Update to Ultralayer

{
  "description": "Daily market signal bars for a sector, country, or asset class. Operation is market_signal.",
  "included_files": [],
  "name": "signals",
  "skill_md_contents": "---\nname: signals\ndescription: Daily market signal bars for a sector, country, or asset class. Operation is market_signal.\n---\n\n# Signals\n\n`market_signal` aggregates Wire activity into contiguous daily or multi-day bars. Each bar carries wire-item attention and the net sentiment of entity mentions for one market scope.\n\n| Operation | Role |\n|-----------|------|\n| `market_signal` | Attention and net sentiment bars for one sector, country, or asset class |\n\n---\n\n## When to use\n\n**Use `market_signal` when you need to:**\n- Track how much Wire coverage a market scope receives over time\n- Measure the aggregate direction and magnitude of entity-mention sentiment\n- Backtest attention and sentiment over a historical window\n- Roll daily activity into coarser multi-day bars\n\n**Do not use when you need:**\n- The headlines behind a move → `list_wire`\n- A company dossier or entity-specific sentiment → `retrieve_entity`\n- Ticker-level impact narratives → developments and events\n\n---\n\n## Use cases\n\n**Sector activity** — Read the latest 14 bars of information-technology attention and net sentiment.\n```json\n{\n  \"value\": \"information_technology\"\n}\n```\n\n**Original energy coverage** — Exclude syndication duplicates when measuring energy activity.\n```json\n{\n  \"value\": \"energy\",\n  \"novelty\": [\"new\", \"update\", \"correction\"]\n}\n```\n\n**Historical country signal** — Backtest US coverage over an explicit system-time window.\n```json\n{\n  \"value\": \"us\",\n  \"start_timestamp\": \"2026-07-15T00:00:00Z\",\n  \"end_timestamp\": \"2026-08-01T00:00:00Z\"\n}\n```\n\n**Weekly asset-class bars** — Roll crypto activity into stable 7-day buckets.\n```json\n{\n  \"value\": \"crypto\",\n  \"resolution\": \"7d\",\n  \"start_timestamp\": \"2026-07-01T00:00:00Z\"\n}\n```\n\n---\n\n## What you get back\n\n| Field | Notes |\n|-------|-------|\n| `bars` | Oldest → newest; empty buckets are present, never omitted |\n| `bar` | Exclusive UTC bucket end |\n| `count` | Distinct Wire items about the scope |\n| `sentiment` | Net sum of every entity-mention sentiment on those items; `0` when empty or when no mentions exist |\n| `sentiment_std` | Population standard deviation across those mention sentiments; `null` when there are no mentions |\n| `partial` | `true` when the latest bucket is still in progress |\n| `resolution` | Bucket length used |\n| `methodology_version` | Signal definition version |\n\nFloats are rounded to 2 decimal places. History is capped at 60 days; omitting `start_timestamp` returns the last 14 bars.\n\n---\n\n## Scope values\n\n`value` is a single string; the dimension is inferred:\n\n| Kind | Examples |\n|------|----------|\n| Sector | `information_technology`, `energy`, `financials`, `health_care` |\n| Asset class | `equities`, `fixed_income`, `currencies`, `commodities`, `crypto`, `real_estate` |\n| Country | Lowercase ISO alpha-2, such as `us`, `cn`, or `gb` |\n\n`novelty` defaults to all four classes (`new`, `update`, `duplicate`, `correction`). Narrow it when you want originals/updates only.\n\n---\n\n## Workflow\n\n| User intent | Approach |\n|-------------|----------|\n| “Is tech coverage increasing?” | Call with `value: information_technology`; read `count` over time |\n| “What is the direction of energy sentiment?” | Call with `value: energy`; read the sign and magnitude of `sentiment` |\n| “How has US attention changed?” | Call with `value: us` and an explicit window |\n| “Show weekly crypto activity” | Call with `value: crypto`, `resolution: 7d` |\n\n1. Pick one scope `value` (sector, country, or asset class).\n2. Omit `start_timestamp` for the latest 14 bars, or set an explicit historical window.\n3. Read `count` as coverage and `sentiment` as unnormalized net mention tone; use `sentiment_std` to assess disagreement.\n4. For narrative detail, follow up with Wire using the same scope filters.\n\n---\n\n## Limitations\n\n- One scope value per call — no multi-value baskets in a single request.\n- Daily (or multi-day) bars only — no intraday resolution yet.\n- Sentiment is an unnormalized net sum across entity mentions; magnitude rises with mention volume and should be compared primarily within the same scope over time.\n- `count` is Wire items, not entity mentions, so it cannot be used to derive average mention sentiment.\n- Country codes are free-form two-letter strings; invalid codes may return empty bars rather than a vocabulary error.\n- Max lookback 60 days.\n\n---\n\n## FAQ\n\n**Is `sentiment` an average?** No. It is the net sum of entity-mention sentiments. Positive and negative mentions offset each other; larger absolute values reflect direction plus mention volume.\n\n**Why is `sentiment` 0 on a quiet day?** Empty or mention-less bars use `0` for this sum-type statistic. Check `count` and `sentiment_std` for context.\n\n**What does `bar` mean?** Exclusive bucket end in UTC. A `1d` bar ending `2026-08-11T00:00:00Z` covers `[2026-08-10, 2026-08-11)`.\n\n**Can I pass a company name?** No — use sectors, asset classes, or country codes. For a company, use Wire or `retrieve_entity`.\n\n**How do I backtest?** Set `start_timestamp` / `end_timestamp` (system timestamps). `end_timestamp: null` means realtime.\n"
}