Monte Carlo Performance Diagnosis
sickn33/agentic-awesome-skills
Diagnoses pipeline performance issues -- slow jobs, expensive queries, latency trends -- using Monte Carlo's cross-platform observability.
Systematic investigation of metric changes and anomalies. An agent skill from nimrodfisher/data-analytics-skills.
Install Root Cause Investigation
$ npx skills add nimrodfisher/data-analytics-skills --skill root-cause-investigation -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install nimrodfisher/data-analytics-skills root-cause-investigation --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/nimrodfisher/data-analytics-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/03-data-analysis-investigation/root-cause-investigation .claude/skills/root-cause-investigation && rm -rf skills-srcUse ~/.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/
Install the "root-cause-investigation" agent skill from https://github.com/nimrodfisher/data-analytics-skills/tree/main/03-data-analysis-investigation/root-cause-investigation into .claude/skills/root-cause-investigation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "root-cause-investigation", 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 install https://github.com/nimrodfisher/data-analytics-skills/tree/main/03-data-analysis-investigation/root-cause-investigationType 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.
$ npx skills add nimrodfisher/data-analytics-skills --skill root-cause-investigation -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install nimrodfisher/data-analytics-skills root-cause-investigation --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nimrodfisher/data-analytics-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/03-data-analysis-investigation/root-cause-investigation .agents/skills/root-cause-investigation && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "root-cause-investigation" agent skill from https://github.com/nimrodfisher/data-analytics-skills/tree/main/03-data-analysis-investigation/root-cause-investigation into .agents/skills/root-cause-investigation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "root-cause-investigation", 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.
$ npx skills add nimrodfisher/data-analytics-skills --skill root-cause-investigation -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install nimrodfisher/data-analytics-skills root-cause-investigation --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nimrodfisher/data-analytics-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/03-data-analysis-investigation/root-cause-investigation .cursor/skills/root-cause-investigation && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "root-cause-investigation" agent skill from https://github.com/nimrodfisher/data-analytics-skills/tree/main/03-data-analysis-investigation/root-cause-investigation into .cursor/skills/root-cause-investigation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "root-cause-investigation", 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 https://github.com/nimrodfisher/data-analytics-skills.git --path 03-data-analysis-investigation/root-cause-investigation--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add nimrodfisher/data-analytics-skills --skill root-cause-investigation -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install nimrodfisher/data-analytics-skills root-cause-investigation --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nimrodfisher/data-analytics-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/03-data-analysis-investigation/root-cause-investigation .gemini/skills/root-cause-investigation && rm -rf skills-srcUse ~/.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/
Install the "root-cause-investigation" agent skill from https://github.com/nimrodfisher/data-analytics-skills/tree/main/03-data-analysis-investigation/root-cause-investigation into .gemini/skills/root-cause-investigation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "root-cause-investigation", 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.
$ gh skill install nimrodfisher/data-analytics-skills root-cause-investigationInstalls 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).
$ npx skills add nimrodfisher/data-analytics-skills --skill root-cause-investigation -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/nimrodfisher/data-analytics-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/03-data-analysis-investigation/root-cause-investigation .github/skills/root-cause-investigation && rm -rf skills-srcUse ~/.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/
Install the "root-cause-investigation" agent skill from https://github.com/nimrodfisher/data-analytics-skills/tree/main/03-data-analysis-investigation/root-cause-investigation into .github/skills/root-cause-investigation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "root-cause-investigation", 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.
$ npx skills add nimrodfisher/data-analytics-skills --skill root-cause-investigation -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install nimrodfisher/data-analytics-skills root-cause-investigation --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nimrodfisher/data-analytics-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/03-data-analysis-investigation/root-cause-investigation .opencode/skills/root-cause-investigation && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "root-cause-investigation" agent skill from https://github.com/nimrodfisher/data-analytics-skills/tree/main/03-data-analysis-investigation/root-cause-investigation into .opencode/skills/root-cause-investigation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "root-cause-investigation", 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
root-cause-investigation- GitHub stars
- 470
- Token cost
- ~764 tokens
- SKILL.md length
- 363 words
- Files
- 5 (incl. scripts, references, assets)
- Skills in repo
- 31
- Repo updated
- First seen
- Licence
- MIT
At a glance
Systematic investigation of metric changes and anomalies. An agent skill from nimrodfisher/data-analytics-skills.
- Works in 6 steps: Validate the change — confirm the metric… → Establish a timeline — plot the metric… → Decompose the metric — break the metric… → …
- A metric unexpectedly changes
- Runs Python scripts from its folder
- Investigating business metric drops
What it does
Root Cause Investigation is an agent skill from nimrodfisher/data-analytics-skills. Systematic investigation of metric changes and anomalies. Use when a metric unexpectedly changes, investigating business metric drops, explaining performance variations, or drilling into aggregated metric drivers.
Its SKILL.md is about 760 tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including scripts, reference files and assets (for example `assets/rca_report_template.md`, `references/hypothesis_testing_guide.md` and `references/rca_framework.md`).
