Agent skill

Business Intelligence

Install Business Intelligence

skills CLI

$ npx skills add ericrisco/rsc-harness --skill business-intelligence -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install ericrisco/rsc-harness business-intelligence --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/ericrisco/rsc-harness.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/business-intelligence .claude/skills/business-intelligence && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "business-intelligence" agent skill from https://github.com/ericrisco/rsc-harness/tree/main/skills/business-intelligence into .claude/skills/business-intelligence/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "business-intelligence", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/ericrisco/rsc-harness/tree/main/skills/business-intelligence

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add ericrisco/rsc-harness --skill business-intelligence -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install ericrisco/rsc-harness business-intelligence --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/ericrisco/rsc-harness.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/business-intelligence .agents/skills/business-intelligence && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "business-intelligence" agent skill from https://github.com/ericrisco/rsc-harness/tree/main/skills/business-intelligence into .agents/skills/business-intelligence/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "business-intelligence", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add ericrisco/rsc-harness --skill business-intelligence -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install ericrisco/rsc-harness business-intelligence --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/ericrisco/rsc-harness.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/business-intelligence .cursor/skills/business-intelligence && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "business-intelligence" agent skill from https://github.com/ericrisco/rsc-harness/tree/main/skills/business-intelligence into .cursor/skills/business-intelligence/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "business-intelligence", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/ericrisco/rsc-harness.git --path skills/business-intelligence

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add ericrisco/rsc-harness --skill business-intelligence -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install ericrisco/rsc-harness business-intelligence --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/ericrisco/rsc-harness.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/business-intelligence .gemini/skills/business-intelligence && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "business-intelligence" agent skill from https://github.com/ericrisco/rsc-harness/tree/main/skills/business-intelligence into .gemini/skills/business-intelligence/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "business-intelligence", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install ericrisco/rsc-harness business-intelligence

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add ericrisco/rsc-harness --skill business-intelligence -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/ericrisco/rsc-harness.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/business-intelligence .github/skills/business-intelligence && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "business-intelligence" agent skill from https://github.com/ericrisco/rsc-harness/tree/main/skills/business-intelligence into .github/skills/business-intelligence/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "business-intelligence", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add ericrisco/rsc-harness --skill business-intelligence -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install ericrisco/rsc-harness business-intelligence --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/ericrisco/rsc-harness.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/business-intelligence .opencode/skills/business-intelligence && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "business-intelligence" agent skill from https://github.com/ericrisco/rsc-harness/tree/main/skills/business-intelligence into .opencode/skills/business-intelligence/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "business-intelligence", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: business-intelligence
GitHub stars: 167
Token cost: ~2.5k tokens
SKILL.md length: 1,049 words
Files: 6 (incl. scripts, references)
Skills in repo: 227
Repo updated: Oct 7, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

A metric (revenue
SKILL.md covers The one rule, The four primitives, Decision: do you even need a… and Pick the layer, plus 7 more sections
Runs Shell scripts from its folder
Margin) needs defining once in a governed semantic layer so every dashboard

What it does

Business Intelligence is an agent skill from ericrisco/rsc-harness. Use when a metric (revenue, MRR, margin) needs defining once in a governed semantic layer so every dashboard, report and agent returns the same number, or when an LLM must answer data questions in plain language without hallucinating SQL. NOT chart layout (that is dashboard), NOT which KPIs to track (that is kpi-framework), NOT a hand-written query (that is sql).

Its SKILL.md is about 2.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files, including scripts and reference files (for example `evals/README.md`, `evals/cases.yaml` and `references/authoring-semantic-models.md`).

It sits in Writing & Content, covering OKRs and executive reporting, Plain language and style rules and SQL. It works with SQL. The repository describes itself as: Your agent invents things because it has no memory, and can't touch your database because it has no arms. rsc is the meta-harness that gives it both, plus the trade to know the… The licence is MIT.

