llm-config
Configure RuVLLM local inference with model selection, MicroLoRA fine-tuning, and SONA adaptation
⌘ K
Newest skills
503 skills
chat-format
Format prompts for different LLM providers with chat templates and HNSW-powered context retrieval
vector-setup
First-run setup for ruvector@0.2.25 — installs ONNX/Brain/SONA add-ons, registers the MCP server, and verifies the install via `doctor`
memory-bridge
Bridge Claude Code auto-memory into AgentDB with ONNX embeddings, deduplicate, and enable unified cross-project search
validate-plugin
Validate a Claude Code plugin structure, frontmatter, and MCP tool references
create-plugin
Scaffold a new Claude Code plugin with proper directory structure, plugin.json, skills, commands, and agents
observe-trace
Trace agent execution by collecting spans and building a trace tree for a task
trader-cloud-backtest
Run a heavy neural-trader job (long walk-forward, big Monte-Carlo, parameter sweep, model training) on the Anthropic Managed Agent cloud runtime instead of locally
music-generate
Generate a new song from a creative brief (genre, mood, language, BPM, theme) via the cogmusic MCP create_production tool
music-connect
One-time setup — mint a Cognitum Music personal access token and register the cogmusic MCP server with Claude Code
harness-similarity
ADR-152 — weighted similarity between two harness fingerprints (genome + score JSON). Returns overall score in [0,1] plus per-component breakdown (cosine over 9 numerics, categorical agreement over 4 enums, jaccard over agent_topology). Unblocks ADR-151 §3.2 Recommender, §3.3 Drift Detection, §3.5 Plugin Compat. Pure-TS, no `@metaharness/*` dep — preserves ADR-150's four architectural constraints.
harness-mint
Scaffold a custom AI agent harness via `metaharness new <name> --template <id> --host <id>`. Defaults to DRY-RUN (no writes) unless --confirm is passed. Refuses to write to the calling repo root or anywhere inside it. Honors ADR-150 architectural constraint + ruflo's "destructive-action confirmation" pattern.
harness-mcp-scan
Static security scan of a harness's declared MCP surface via `harness mcp-scan <path>`. Reads `.mcp/servers.json` + `.harness/claims.json`. Pure-read, no dispatch. Exits 1 on findings at or above `--fail-on` severity.
harness-gepa
Inspect and audit GEPA genomes via the `@metaharness/darwin/gepa` library entry (darwin 0.8.0) — load/validate a genome (default is the shipped cand-6 promotion), render the system prompt a genome compiles to, or classify failure modes in a run transcript. The `gepaOptimize` loop itself is library-only (bring your own evaluator) and not surfaced here — use `harness-evolve` for sandbox-scored evolution. Degrades gracefully when @metaharness/darwin is absent.
harness-genome
7-section repo readiness report from `metaharness genome <path>`. Returns repo_type / agent_topology / risk_score / mcp_surface / test_confidence / publish_readiness. Pure-read; degrades gracefully (ADR-150).
federation-status
Show federation health — peers, sessions, trust levels, and message metrics. Use when the user asks "is federation healthy?", "show peers", "federation status", or wants to inspect cross-installation agent connectivity.
cognitive-pattern
Define and manage cognitive patterns for agent reasoning and decision-making
cost-trend
Read every docs/benchmarks/runs/*.json and surface drift in win rate, latency, escalation rate, and LLM-baseline cost over time
cost-track
Auto-capture per-session token usage from the Claude Code session jsonl and persist to the cost-tracking namespace
cost-booster-route
Route tasks through hooks_route, partition by Agent Booster availability, and report Tier 1 bypass utilization with $0 cost