artifacts-creating-and-managing
Creates and manages project artifacts (research, spikes, analysis, plans) using templated scripts. Use when asked to "create an ADR", "research topic", "spike investigation", "implementation plan", or "create analysis". Provides standardized structure, naming conventions, and helper scripts for artifact organization. Works with .claude/artifacts/ directory, Python scripts, and markdown templates.
What this skill does
# Artifacts: Creating and Managing
## Table of Contents
1. [Quick Start](#quick-start)
2. [Triggers](#triggers)
3. [Purpose](#purpose)
4. [When to Use Artifacts](#when-to-use-artifacts)
5. [Directory Structure](#directory-structure)
6. [File Naming Conventions](#file-naming-conventions)
7. [Core Rules](#core-rules)
8. [Category Definitions](#category-definitions)
9. [Helper Scripts](#helper-scripts)
10. [Integration Pattern](#integration-pattern)
11. [Supporting Files](#supporting-files)
12. [Best Practices](#best-practices)
13. [Red Flags to Avoid](#red-flags-to-avoid)
## Quick Start
See [scripts/create_adr.py](/Users/dawiddutoit/projects/claude/custom-claude/skills/artifacts-creating-and-managing/scripts/create_adr.py) for creating ADRs.
See [scripts/create_research_topic.py](/Users/dawiddutoit/projects/claude/custom-claude/skills/artifacts-creating-and-managing/scripts/create_research_topic.py) for creating research topics.
See [scripts/create_implementation_plan.py](/Users/dawiddutoit/projects/claude/custom-claude/skills/artifacts-creating-and-managing/scripts/create_implementation_plan.py) for creating implementation plans.
## Triggers
Trigger with phrases like:
- "create an ADR"
- "create ADR for [decision]"
- "research [topic]"
- "create research topic"
- "spike investigation on [topic]"
- "create spike for [investigation]"
- "implementation plan for [feature]"
- "create analysis"
- "analyze [subject]"
- "document decision"
- "plan implementation"
## Purpose
Standardizes how artifacts are created and organized within `.claude/artifacts/` directory. Artifacts are temporary work products that support development but don't belong in version control or permanent documentation.
## When to Use This Skill
Use when asked to:
- Document architectural decisions ("create an ADR for event sourcing")
- Research technical topics ("research GraphQL libraries for React")
- Plan feature implementations ("create implementation plan for 2FA")
- Conduct time-boxed investigations ("spike on OAuth2 integration")
- Analyze existing code or architecture ("analyze performance bottlenecks")
Do NOT use when:
- Creating permanent documentation (use `docs/` directory instead)
- Writing source code (use `src/` directory)
- User needs quick inline answers (respond directly in conversation)
## When to Use Artifacts
**Use artifacts when:**
- Conducting research ("research GraphQL libraries")
- Creating spikes ("spike on authentication approaches")
- Writing analysis ("analyze performance bottlenecks")
- Documenting decisions (ADRs)
- Planning implementations
- Capturing session notes
- Recording investigation results
**Don't use artifacts for:**
- Permanent documentation (use `docs/` instead)
- Source code (use `src/` instead)
- Tests (use `tests/` instead)
- Configuration (use config files)
## Directory Structure
```
.claude/artifacts/
├── YYYY-MM-DD/ # Date-based organization
│ ├── research/ # Research topics
│ │ └── topic-name.md
│ ├── spikes/ # Technical spikes
│ │ └── spike-name.md
│ ├── analysis/ # Code/architecture analysis
│ │ └── analysis-name.md
│ ├── plans/ # Implementation plans
│ │ └── plan-name.md
│ ├── sessions/ # Session notes
│ │ └── session-name.md
│ └── adr/ # Architecture Decision Records
│ └── NNN-decision-name.md
└── completed/ # Archived artifacts
└── adr/
└── NNN-decision-name.md
```
## File Naming Conventions
**Research topics:**
```
.claude/artifacts/YYYY-MM-DD/research/topic-name.md
Example: .claude/artifacts/2025-12-24/research/graphql-libraries.md
```
**Spikes:**
```
.claude/artifacts/YYYY-MM-DD/spikes/spike-name.md
Example: .claude/artifacts/2025-12-24/spikes/oauth2-integration.md
```
**Analysis:**
```
.claude/artifacts/YYYY-MM-DD/analysis/analysis-name.md
Example: .claude/artifacts/2025-12-24/analysis/performance-bottlenecks.md
```
**Implementation plans:**
```
.claude/artifacts/YYYY-MM-DD/plans/feature-name-plan.md
Example: .claude/artifacts/2025-12-24/plans/user-authentication-plan.md
```
**ADRs:**
```
.claude/artifacts/YYYY-MM-DD/adr/NNN-decision-title.md
Example: .claude/artifacts/2025-12-24/adr/001-use-event-sourcing.md
```
## Core Rules
1. **Date-based organization** - All artifacts under `YYYY-MM-DD/` directory
2. **Kebab-case names** - Use hyphens, lowercase, no spaces
3. **Category folders** - research/, spikes/, analysis/, plans/, adr/
4. **Markdown format** - All artifacts are .md files
5. **Templated creation** - Use helper scripts for consistency
6. **Completion tracking** - Move to `completed/` when done
## Category Definitions
### Research
**Purpose:** Investigate libraries, tools, or approaches
**Template:** See [templates/research_template.md](/Users/dawiddutoit/projects/claude/custom-claude/skills/artifacts-creating-and-managing/templates/research_template.md)
**Example usage:** "Research GraphQL client libraries for React"
### Spikes
**Purpose:** Time-boxed technical investigation
**Template:** Spike template not yet created (use research template as starting point)
**Example usage:** "Spike on OAuth2 integration with existing auth system"
### Analysis
**Purpose:** Investigate existing code/architecture
**Template:** Analysis template not yet created (use research template as starting point)
**Example usage:** "Analyze performance bottlenecks in API handlers"
### Plans
**Purpose:** Document implementation approach
**Template:** See [templates/implementation_plan_template.md](/Users/dawiddutoit/projects/claude/custom-claude/skills/artifacts-creating-and-managing/templates/implementation_plan_template.md)
**Example usage:** "Plan implementation of two-factor authentication"
### ADRs (Architecture Decision Records)
**Purpose:** Document architectural decisions
**Template:** See [templates/adr_template.md](/Users/dawiddutoit/projects/claude/custom-claude/skills/artifacts-creating-and-managing/templates/adr_template.md)
**Example usage:** "ADR 001: Use Event Sourcing for Audit Trail"
## Helper Scripts
All scripts located in `.claude/skills/artifacts-creating-and-managing/scripts/`:
### create_adr.py
See [scripts/create_adr.py](/Users/dawiddutoit/projects/claude/custom-claude/skills/artifacts-creating-and-managing/scripts/create_adr.py) for full script.