When your agent uses it

A metric (revenue
Margin) needs defining once in a governed semantic layer so every dashboard
Report and agent returns the same number
An LLM must answer data questions in plain language without hallucinating SQL

Example prompts

“/business-intelligence”

Requirements

A Bash shell

What it can do on your machine

Read from SKILL.md and the folder at commit e3d5b33. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/ (Shell), which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Business Intelligence loads about 2.5k tokens when it runs, and up to ~4.9k if it reads all its reference files. Until then it costs about 98 tokens; SKILL.md has 1,049 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~98
When it runs · the whole SKILL.md, loaded when a task matches: ~2.5k
With references · SKILL.md plus every file in references/, read only if the agent opens them: ~4.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from ericrisco/rsc-harness at commit e3d5b33, republished under its MIT licence (© ericrisco). 1,049 words, ~2,504 tokens.

Download SKILL.mdSave it as .claude/skills/business-intelligence/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.

name: business-intelligence
description: Use when a metric (revenue, MRR, margin) needs defining once in a governed semantic layer so every dashboard, report and agent returns the same number, or when an LLM must answer data questions in plain language without hallucinating SQL. NOT chart layout (that is `dashboard`), NOT which KPIs to track (that is `kpi-framework`), NOT a hand-written query (that is `sql`).
tags: business-intelligence, semantic-layer, metrics-layer, text-to-sql, natural-language-query, dbt, cube
recommends: sql, dashboard, kpi-framework, reporting, analytics, forecasting, clickhouse-analytics, duckdb
origin: risco

Business intelligence

Answer business questions over the org's data through a governed semantic layer — define each metric once in versioned YAML, then route every "what was revenue last quarter by region" through that layer. Numbers come out consistent, auditable, and the same for everyone. This skill builds the layer and queries it in plain language.

The one rule

Never free-hand SQL against raw tables to answer a governed business question. Go through the layer.

Why, with numbers: in dbt's April 2026 benchmark (ACME Insurance, 11 questions × 20 runs, ~15-table schema), an LLM grounded in a semantic layer scored 98.2% (Claude Sonnet 4.6) / 100% (GPT-5.3 Codex) vs 90.0% / 84.1% for raw text-to-SQL on the same schema; on the unmodeled schema it was 72.7% vs 64.5%, and a 2023 GPT-4 baseline managed 32.7%. The layer is not bureaucracy — it is the accuracy. The model writing SQL against undecorated tables is the failure mode you are eliminating.

Your job is two motions: (1) build the metrics layer (entities, dimensions, measures, metrics) and (2) query it — translate a plain-language question into metric + dimensions + grain + filter, never into a hand-written query.

The four primitives

Every semantic layer (MetricFlow, Cube, warehouse-native) is built from the same four nouns. Learn these and the rest is syntax.

Entities — the join keys. order_id is the primary entity of orders; customer_id is a foreign entity that joins to customers. Entities are how the layer knows how tables relate so it writes the join, not you.
Dimensions — the axes you group and filter by, including time grains (order_date by day/week/month/quarter) and categoricals (region, product_category).
Measures — a single aggregation of a column: sum(amount), count(distinct customer_id).
Metrics — named, reusable expressions built over measures: gross_revenue, mrr, gross_margin_pct. This is what a human or agent actually asks for by name.

yaml

# MetricFlow-style semantic model for an orders table
semantic_models:
  - name: orders
    model: ref('fct_orders')
    entities:
      - name: order        # primary join key
        type: primary
        expr: order_id
      - name: customer     # foreign key -> customers semantic model
        type: foreign
        expr: customer_id
    dimensions:
      - name: order_date
        type: time
        type_params: { time_granularity: day }   # grain is declared, not implied
      - name: region
        type: categorical
    measures:
      - name: order_amount
        agg: sum            # explicit aggregation
        expr: amount

Decision: do you even need a layer?

Do not stand up a semantic layer for a spreadsheet. Branch on consumers and conflict, not on data size alone.