It sits in Data & Analytics, covering Root cause analysis. The repository describes itself as: A comprehensive list of Claude & Codex skills for a wide range of data analytics tasks. The licence is MIT.
When your agent uses it
- A metric unexpectedly changes
- Investigating business metric drops
- Explaining performance variations
- Drilling into aggregated metric drivers
Example prompts
- “/root-cause-investigation”
Requirements
- Python 3
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Validate the change — confirm the metric changed beyond normal variance using a z-score or simple comparison to the rolling average. If…
- Establish a timeline — plot the metric over time to pinpoint when the change started. A sudden step change suggests a specific event; a…
- Decompose the metric — break the metric into its constituent parts (e.g., revenue = volume × price × mix). Determine which component is…
- Drill down systematically — compare the metric before vs. after the change across available dimensions (geography, platform, channel…
- Test hypotheses — generate explicit hypotheses (volume drop, mix shift, per-unit quality change, data issue) and accept or reject each…
- Write the root cause report — document the primary driver (quantified share of impact), supporting evidence, rejected hypotheses, and…
What it can do on your machine
Read from SKILL.md and the folder at commit 9449d36. 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/ (Python), 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
Root Cause Investigation loads about 764 tokens when it runs, and up to ~2.4k if it reads all its reference files. Until then it costs about 60 tokens; SKILL.md has 363 words of instructions outside code blocks.
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 nimrodfisher/data-analytics-skills at commit 9449d36, republished under its MIT licence (© nimrodfisher). 363 words, ~764 tokens.
Download SKILL.mdSave it as
.claude/skills/root-cause-investigation/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.- name
- root-cause-investigation
- description
- Systematic investigation of metric changes and anomalies. Use when a metric unexpectedly changes, investigating business metric drops, explaining performance variations, or drilling into aggregated metric drivers.
Root Cause Investigation
When to use
- A key metric dropped (or spiked) unexpectedly and the team needs an explanation
- Stakeholders are asking "why did X happen?" and need an evidence-based answer
- A metric change has been observed but the team is unsure whether it's noise or signal
- Preparing a post-mortem after an incident that affected business metrics
- A trend change happened weeks ago and needs retrospective investigation
Process
- Validate the change — confirm the metric changed beyond normal variance using a z-score or simple comparison to the rolling average. If the change is within ±1.5 standard deviations, document it as within normal range and close. Use
scripts/drilldown_analyzer.py --validate. - Establish a timeline — plot the metric over time to pinpoint when the change started. A sudden step change suggests a specific event; a gradual drift suggests a structural shift.
- Decompose the metric — break the metric into its constituent parts (e.g., revenue = volume × price × mix). Determine which component is driving the change before drilling into dimensions.
- Drill down systematically — compare the metric before vs. after the change across available dimensions (geography, platform, channel, product category, user segment). Sort by absolute contribution to identify the primary driver. Use
scripts/drilldown_analyzer.py --drilldown. Seereferences/rca_framework.mdfor the structured approach. - Test hypotheses — generate explicit hypotheses (volume drop, mix shift, per-unit quality change, data issue) and accept or reject each with evidence. Correlate the timeline with known events from
references/hypothesis_testing_guide.md. - Write the root cause report — document the primary driver (quantified share of impact), supporting evidence, rejected hypotheses, and tiered recommendations (immediate / short-term / long-term). Use
assets/rca_report_template.md.
Show full SKILL.md (102 more words)Show less
Inputs the skill needs
- Metric name and historical values (at least 30 days before the change)
- Granular data with dimensional breakdowns (geography, platform, segment, etc.)
- The date or date range when the change was noticed
- A change log or incident log for the same period (product releases, campaigns, outages)
- The business context: what decisions depend on this metric
Output
scripts/drilldown_analyzer.py— validates the change, computes dimensional drill-downs, and ranks contributors by impactreferences/rca_framework.md— structured five-step RCA method with decision rulesreferences/hypothesis_testing_guide.md— checklist of common root causes and how to test eachassets/rca_report_template.md— report template: what changed, when, primary driver, supporting evidence, timeline, recommendations
© nimrodfisher, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 4 other files (scripts, references, assets) in 03-data-analysis-investigation/root-cause-investigation of nimrodfisher/data-analytics-skills.
- SKILL.md
- assets/rca_report_template.md
- references/hypothesis_testing_guide.md
- references/rca_framework.md
- scripts/drilldown_analyzer.py
Open the folder on GitHubat commit 9449d36
Compare with similar skills
Root Cause Investigation 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Root Cause Investigation this skillnimrodfisher/data-analytics-skills | 470 | — | ~764 | Automated safety check: Pass | MIT | |
| Monte Carlo Performance Diagnosissickn33/agentic-awesome-skills | 47k | 1 repos | ~2k | Automated safety check: Pass | Apache-2.0 | |
| Anomaly Investigationgaasher/Agent-Loop-Skills | 174 | — | ~2.1k | Automated safety check: Pass | MIT | |
| Pm Metricsserejaris/personal-corp-os | 229 | — | ~3k | Automated safety check: Pass | MIT | |
| Amazon Opensearch Serviceaws/agent-toolkit-for-aws | 2.8k | — | ~2.4k | Automated safety check: Pass | Apache-2.0 | |
| Data Analysis Standardmohitagw15856/pm-claude-skills | 1.4k | — | ~1.7k | Automated safety check: Pass | MIT |
Similar skills
Anomaly Investigation
gaasher/Agent-Loop-Skills
A skill your agent uses when the user has a known, already-observed anomaly in their data — a metric spike or drop, an outlier, an unexpected number — and wants its root cause diagnosed, not guessed.
