plugins/d-nd-core/skills/self-setup/SKILL.md
First-run setup for D-ND plugin. Maps the local environment, detects capabilities, configures node identity. Run once after installation or when environment changes.
npx skillsauth add grazianoguiducci/d-nd-seed self-setupInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Run this after installing the d-nd-core plugin to configure it for your environment.
.env.d-nd with discovered settingsecho "=== D-ND Node Discovery ==="
echo "Hostname: $(hostname)"
echo "User: $(whoami)"
echo "OS: $(uname -s 2>/dev/null || echo 'Windows')"
echo "CWD: $(pwd)"
echo ""
# Detect repos
echo "## Detected Repositories"
for dir in */; do
if [ -d "$dir/.git" ]; then
commit=$(git -C "$dir" rev-parse --short HEAD 2>/dev/null)
branch=$(git -C "$dir" branch --show-current 2>/dev/null)
echo " $dir — $branch @ $commit"
fi
done
echo ""
# Detect capabilities
echo "## Capabilities"
command -v ssh >/dev/null 2>&1 && echo " SSH: available" || echo " SSH: not available"
command -v docker >/dev/null 2>&1 && echo " Docker: available" || echo " Docker: not available"
command -v node >/dev/null 2>&1 && echo " Node.js: $(node --version 2>/dev/null)" || echo " Node.js: not available"
command -v python3 >/dev/null 2>&1 && echo " Python: $(python3 --version 2>/dev/null)" || echo " Python: not available"
command -v git >/dev/null 2>&1 && echo " Git: $(git --version 2>/dev/null)" || echo " Git: not available"
echo ""
# Test API connectivity (if configured)
if [ -n "$DND_VPS_IP" ]; then
echo "## API Connectivity"
curl -s --max-time 3 "http://${DND_VPS_IP}:${DND_VPS_PORT:-3002}/api/status" \
-H "X-Auth-Token: ${DND_API_TOKEN}" >/dev/null 2>&1 \
&& echo " API: reachable" || echo " API: unreachable"
fi
Based on discovery results, set these environment variables in your shell profile or .env.d-nd:
# D-ND Node Configuration
export DND_NODE_ID="MY_NODE" # Your node identifier
export DND_PROJECT_DIR="/path/to" # Base project directory
export DND_VPS_IP="" # Server IP (if applicable)
export DND_VPS_PORT="3002" # API port (if applicable)
export DND_API_TOKEN="" # API auth token (if applicable)
Run /d-nd-core:system-check to verify everything works.
Nodes are identified by their capabilities, not by fixed names:
| Capability | Description | |-----------|-------------| | Full access | SSH, Docker, all repos, deploy | | Development | Code editor, local repos, test environment | | Satellite | Autonomous project, receives seed updates | | Specialized | Specific domain (design, finance, research) |
The operator assigns the role. The system adapts.
$ARGUMENTS
testing
Closure reflection protocol. After a significant work block concludes (feature shipped, session ending, major commit landed, cross-node coordination resolved), runs a 10-question interview that extracts meaning, impact, and next questions — then emits multiple audience-specific artifacts (changelog, external editorial, AI integration docs, memory crystal, backlog seed). Turns implicit maturation into explicit narrative. Use at the end of meaningful work, not after trivial edits.
testing
The neutral form of the D-ND method. Meta-skill that recognizes context and orients toward the right specialization (cec, autologica, cascade, assertion-verifier, etc.). Activate at the start of a non-trivial work block or when input matches trigger words ('where are we', 'what here', 'orchestrate', 'connect', 'sieve this').
development
Five mechanical gates for any content publish pipeline with CMS + rendering layers. Prevents false security: 'API returned 200' does not mean 'visitor sees clean content'. Use when writing content to a multi-layer serving system (CMS API, static files, prerendered HTML, cached copies).
testing
Multi-node consultation protocol for high-leverage decisions. Dispatches the same question to N independent LLM/agent nodes in isolation, then synthesizes their responses into a summa that exposes convergence (high-confidence claims), dissensus (real uncertainty zones), and emergent points (insights no single node produced). Reduces single-node training bias. Supports recursive escalation for stable-state convergence. Use for decisions that propagate via A14 cascade — seed updates, crystallizations, advisory→mechanical promotions, high-visibility copy, lab result interpretation.