Situation	Build the layer?	Route
One analyst, one table, a 200-row CSV, a one-off question	No	`../sql/SKILL.md` or `../duckdb/SKILL.md`
One metric, queried in one place, never disputed	No	`../sql/SKILL.md`
Many consumers (dashboards + reports + notebooks + an agent)	Yes	this skill
An LLM/agent must answer data questions safely	Yes	this skill
Two teams already report different numbers for the same thing	Yes	this skill

If the answer is "no," stop here and write the query. The layer earns its weight only when a definition has to be shared.

Pick the layer

Pick	When	Why
dbt Semantic Layer / MetricFlow	You already run dbt; want Git-native definitions colocated with models, reviewed in PR/CI	Metrics live in YAML next to dbt models, version-controlled, served over JDBC + GraphQL APIs that apps query; compiles to SQL on Snowflake/BigQuery/Redshift/Databricks
Cube	One definition must feed a BI tool and a product dashboard and an AI copilot	Open-source, one definition exposed over four query APIs (SQL/REST/GraphQL/MDX) plus an AI API / MCP support so agents call governed metrics as tools
Warehouse-native (Snowflake Semantic Views / Databricks Metric Views)	The org is all-in on one warehouse	Semantic objects live inside the warehouse — no separate service to run

MetricFlow was open-sourced (Apache 2.0) at Coalesce 2025 and contributed as an OSI reference implementation, so its YAML is a safe default authoring format regardless of which engine you land on.

Author the model

One definition, version-controlled, reviewed in PR — colocated with the models. Definitions belong in code review, not in a BI tool's UI where they silently fork.

yaml

# A metric defined once over the measure above
metrics:
  - name: gross_revenue
    label: Gross Revenue
    type: simple
    type_params:
      measure: order_amount     # built on the measure, not raw SQL
  - name: gross_margin_pct
    label: Gross Margin %
    type: ratio                 # ratio metric: numerator / denominator
    type_params:
      numerator: gross_profit
      denominator: gross_revenue

text

# Bad -> Good
Bad:  "revenue" SUM(amount) hand-written in Tableau,
      SUM(net_amount) in the Looker view,
      SUM(amount)-refunds in a notebook  -> three different numbers
Good: one `gross_revenue` metric in YAML; Tableau, the notebook,
      and the agent all query that one metric -> one number

For multi-entity join paths, additive vs non-additive vs ratio vs cumulative/derived metrics, semi-additive measures (balances, inventory snapshots), time spines, and the fan-out double-count trap, see references/authoring-semantic-models.md.

Query in plain language

Decompose the question into the four parts before any SQL exists. Never jump to a query.

text

Question: "MRR by plan, monthly, last 2 quarters, EU customers only"
  metric      -> mrr
  group by    -> plan
  time grain  -> month
  date filter -> last 2 quarters
  filter      -> region = 'EU'

You hand the layer that spec; it generates the governed SQL. You then explain the answer back in business terms ("EU MRR grew 8% QoQ, driven by the Pro plan"), not as a table dump.

Show full SKILL.md (393 more words)Show less

Wire the agent

Expose the layer as an MCP / metrics tool. The agent selects governed metrics + dimensions; the layer returns the SQL/results. The agent never sees raw warehouse tables.

text

# Bad -> Good
Bad:  agent gets warehouse credentials, reads the schema,
      writes SELECT ... FROM raw.orders JOIN ...  -> 84-90% accurate, unauditable
Good: agent calls query_metrics(metric="gross_revenue",
      group_by=["region"], grain="month", filters=["region='EU'"])
      -> layer returns governed SQL/result, 98-100% accurate

Guardrails: deny raw-table access, validate that requested dimensions actually exist on the metric, reject any ungoverned aggregate. Full MCP pattern plus dbt SL GraphQL/JDBC and Cube REST/SQL/MCP query shapes are in references/wiring-agents-and-apis.md.

Reconcile conflicting numbers

When sales says revenue is X and finance says Y, it is almost never a query bug — it is two definitions. Do not write a third query to "settle it." Find the two definitions, pick the correct one, encode it once in the layer, and point both teams at it. The disagreement disappears because there is now one number to disagree about.