**Required:** --title, --status, --context
**Optional:** --decision, --consequences
### create_research_topic.py
See [scripts/create_research_topic.py](/Users/dawiddutoit/projects/claude/custom-claude/skills/artifacts-creating-and-managing/scripts/create_research_topic.py) for full script.
**Required:** --topic, --objective
**Optional:** --questions (multiple)
### create_spike.py
Note: Spike script not yet created. Use create_research_topic.py as alternative.
### create_analysis.py
Note: Analysis script not yet created. Use create_research_topic.py as alternative.
### create_implementation_plan.py
See [scripts/create_implementation_plan.py](/Users/dawiddutoit/projects/claude/custom-claude/skills/artifacts-creating-and-managing/scripts/create_implementation_plan.py) for full script.
**Required:** --feature, --overview
**Optional:** --steps (multiple), --risks
## Integration Pattern
**Typical workflow:**
1. **Create artifact:** Use helper scripts (see Helper Scripts section)
2. **Work on artifact:**
- Add findings, analysis, or decisions
- Reference code, documentation, or other artifacts
- Update as investigation progresses
3. **Complete artifact:**
- Mark as complete (status: accepted/completed)
- Move to `completed/` if ADR
- Reference in code or documentation
- Archive or delete if temporary
4. **Cross-reference:**
- Link from code comments: `// See: .claude/artifacts/YYYY-MM-DD/research/topic.md`
- Link from documentation: `docs/` references artifacts
- Link between artifacts: Related ADRs reRelated in Writing & Docs
jax-development
IncludedUse this skill when the user is writing, debugging, profiling, refactoring, reviewing, benchmarking, parallelising, exporting, or explaining JAX code, or when they mention JAX, jax.numpy, jit, grad, value_and_grad, vmap, scan, lax, random keys, pytrees, jax.Array, sharding, Mesh, PartitionSpec, NamedSharding, pmap, shard_map, Pallas, XLA, StableHLO, checkify, profiler, or the JAX repo. It helps turn NumPy or PyTorch-style code into pure functional JAX, fix tracer/control-flow/shape/PRNG bugs, remove recompiles and host-device syncs, choose transforms and sharding strategies, inspect jaxpr/lowering/IR, and benchmark compiled code correctly.
nature-article-writer
IncludedDrafts, rewrites, diagnostically critiques, and style-calibrates primary research manuscripts for Nature and Nature Portfolio journals. Use when the user wants a Nature-style title, summary paragraph or abstract, introduction, results, discussion, methods, figure legends, presubmission enquiry, cover letter, reviewer response, or when a scientific draft sounds generic, jargon-heavy, structurally weak, or AI-ish and needs precise, broad-reader-friendly prose without inventing data, analyses, or references. Best for primary research articles and letters rather than reviews or press releases unless explicitly adapting one.
deckrd
IncludedDocument-driven framework that derives requirements, specifications, implementation plans, and executable tasks from goals through structured AI dialogue. Use when user says "write requirements", "create spec", "plan implementation", "derive tasks", "structure this feature", "break down into tasks", or "document this module". Also use for reverse engineering existing code into docs (/deckrd rev). Do NOT use for direct code writing — use /deckrd-coder after tasks are generated. Do NOT use when the user only wants to run or fix existing code without planning.
clinical-decision-support
IncludedGenerate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.
handling-sf-data
IncludedSalesforce data operations with 130-point scoring. Use this skill to create, update, delete, bulk import/export, generate test data, and clean up org records using sf CLI and anonymous Apex. TRIGGER when: user creates test data, performs bulk import/export, uses sf data CLI commands, needs data factory patterns for Apex tests, or needs to seed/clean records in a Salesforce org. DO NOT TRIGGER when: SOQL query writing only (use querying-soql), Apex test execution (use running-apex-tests), or metadata deployment (use deploying-metadata).
accelint-ac-to-playwright
IncludedConvert and validate acceptance criteria for Playwright test automation. Use when user asks to (1) review/evaluate/check if AC are ready for automation, (2) assess if AC can be converted as-is, (3) validate AC quality for Playwright, (4) turn AC into tests, (5) generate tests from acceptance criteria, (6) convert .md bullets or .feature Gherkin files to Playwright specs, (7) create test automation from requirements. Handles both bullet-style markdown and Gherkin syntax with JSON test plan generation and validation.