Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Model business performance, define KPIs, and turn data into decision-ready dashboards, briefings, and operating cadences for teams and executives.
Model business performance, define KPIs, and turn data into decision-ready dashboards, briefings, and operating cadences for teams and executives.
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
On first use, read setup.md for integration behavior and memory initialization.
Use this skill when the user needs to build or improve business intelligence systems: KPI definitions, metric architecture, dashboard planning, executive reporting, and decision review loops. This skill is optimized for operators, founders, product leaders, finance leaders, and analysts who need clear answers to "what changed, why it changed, and what to do next".
Working memory lives in ~/business-intelligence/. See memory-template.md for base structure and status behavior. ~/business-intelligence/ ├── memory.md # HOT: goals, KPI ownership, active decisions ├── metric-tree/ # WARM: objective -> driver -> metric maps ├── kpi-contracts/ # WARM: metric definitions and formula versions ├── dashboard-specs/ # WARM: visualization and drill-down specifications ├── insight-briefs/ # WARM: weekly and monthly decision briefs ├── operating-cadence/ # WARM: review rituals and escalation rules └── archive/ # COLD: retired KPIs and past planning cycles
Load only the file needed for the current task to keep context focused. TopicFileSetup and integrationsetup.mdMemory schemamemory-template.mdObjective and metric tree designmetric-tree.mdKPI definition contractskpi-dictionary.mdDashboard and drill-down designdashboard-specs.mdDecision brief templatesinsight-briefs.mdReview rituals and escalation rulesdecision-cadence.mdSource quality and data contractsdata-contracts.md
Every BI request must begin with one decision question and one owner. If there is no decision owner, the output is reporting noise and should be reframed before building metrics.
Map each business objective to drivers, then drivers to measurable KPIs. Do not build dashboards first. Dashboards without a metric tree create disconnected charts and contradictory narratives.
Each KPI needs a written contract: definition, formula, grain, source, refresh cadence, owner, and valid interpretation window. Never compare KPI values across periods if formula version or source logic changed without annotation.
For every lagging KPI, define at least one leading indicator that signals future movement. If the system only tracks lagging outcomes, intervention happens too late.
Every insight output must include: What changed Why it changed Confidence level Recommended action Action owner and due date A BI summary without an action owner is incomplete.
Use consistent metric naming, time windows, segment logic, color semantics, and drill-down paths. Inconsistent dashboard specs make cross-team comparisons invalid.
Define daily, weekly, monthly, and quarterly BI rituals with clear participants and escalation triggers. Without a fixed cadence, KPI review becomes reactive and decision quality degrades.
Starting with visualization tooling before KPI contracts -> expensive dashboards with weak decisions. Tracking too many KPIs per objective -> teams lose focus on actual drivers. Blending forecast assumptions with actuals in one number -> executives make false confidence calls. Changing formulas without version notes -> historical trend comparisons become invalid. Reporting movement without attribution depth -> teams cannot identify correct interventions. Sending BI updates without action owners -> insights do not convert into execution.
This skill makes NO external network requests. EndpointData SentPurposeNoneNoneN/A No data is sent externally.
Data that leaves your machine: Nothing by default. Data that stays local: BI context, KPI contracts, and reporting notes under ~/business-intelligence/. Decision cadence and retrospective notes stored locally when memory is enabled. This skill does NOT: Access files outside ~/business-intelligence/ for memory storage. Transmit metrics or business data to third-party APIs by default. Create background automations without explicit user confirmation. Modify its own skill definition files.
Install with clawhub install <slug> if user confirms: analytics - analysis workflows for interpreting performance patterns. data-analysis - analysis workflows for modeling trends, segments, and causal signals. dashboard - dashboard implementation for KPI visualization layers. strategy - strategic planning frameworks tied to business outcomes. report - structured report generation for stakeholder communication.
If useful: clawhub star business-intelligence Stay updated: clawhub sync
Data access, storage, extraction, analysis, reporting, and insight generation.
Largest current source with strong distribution and engagement signals.