Portability (OSI)

Author toward the Open Semantic Interchange standard so definitions survive a tool switch. OSI is the vendor-neutral, Apache-2.0, YAML-based spec for datasets/metrics/dimensions/relationships, launched 2025-09-23 by Snowflake + dbt Labs, Cube, Salesforce/Tableau and others; v1.0 spec published on GitHub 2026-01-27. Write MetricFlow/OSI-shaped YAML; never invent a proprietary metric format trapped in one BI tool.

Anti-patterns

Anti-pattern	Why it bites	Instead
Free-handing the SQL "just this once" because it's faster	"Once" becomes the fourth conflicting revenue figure; it's unauditable	Add/query a metric
Letting each dashboard define revenue itself	That is exactly how you get three numbers and a fire drill	One metric, all consumers query it
Skipping the time dimension's grain because it's "obvious"	Undeclared grain → silent daily-vs-monthly mismatches	Declare `time_granularity`/`grain`
Handing the agent warehouse creds to figure out the joins	Raw text-to-SQL is 84-90% (33% in 2023) and unauditable; the dbt 2026 benchmark puts the layer +8-14pts ahead	Expose metrics via MCP/API
Standing up a semantic layer for a 200-row CSV	Pure overhead for one analyst	`../sql/SKILL.md` / `../duckdb/SKILL.md`
Hard-coding the EU filter into the metric	Now you need a second metric for every region	Pass filters at query time

Verify

Run scripts/verify.sh [path] on your semantic-model directory. It is read-only, never touches a warehouse, and discovers candidate YAML, then warns (advisory) on: a metric with no underlying measure, a measure with no declared agg, a time dimension with no grain, duplicate metric names, and a .sql beside the model hand-rolling an aggregate the layer should own. It exits non-zero only on unparseable YAML; an empty or clean target passes clean.

Siblings: ../sql/SKILL.md · ../dashboard/SKILL.md · ../kpi-framework/SKILL.md · ../reporting/SKILL.md · ../analytics/SKILL.md · ../forecasting/SKILL.md

Files

SKILL.md and 5 other files (scripts, references) in skills/business-intelligence of ericrisco/rsc-harness.

SKILL.md
evals/README.md
evals/cases.yaml
references/authoring-semantic-models.md
references/wiring-agents-and-apis.md
scripts/verify.sh

Open the folder on GitHubat commit e3d5b33

Compare with similar skills

Business Intelligence next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Business Intelligence compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Business Intelligence this skillericrisco/rsc-harness	167	—	~2.5k	Automated safety check: Pass	MIT	today
SQL To Business Logicnimrodfisher/data-analytics-skills	465	—	~636	Automated safety check: Pass	MIT	13 days ago
SQL Translatorcriptogus/agent-evolve-network	288	—	~735	Automated safety check: Pass	CC-BY-SA-4.0	28 days ago
Advanced Analytics Dashboardsickn33/agentic-awesome-skills	47k	1 repos	~3.3k	Automated safety check: Pass	MIT	yesterday
Weekly Ops Reportdavila7/claude-code-templates	32k	—	~861	Automated safety check: Pass	MIT	today
SQL Root Cause Analysiszj-unicom-ai/UniEmployee	358	—	~433	Automated safety check: Pass	MIT	today

