From luca
Inspect recent Claude Code agent activity by querying repo-recall directly. Stateless, no stack. Triggers - /luca-inspect, luca inspect, inspect luca, what's luca seeing, summarize this session, what did I just do, recent sessions, peek at the substrate.
How this skill is triggered — by the user, by Claude, or both
Slash command
/luca:luca-inspectThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Run the LUCA query digest. Stateless. No docker, no Grafana, no local store.
Run the LUCA query digest. Stateless. No docker, no Grafana, no local store.
LUCA exposes the digest via two equivalent paths:
mcporter call luca.query_digest - canonical. LUCA is lazy-loaded through mcporter, so it never shows up as an eager mcp__luca__* tool. Invoke it on demand with mcporter call. Works in any mcporter-aware client (Claude Code, Cursor, Cline).coily exec query-digest - CLI fallback. Use only when mcporter is unavailable, or when the same shell session needs to capture the output.Both call the same run_query() function, so the output is byte-identical.
curl -fsS http://127.0.0.1:7777/api/scan-version >/dev/null 2>&1 || echo "repo-recall down"
If down, suggest brew services start coilysiren/tap/repo-recall and stop.
Via MCP (preferred):
mcporter call luca.query_digest # last 1h (default)
mcporter call luca.query_digest window=1d
mcporter call luca.query_digest window=7d
Via CLI:
coily exec query-digest # last 1h
coily exec query-digest -- --window 1d # last 1d
coily exec query-digest -- --window 7d # last 7d
Print the digest verbatim. If the user asks a follow-up that needs cross-run synthesis (recurring patterns, anomalies, hand-off-to-Kai questions), hand off to the tooling-luca-meta-loop skill.
npx claudepluginhub coilyco-flight-deck/luca --plugin lucaSearches MemPalace before answering questions about past work, people, projects, or prior decisions. Returns verbatim stored content instead of guessing from model memory.
Guides Payload CMS config (payload.config.ts), collections, fields, hooks, access control, APIs. Debugs validation errors, security, relationships, queries, transactions, hook behavior.
Implements vector databases with Pinecone, Weaviate, Qdrant, Milvus, pgvector for semantic search, RAG, recommendations, and similarity systems. Optimizes embeddings, indexing, and hybrid search.