neural-data-platform

On-demand vision alignment check. Spawns ndp-vision-guardian to review SPARC artifacts against product/vision/ALIGNMENT-CRITERIA.md.

Validate planning swarm output: artifact existence, AC coverage, pattern IDs, stale references, internal consistency. Produces a glass box report.

NDP 4-tier implementation validation. Tier 1: compilation (build+test+anti-stub). Tier 2: process adherence. Tier 3: spec compliance. Tier 4: risk classification. Produces glass box reports.

Retrieve APPLICATION patterns (architecture, procedures, conventions) from AgentDB using multi-signal retrieval: pattern search, causal recall, and RL predictions. Use BEFORE implementing to ensure consistency.

AgentDB pattern lifecycle management: list, get, delete, deprecate, update, stats, search, duplicates. Use when cleaning up stale patterns, removing deprecated entries, finding duplicates, or auditing pattern health. Workaround for missing MCP delete/update tools (GH Issue #42).

Record feedback on pattern effectiveness. Stores episodes that train the recommendation system, feed the RL engine for smarter pattern ranking, build causal knowledge, and enable pattern discovery via learner.

Store APPLICATION patterns (architecture, procedures, conventions) in AgentDB's patterns table. NOT for swarm/transient memory.

Auto-discover patterns from reflexion episodes. Run post-feature to consolidate successful approaches into reusable patterns.

Record human judgment on validation results. Approve confirms accuracy; reject identifies false negatives. Stores calibration data in AgentDB.

Render per-check Bayesian trust scores from AgentDB reflexion entries. Read-only -- no side effects.

Compile an IMPLEMENTATION-BRIEF.md into claude-flow memory chunks and store ADRs in AgentDB. Agents get a Level-1 summary with objective, ADR pattern IDs, and scope — pull details on-demand.

Launch a real working swarm: claude-flow coordination layer + Claude Code agent runtime. Wires MCP state tracking to actual Task-tool agents.

NDP-specific GitHub workflow using Trunk-Based Development (TBD). Commit directly to main with conventional commits. Use this skill for ALL git operations in the Neural Data Platform project.