← Hive AxylCONTENT HISTORY

Update to Hive Axyl

Snapshot Oct 24, 2026 · 13:42 UTC · version 2.1.0

Collection source: downloaded plugin package.

WHAT CHANGED

First saved snapshot

No earlier snapshot is available to establish a change.

Save Hive Axyl and check future changes in Following.

Up to 10 plugins free · no card required.

Compare saved observations

Download comparison JSON
Full technical diff · 0 changed fields
Full snapshot data
{
  "description": "Breaks Hive Analytics metrics down by dimensions through preview_chart and ranks users through preview_chart_rank.\nThis is read-only contributor analysis, not defining or saving a user segment. Follow axyl-analytics-common first.\n\nTRIGGER when:\n- The user asks to break down any metric by OS, country, market, product, or another confirmed dimension\n- The user asks which segments contributed to an already identified metric spike or drop\n- The user asks for a list of whale users or top-paying users\n\nDO NOT TRIGGER when:\n- The request asks whether a change is anomalous or scans metrics for anomalies → use axyl-detect-anomaly\n- The request is a simple metric figure lookup → use axyl-analytics-common (preview_chart)\n- The request investigates one specific user's activity, purchases, or logins → use axyl-inspect-user\n- The request is to create and save a segment or take a snapshot → axyl-create-segment\n- The request is development work unrelated to analytics\n",
  "included_files": [
    {
      "relative_path": "references/dimension_breakdown.md",
      "size_in_bytes": 6157
    },
    {
      "relative_path": "references/user_ranking.md",
      "size_in_bytes": 5093
    }
  ],
  "name": "axyl-drill-down-metrics",
  "skill_md_contents": "---\nname: axyl-drill-down-metrics\nmetadata:\n  version: \"1.0.0\"\ndescription: |\n  Breaks Hive Analytics metrics down by dimensions through preview_chart and ranks users through preview_chart_rank.\n  This is read-only contributor analysis, not defining or saving a user segment. Follow axyl-analytics-common first.\n\n  TRIGGER when:\n  - The user asks to break down any metric by OS, country, market, product, or another confirmed dimension\n  - The user asks which segments contributed to an already identified metric spike or drop\n  - The user asks for a list of whale users or top-paying users\n\n  DO NOT TRIGGER when:\n  - The request asks whether a change is anomalous or scans metrics for anomalies → use axyl-detect-anomaly\n  - The request is a simple metric figure lookup → use axyl-analytics-common (preview_chart)\n  - The request investigates one specific user's activity, purchases, or logins → use axyl-inspect-user\n  - The request is to create and save a segment or take a snapshot → axyl-create-segment\n  - The request is development work unrelated to analytics\n---\n\n# axyl-drill-down-metrics\n\n> **CRITICAL — Always review the common rules in [axyl-analytics-common](../axyl-analytics-common/SKILL.md) first.**\n> **CRITICAL — Use only project_id and company_cd values confirmed through PROJECT_ID_GATE.**\n> **CRITICAL — Use only org_idx and workspace_idx values confirmed through ORG_WORKSPACE_GATE (required for every preview_chart and preview_chart_rank call).**\n> **CRITICAL — Always read the relevant `references/` document before calling each analysis pattern.**\n\n---\n\n## Analysis Patterns\n\n### Segment breakdown\n- [Dimension breakdown](references/dimension_breakdown.md) — use `preview_chart` with `dimensions` to break down by OS, country, market, and so on. Applies to any metric, not just DAU and revenue\n- [User ranking](references/user_ranking.md) — use `preview_chart_rank` to aggregate and rank by userId. Ranking works with any metric, including payment amount and login count\n- **Tool contracts:** [preview_chart](../axyl-analytics-common/references/preview_chart.md) / [preview_chart_rank](../axyl-analytics-common/references/preview_chart_rank.md)\n\n---\n\n## Workflow\n\n### Prerequisite — Review the common rules\n\nPROJECT_ID_GATE, ORG_WORKSPACE_GATE, SCHEMA_FIRST, and NO_GUESSING from axyl-analytics-common apply. EXISTING_ASSET_FIRST\ndoes not apply; Step 1-0 matches the company definition through metric mode. But when the user names a saved chart or dashboard, follow the named-asset rule under EXISTING_ASSET_FIRST in [Query preparation](../axyl-analytics-common/references/query_preparation.md) (its filters and a named dashboard's global filters are kept); for a named dashboard, use its global period as the query period unless the user gave one.\nIf project_id and company_cd have not been confirmed, perform PROJECT_ID_GATE first; if org_idx and workspace_idx have\nnot been confirmed, perform ORG_WORKSPACE_GATE first.