian rhythm detection with MetaCycle or CosinorPy, GAM trajectory fitting with mgcv, and per-cluster pathway enrichment with clusterProfiler. Supports both R and Python alternatives at each step.

Complete environmental DNA metabarcoding workflow from raw amplicon sequences to biodiversity assessment and community ecology. Supports two processing paths: OBITools3 (CLI-based, optimized for eDNA) and DADA2 (R-based, ASV resolution). Includes contamination filtering with decontam, Hill number diversity analysis with iNEXT, and constrained ordination with vegan for community comparison. Handles all common eDNA markers (COI, 12S, ITS, rbcL, 18S).

This workflow takes you from raw DNA sequencing FASTQ files to a filtered set of variant calls (SNPs and indels). It covers the entire process from quality control through alignment and variant calling.

The MCP Context Provider now includes comprehensive build automation to ensure code quality, consistent releases, and streamlined development workflows.

| Pattern | When to Use | | ------------------------ | ------------------------------------------------- | | `AutomationCondition` | Modern asset-centric automation with conditions | | `ScheduleDefinition` | Fixed time intervals (daily, hourly, monthly) | | `@dg.schedule` decorator | Custom schedule logic with dynamic job selection | | `@dg.sensor` | Event-driven triggers (file changes, API updates) | | `PartitionsD

You are helping a developer prototype a new Dagster implementation following best practices. The implementation requirements and working directory have been provided: $ARGUMENTS

Start Manus-style file-based planning. Creates task_plan.md, findings.md, progress.md for complex tasks.

<!-- ============================================================ [CUSTOMIZE] This is a template. Fill in your workflow details. ============================================================ --> > **Vision**: [CUSTOMIZE: One-sentence description of workflow goal] > **Last updated**: [Date] (Iteration 0) > **Status**: Not started

This document explains our compliance status with OSSF Scorecard checks and documents any accepted risks or false positives.

This document explains our compliance status with OSSF Scorecard checks and documents any accepted risks or false positives.

This guide explains how to set up the automated AI PR review system using OpenRouter to analyze pull requests with your choice of AI model.

Releases are now **fully automated** when PRs are merged to the `main` branch.

This repository enforces that all pull requests must be linked to an issue that has an assignee. PRs that don't meet this requirement are automatically closed.

*Balancing automation with human oversight for safe, effective AI systems* --- Human-in-the-Loop (HITL) is a critical design pattern for AI agents. It ensures that humans remain in control of important decisions while still benefiting from AI automation. This guide covers everything you need to know about implementing HITL in agent systems. ---

> English version: [README.md](README.md) <p align="center"> <a href="https://github.com/japan1988/multi-agent-mediation/stargazers"> <img src="https://img.shields.io/github/stars/japan1988/multi-agent-mediation?style=social" alt="GitHub Stars"> </a> <a href="https://github.com/japan1988/multi-agent-mediation/issues"> <img src="https://img.shields.io/github/issues/japan1988/multi-agent-mediation?style=flat-square" alt="Open Issues"> </a> <a href="./LICENSE"> <img src="https://img.shields.io/b...

> English: [README.md](README.md) <p align="center"> <a href="https://github.com/japan1988/multi-agent-mediation/stargazers"> <img src="https://img.shields.io/github/stars/japan1988/multi-agent-mediation?style=social" alt="GitHub Stars"> </a> <a href="https://github.com/japan1988/multi-agent-mediation/issues"> <img src="https://img.shields.io/github/issues/japan1988/multi-agent-mediation?style=flat-square" alt="Open Issues"> </a> <a href="./LICENSE"> <img src="https://img.shields.io/badge/lic...

> English version: [README.md](README.md) <p align="center"> <a href="https://github.com/japan1988/multi-agent-mediation/stargazers"> <img src="https://img.shields.io/github/stars/japan1988/multi-agent-mediation?style=social" alt="GitHub Stars"> </a> <a href="https://github.com/japan1988/multi-agent-mediation/issues"> <img src="https://img.shields.io/github/issues/japan1988/multi-agent-mediation?style=flat-square" alt="Open Issues"> </a> <a href="./LICENSE"> <img src="https://img.shields.io/b...

（fail-closed + HITL） <p align="center"> <a href="https://github.com/japan1988/multi-agent-mediation/stargazers"> <img src="https://img.shields.io/github/stars/japan1988/multi-agent-mediation?style=social" alt="GitHub Stars"> </a> <a href="https://github.com/japan1988/multi-agent-mediation/issues"> <img src="https://img.shields.io/github/issues/japan1988/multi-agent-mediation?style=flat-square" alt="Open Issues"> </a> <a href="./LICENSE"> <img src="https://img.shields.io/badge/license-Apache--...

（fail-closed + HITL） <p align="center"> <a href="https://github.com/japan1988/multi-agent-mediation/stargazers"> <img src="https://img.shields.io/github/stars/japan1988/multi-agent-mediation?style=social" alt="GitHub Stars"> </a> <a href="https://github.com/japan1988/multi-agent-mediation/issues"> <img src="https://img.shields.io/github/issues/japan1988/multi-agent-mediation?style=flat-square" alt="Open Issues"> </a> <a href="./LICENSE"> <img src="https://img.shields.io/badge/license-Apache--...