Similar skills

SQL To Business Logic
nimrodfisher/data-analytics-skills
Translate SQL queries into plain language business logic. An agent skill from nimrodfisher/data-analytics-skills.
465 GitHub stars~636 tokensUpdated 13 days ago
DatabasesAuto-check passed
SQL Translator
criptogus/agent-evolve-network
Translates a plain-English question into a single, safe, read-only SQL query against a known schema, with assumptions made explicit.
288 GitHub stars~735 tokensUpdated 28 days ago
DatabasesAuto-check passed
Advanced Analytics Dashboard
sickn33/agentic-awesome-skills
Dashboard metric register: metric, source module, formula, period, value, target, trend, owner and last-updated, as CSV, SQL, JSON Schema or Notion on request.
47k GitHub starsUsed in 1 repo~3.3k tokens
Business, Finance & HRAuto-check passed
Weekly Ops Report
davila7/claude-code-templates
Turn raw operational data into a weekly management report that answers exactly three questions - what changed, where is it concentrated, what needs a decision.
32k GitHub stars~861 tokensUpdated today
Writing & ContentAuto-check passed
SQL Root Cause Analysis
zj-unicom-ai/UniEmployee
SQL 版归因分析技能。当用户问为什么、指标异常、趋势下滑/增长、KPI 未达标、营收/订单/转化/成本波动时使用. An agent skill from zj-unicom-ai/UniEmployee.
358 GitHub stars~433 tokensUpdated today
DevelopmentAuto-check passed
Lens Metrics
jeremylongshore/tons-of-skills-marketplace
Produce a complete metrics definition doc — metric name, formula, data source, segmentation, SQL or event tracking spec, and what good/bad looks like.
2.8k GitHub stars~2.8k tokensUpdated today
Product & Project ManagementAuto-check: notes

Questions about Business Intelligence

What does Business Intelligence do?

A skill your agent uses when a metric (revenue, MRR, margin) needs defining once in a governed semantic layer so every dashboard, report and agent returns the same number, or when an LLM must answer…. Business Intelligence is an agent skill from ericrisco/rsc-harness. Use when a metric (revenue, MRR, margin) needs defining once in a governed semantic layer so every dashboard, report and agent returns the same number, or when an LLM must answer data questions in plain language without hallucinating SQL.

When should I use Business Intelligence?

Business Intelligence fits situations like: A metric (revenue; margin) needs defining once in a governed semantic layer so every dashboard; report and agent returns the same number; an LLM must answer data questions in plain language without hallucinating SQL.

How do I install Business Intelligence in Claude Code?

Run `npx skills add ericrisco/rsc-harness --skill business-intelligence -a claude-code`. Or copy the skill folder (skills/business-intelligence in ericrisco/rsc-harness) into .claude/skills/business-intelligence in your project. Claude Code loads it when a task matches its description.

How do I install Business Intelligence in Codex?

Run `npx skills add ericrisco/rsc-harness --skill business-intelligence -a codex`. Or copy the skill folder (skills/business-intelligence in ericrisco/rsc-harness) into .agents/skills/business-intelligence in your project. Codex loads it when a task matches its description.

Can I use Business Intelligence in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ericrisco/rsc-harness --skill business-intelligence -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/business-intelligence, .gemini/skills/business-intelligence, .github/skills/business-intelligence and .opencode/skills/business-intelligence in your project.

What does Business Intelligence need to run?

Going by SKILL.md and its folder, Business Intelligence needs a shell for the scripts in its folder. Our summary lists: A Bash shell.

Does Business Intelligence access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Business Intelligence safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Business Intelligence use?

Business Intelligence is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Business Intelligence use?

About 2.5k tokens (SKILL.md is roughly 10k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.4k tokens, read only when the agent opens those files.

What are the alternatives to Business Intelligence?

Skills that share tags, products or a category with Business Intelligence: SQL To Business Logic (nimrodfisher/data-analytics-skills, 465 stars), SQL Translator (criptogus/agent-evolve-network, 288 stars), Advanced Analytics Dashboard (sickn33/agentic-awesome-skills, 47k stars) and Weekly Ops Report (davila7/claude-code-templates, 32k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Business Intelligence?

ericrisco (a GitHub user) maintains it in ericrisco/rsc-harness, which has 167 GitHub stars. The repository holds 227 skills in this directory. The repository was last updated on October 7, 2026.

Source: ericrisco/rsc-harness on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Business Intelligence

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Business intelligence

The one rule

The four primitives

Decision: do you even need a layer?

Pick the layer

Author the model

Query in plain language

Wire the agent

Reconcile conflicting numbers

Portability (OSI)

Anti-patterns

Verify

Files

Compare with similar skills

Similar skills

More from ericrisco/rsc-harness

Related

Questions about Business Intelligence