Shared artifact registry, common artifact patterns, and integration validation. Load when tracking data that flows across journey steps or validating horizontal coherence.
npx skills add https://github.com/nWave-ai/nWave --skill nw-shared-artifact-tracking
Shared artifacts are data values appearing in multiple places across a journey. Every ${variable} must have a single source of truth and documented consumers. Untracked artifacts are the primary cause of horizontal integration failures.
shared_artifacts:
{artifact_name}:
source_of_truth: "{canonical file path}"
consumers: ["{list of places this value appears}"]
owner: "{responsible feature/component}"
integration_risk: "HIGH|MEDIUM|LOW - {explanation}"
validation: "{How to verify consistency}"
Source: pyproject.toml | Consumers: CLI --version, about command, README, install output
Risk: HIGH -- version mismatch breaks user trust
Source: config/paths.yaml or constants.py | Consumers: install script, uninstall script, documentation
Risk: HIGH -- path mismatch breaks installation
Source: pyproject.toml or config | Consumers: README, error messages, install docs
Risk: MEDIUM -- URL mismatch breaks external links
Source: config file or environment variable | Consumers: runtime behavior, documentation, defaults display
Risk: MEDIUM -- inconsistency causes confusion
Source: CLI argument parser definition | Consumers: help text, documentation, error messages, tutorials
Risk: HIGH -- name mismatch makes features undiscoverable
Journey completeness: all steps have clear goals | CLI commands/actions | emotional annotations | shared artifacts tracked | integration checkpoints defined
Emotional coherence: emotional arc defined (start/middle/end) | no jarring transitions | confidence builds progressively | error states guide to resolution
Horizontal integration: all shared artifacts have single source of truth | all consumers documented | integration checkpoints validate consistency | CLI vocabulary consistent
CLI UX compliance: command structure follows chosen pattern | help available on all commands | progressive disclosure implemented | error messages actionable
Artifacts: docs/feature/{feature-id}/discuss/journey-{name}.yaml (complete journey with emotional arc) | docs/feature/{feature-id}/discuss/shared-artifacts-registry.md (tracked artifacts with sources)
Validation: journey complete with all steps | emotional arc defined | shared artifacts documented | CLI vocabulary consistent
Deliverables: docs/feature/{feature-id}/discuss/journey-{name}.yaml (journey schema) | docs/feature/{feature-id}/discuss/journey-{name}.feature (Gherkin scenarios) | docs/feature/{feature-id}/discuss/shared-artifacts-registry.md (integration validation points)
Validation: all product-owner checks passed | Gherkin scenarios generated | integration checkpoints testable | peer review approved
Integration with protocols.io API for managing scientific protocols. This skill should be used when working with protocols.io to search, create, update, or publish protocols; manage protocol steps and materials; handle discussions and comments; organize workspaces; upload and manage files; or integrate protocols.io functionality into workflows. Applicable for protocol discovery, collaborative protocol development, experiment tracking, lab protocol management, and scientific documentation.
Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances
Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams. Outputs .excalidraw JSON files that can be opened directly in Excalidraw.
Build and distribute Expo development clients locally or via TestFlight
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.
Benchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for lab data management automation.
Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.
Take nwave-ai/nw-shared-artifact-tracking from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.