aiwg-setup-warp
Setup Warp Terminal with AIWG framework context (preserves existing content)
What this skill does
# AIWG Setup Warp
You are an SDLC Setup Specialist responsible for configuring existing projects to use the AIWG SDLC framework with Warp Terminal.
## Your Task
When invoked with `/aiwg-setup-warp [project-directory]`:
1. **Detect** AIWG installation path
2. **Read** existing project WARP.md (if present)
3. **Preserve** all user-specific notes, rules, and configuration
4. **Add or update** AIWG framework section with orchestration guidance
5. **Aggregate** all SDLC agents and commands into single WARP.md file
6. **Validate** setup is complete
## Important Context
This command is designed for **existing projects** that want to adopt the AIWG SDLC framework with Warp Terminal. For **new projects**, use `aiwg -new` instead.
**Key differences**:
- `aiwg -new`: Creates fresh project scaffold with WARP.md template
- `aiwg-setup-warp`: Updates existing WARP.md while preserving user content
**Warp vs Claude**:
- Claude: Separate `.claude/agents/*.md` files
- Warp: Single `WARP.md` file with aggregated content
- Warp loads WARP.md automatically when terminal opens in project directory
## Execution Steps
### Step 1: Resolve AIWG Installation Path
Detect where AIWG is installed using standard resolution:
```bash
# Priority order:
# 1. Environment variable: $AIWG_ROOT
# 2. User install: ~/.local/share/ai-writing-guide
# 3. System install: /usr/local/share/ai-writing-guide
# 4. Git repo (dev): <current-repo-root>
```
**Implementation**:
```bash
# Try environment variable first
if [ -n "$AIWG_ROOT" ] && [ -d "$AIWG_ROOT/agentic/code/frameworks/sdlc-complete" ]; then
AIWG_PATH="$AIWG_ROOT"
# Try standard user install
elif [ -d "$HOME/.local/share/ai-writing-guide/agentic/code/frameworks/sdlc-complete" ]; then
AIWG_PATH="$HOME/.local/share/ai-writing-guide"
# Try system install
elif [ -d "/usr/local/share/ai-writing-guide/agentic/code/frameworks/sdlc-complete" ]; then
AIWG_PATH="/usr/local/share/ai-writing-guide"
# Fallback: not found
else
echo "❌ Error: AIWG installation not found"
echo ""
echo "Please install AIWG first:"
echo " curl -fsSL https://raw.githubusercontent.com/jmagly/ai-writing-guide/refs/heads/main/tools/install/install.sh | bash"
echo ""
echo "Or set AIWG_ROOT environment variable if installed elsewhere."
exit 1
fi
```
Use Bash tool to resolve the path, then store result.
### Step 2: Check Existing WARP.md
Detect if project already has WARP.md and whether it contains AIWG section:
```bash
PROJECT_DIR="${1:-.}" # Default to current directory
WARP_MD="$PROJECT_DIR/WARP.md"
```
**Three scenarios**:
1. **No WARP.md** → Create from template
2. **WARP.md exists, no AIWG section** → Intelligently merge
3. **WARP.md exists with AIWG section** → Update AIWG section in place
Use Read tool to check file, grep to detect AIWG section.
**Key Difference from Claude**: Warp uses single `WARP.md` file, not `.warp/agents/*.md` subdirectories.
### Step 3: Load AIWG Template
Instead of directly reading a template file, you must **call the setup-warp.mjs script** to generate the aggregated WARP.md content:
```bash
# Call setup script to generate WARP.md content
node "$AIWG_PATH/tools/warp/setup-warp.mjs" \
--target "$PROJECT_DIR" \
--mode sdlc \
--dry-run
```
**Script responsibilities**:
1. Read base AIWG orchestration context
2. Aggregate all 58 agent files → "SDLC Agents" section
3. Aggregate all 42+ command files → "SDLC Commands" section
4. Combine into single WARP.md template with proper formatting
**Template structure** (generated by script):
```markdown
# Project Context
<!-- User content preserved above this line -->
---
## AIWG SDLC Framework
{AIWG orchestration overview}
---
## SDLC Agents (58 Specialized Roles)
### Intake Coordinator
**Tools**: Bash, Read, Write, MultiEdit, WebFetch
**Purpose**: Transform intake forms into validated inception plans...
{agent content aggregated from all .md files}
---
## SDLC Commands (42+ Workflows)
### /intake-wizard
**Purpose**: Generate or complete intake forms interactively
{command content aggregated from all .md files}
---
```
### Step 4: Intelligent Merge Strategy
**Same pattern as aiwg-setup-project**:
```python
# Pseudo-code
# Parse existing WARP.md sections
sections = parse_markdown_sections(existing_warp_md)
# Identify user sections (NOT AIWG-managed)
user_sections = [s for s in sections if not is_aiwg_section(s.heading)]
# Identify AIWG sections (to be replaced)
aiwg_sections = [s for s in sections if is_aiwg_section(s.heading)]
# Merge: user first, then AIWG
merged_content = format_sections(user_sections) + "\n\n---\n\n" + aiwg_template
```
**AIWG-managed section headings**:
- `## AIWG SDLC Framework`
- `## SDLC Agents`
- `## SDLC Commands`
- `## Platform Compatibility`
- `## Core Orchestrator`
- `## Natural Language`
- `## Phase Overview`
**User-managed sections** (preserved):
- `# Project Context` (header)
- `## Tech Stack`
- `## Team Conventions`
- `## Project Rules`
- Any custom `##` headings not matching AIWG patterns
### Step 5: Execute Merge
**CRITICAL**: Call the `setup-warp.mjs` script via Bash tool. This script handles all merge logic.
**Scenario 1: No existing WARP.md**
```bash
node "$AIWG_PATH/tools/warp/setup-warp.mjs" \
--target "$PROJECT_DIR" \
--mode sdlc
```
Script will:
- Generate WARP.md from template
- Aggregate all agents and commands
- Substitute `{AIWG_ROOT}` with actual path
- Create WARP.md in project directory
**Scenario 2: WARP.md exists, no AIWG section**
```bash
node "$AIWG_PATH/tools/warp/setup-warp.mjs" \
--target "$PROJECT_DIR" \
--mode sdlc
```
Script will:
- Read existing WARP.md
- Preserve all user content
- Append AIWG sections with separator
- Add timestamp marker: `<!-- AIWG SDLC Framework (auto-updated) -->`
**Scenario 3: WARP.md exists with AIWG section**
```bash
node "$AIWG_PATH/tools/warp/setup-warp.mjs" \
--target "$PROJECT_DIR" \
--mode sdlc
```
Script will:
- Read existing WARP.md
- Identify and preserve user sections
- Replace AIWG sections with updated content
- Maintain all custom user sections
**Alternative: Dry-run first**
```bash
# Preview changes without writing
node "$AIWG_PATH/tools/warp/setup-warp.mjs" \
--target "$PROJECT_DIR" \
--mode sdlc \
--dry-run
```
### Step 6: Validate Setup
Run validation checks:
```bash
echo ""
echo "======================================================================="
echo "Warp Setup Validation"
echo "======================================================================="
echo ""
# Check 1: AIWG installation accessible
if [ -d "$AIWG_PATH/agentic/code/frameworks/sdlc-complete" ]; then
echo "✓ AIWG installation: $AIWG_PATH"
else
echo "❌ AIWG installation not accessible"
fi
# Check 2: WARP.md updated
if [ -f "$WARP_MD" ]; then
if grep -q "## AIWG" "$WARP_MD"; then
echo "✓ WARP.md has AIWG section"
else
echo "❌ WARP.md missing AIWG section"
fi
else
echo "❌ WARP.md not found"
fi
# Check 3: Agent count
agent_count=$(grep -c "^### " "$WARP_MD" || true)
if [ "$agent_count" -ge 58 ]; then
echo "✓ WARP.md contains $agent_count agents (expected: 58+)"
else
echo "⚠️ Warning: WARP.md contains only $agent_count agents (expected: 58+)"
fi
# Check 4: Command count
command_count=$(grep -c "^### /" "$WARP_MD" || true)
if [ "$command_count" -ge 40 ]; then
echo "✓ WARP.md contains $command_count+ commands (expected: 42+)"
else
echo "⚠️ Warning: WARP.md contains only $command_count commands (expected: 42+)"
fi
# Check 5: Warp compatibility note
if grep -q "Warp Terminal" "$WARP_MD"; then
echo "✓ Warp Terminal compatibility documented"
else
echo "⚠️ Warning: Warp Terminal compatibility not documented"
fi
echo ""
echo "======================================================================="
```
Use Bash tool for validation.
### Step 7: Provide Next Steps
After successful setup, provide clear guidance:
```markdown
# Warp Setup Complete ✓
**Project**: {project-directory}
**AIWG InstallatioRelated 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.