Pm Metrics
serejaris/personal-corp-os
Делает ревью продуктовых метрик — тренды, аномалии, root causes и рекомендации к действиям.
- Official
Amazon Opensearch Service
aws/agent-toolkit-for-aws
Guides migration, provisioning, search, log-analytics, trace-analytics, and Agentic AI Assistant workflows for Amazon OpenSearch Service and Serverless across six capabilities — migration…
Data Analysis Standard
mohitagw15856/pm-claude-skills
Structure a product data analysis, metric deep-dive, funnel analysis, or cohort study.
Troubleshooting Dbt Job Errors
Kilo-Org/kilo-marketplace
Diagnoses dbt Cloud/platform job failures by analyzing run logs, querying the Admin API, reviewing git history, and investigating data issues.
More from nimrodfisher/data-analytics-skills
All 31 skills in this repoAb Test Analysis
nimrodfisher/data-analytics-skills
Rigorous A/B test statistical analysis. An agent skill from nimrodfisher/data-analytics-skills.
Analysis Assumptions Log
nimrodfisher/data-analytics-skills
Track and document analytical assumptions and decisions. An agent skill from nimrodfisher/data-analytics-skills.
Analysis QA Checklist
nimrodfisher/data-analytics-skills
Pre-delivery quality assurance for analysis work. An agent skill from nimrodfisher/data-analytics-skills.
Business Metrics Calculator
nimrodfisher/data-analytics-skills
Standard business metric calculation with industry benchmarks.
Cohort Analysis
nimrodfisher/data-analytics-skills
Time-based cohort analysis with retention and behaviour tracking.
Context Packager
nimrodfisher/data-analytics-skills
Efficiently package context for AI-assisted analysis. An agent skill from nimrodfisher/data-analytics-skills.
Related
Categories
Questions about Root Cause Investigation
What does Root Cause Investigation do?
Systematic investigation of metric changes and anomalies. An agent skill from nimrodfisher/data-analytics-skills. Root Cause Investigation is an agent skill from nimrodfisher/data-analytics-skills. Systematic investigation of metric changes and anomalies.
When should I use Root Cause Investigation?
Root Cause Investigation fits situations like: A metric unexpectedly changes; investigating business metric drops; explaining performance variations; drilling into aggregated metric drivers.
How do I install Root Cause Investigation in Claude Code?
Run `npx skills add nimrodfisher/data-analytics-skills --skill root-cause-investigation -a claude-code`. Or copy the skill folder (03-data-analysis-investigation/root-cause-investigation in nimrodfisher/data-analytics-skills) into .claude/skills/root-cause-investigation in your project. Claude Code loads it when a task matches its description.
How do I install Root Cause Investigation in Codex?
Run `npx skills add nimrodfisher/data-analytics-skills --skill root-cause-investigation -a codex`. Or copy the skill folder (03-data-analysis-investigation/root-cause-investigation in nimrodfisher/data-analytics-skills) into .agents/skills/root-cause-investigation in your project. Codex loads it when a task matches its description.
Can I use Root Cause Investigation 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 nimrodfisher/data-analytics-skills --skill root-cause-investigation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/root-cause-investigation, .gemini/skills/root-cause-investigation, .github/skills/root-cause-investigation and .opencode/skills/root-cause-investigation in your project.
What does Root Cause Investigation need to run?
Going by SKILL.md and its folder, Root Cause Investigation needs Python for the scripts in its folder. Our summary lists: Python 3.
Does Root Cause Investigation 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 Root Cause Investigation 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 Root Cause Investigation use?
Root Cause Investigation 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 Root Cause Investigation use?
About 764 tokens (SKILL.md is roughly 3.1k 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 1.6k tokens, read only when the agent opens those files.
What are the alternatives to Root Cause Investigation?
Skills that share tags, products or a category with Root Cause Investigation: Monte Carlo Performance Diagnosis (sickn33/agentic-awesome-skills, 47k stars), Anomaly Investigation (gaasher/Agent-Loop-Skills, 174 stars), Pm Metrics (serejaris/personal-corp-os, 229 stars) and Amazon Opensearch Service (aws/agent-toolkit-for-aws, 2.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Root Cause Investigation?
nimrodfisher (a GitHub user) maintains it in nimrodfisher/data-analytics-skills, which has 470 GitHub stars. The repository holds 31 skills in this directory. The repository was last updated on September 25, 2026.
Source: nimrodfisher/data-analytics-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.