\n\n### Phase 1 — Verify the schema (SCHEMA_FIRST)\n\n```\nStep 1-0. Call list_metrics(company_cd)\n  → if the metric to break down (DAU, revenue, ...) is registered, use metric mode in preview_chart\n    so the numbers match the company's definition and the console; a revenue metric also needs currency\n  → only when it is not registered, build the measure in event mode with Steps 1-1 and 1-2\n  → either way, confirm the breakdown dimension with Step 1-2 (list_dimensions); for a registered metric, the event\n    is the text of the {type:\"event\"} token in its metric_config (read it only — do not put tokens into event_measures)\n  → user rankings (preview_chart_rank by userId) may use event mode directly\n\nStep 1-1. Call list_events(company_cd)\n  → confirm the event name and event_idx to use\n  → can be skipped if the event name has already been confirmed\n\nStep 1-2. Call list_dimensions(company_cd, event_name)\n  → confirm the dimension name, dimension_idx, is_price, and is_currency to use\n  → note the name and idx to use in dimensions or adhoc_filters\n  → can be skipped if the dimension information has already been confirmed\n\nStep 1-3. ORG_WORKSPACE_GATE (check_analytics_admin → list_organizations → list_projects(company_cd, org_idx) →\n          list_workspaces; steps already done by PROJECT_ID_GATE are reused)\n  → obtain the org_idx/workspace_idx that preview_chart and preview_chart_rank require\n  → can be skipped if the values have already been confirmed\n```\n\n### Phase 2 — Segment breakdown\n\n```\nStep 2-1. DAU breakdown     → preview_chart (dimensions=[{idx: <dimension_idx>, name: \"os\"|\"country\"|...}])\nStep 2-2. Revenue breakdown → preview_chart (dimensions=[{idx: <dimension_idx>, name: \"country\"|\"productName\"|...}], with currency specified)\nStep 2-3. User ranking      → preview_chart_rank\n  (dimensions=[{idx: <dimension_idx>, name: \"userId\"}], set rank_limit/rank_order/rank_tie_mode/rank_group_mode)\n```\n\n> **Principle for presenting results:** Do not declare a cause from a single dimension breakdown.\n> Express it as \"the segment with the largest impact + the hypothesis to check.\"\n\n### Phase 3 — Decide whether to hand off an individual-user investigation\n\n```\nStep 3. If the ranking result requires investigating one user's activity, purchases, or logins\n  └─ pass the selected user_id and confirmed project scope to axyl-inspect-user.\n  └─ Do not query individual-user history in this skill.\n```\n\nThe full drill-down chain:\n```\nlist_metrics → list_events → list_dimensions (verify the schema) → (ORG_WORKSPACE_GATE)\n  └─ preview_chart (dimension breakdown)        ← Phase 2\n       └─ preview_chart_rank (user ranking)     ← Phase 2\n            └─ decide whether to hand off to axyl-inspect-user ← Phase 3\n```\n\n---\n\n## Prohibited Behavior ❌\n\n| Situation | Prohibited behavior | Correct behavior |\n|------|----------|-----------|\n| project_id unconfirmed | Running the drill-down right away | Perform PROJECT_ID_GATE, then retry |\n| org_idx/workspace_idx unconfirmed | Calling preview_chart or preview_chart_rank with an arbitrary value (for example, 0) | Perform ORG_WORKSPACE_GATE, then retry |\n| Specific-user investigation needed | Querying individual history in this skill | Pass the selected user_id and project scope to axyl-inspect-user |\n| Dimension unclear | Guessing and passing it | Confirm with `list_dimensions`, then pass it |\n| Displaying revenue | Showing only the number | Always display the currency basis alongside; when its event has no `is_currency=1` dimension, state that the amounts are not converted instead |\n| Single dimension breakdown result | Declaring \"the cause is X\" | Express it as \"the segment with the largest impact is X, and the hypothesis to check is Y\" |\n\n---\n\n## Exception Handling\n\n| Situation | Response |\n|------|------|\n| Dimension name error | Select the correct dimension_name from the list_dimensions result, then retry |\n| Empty user ranking result | Explain that no user generated that metric in that period. Suggest widening the date range |\n| Organization or workspace authorization denial | Do not retry the same call unchanged or with a guessed identifier; follow MCP_ACCESS_GATE (denied call with `org_idx`) |\n| Not connected to the Hive Axyl MCP server (first install, never signed in), or the sign-in session expired | Apply MCP_CONNECTION_GATE in axyl-analytics-common. Cannot retry without user action |\n"
}

SHA-256 of public snapshot: 3dac04cafb446ba5c077869b0b7fe915d026afd7663ce42c6695910c2ab9b996