Review PR
apache/shardingsphere
Review Apache ShardingSphere or user-authorized downstream pull requests and PR discussions from public or authorized repository evidence.
A workflow for conducting rigorous, reproducible data investigations and ad-hoc analyses.
Install Data Investigation
$ npx skills add Kilo-Org/kilo-marketplace --skill data-investigation -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Kilo-Org/kilo-marketplace data-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/Kilo-Org/kilo-marketplace.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/data-investigation .claude/skills/data-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 "data-investigation" agent skill from https://github.com/Kilo-Org/kilo-marketplace/tree/main/skills/data-investigation into .claude/skills/data-investigation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "data-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/Kilo-Org/kilo-marketplace/tree/main/skills/data-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 Kilo-Org/kilo-marketplace --skill data-investigation -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Kilo-Org/kilo-marketplace data-investigation --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Kilo-Org/kilo-marketplace.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/data-investigation .agents/skills/data-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 "data-investigation" agent skill from https://github.com/Kilo-Org/kilo-marketplace/tree/main/skills/data-investigation into .agents/skills/data-investigation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "data-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 Kilo-Org/kilo-marketplace --skill data-investigation -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Kilo-Org/kilo-marketplace data-investigation --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Kilo-Org/kilo-marketplace.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/data-investigation .cursor/skills/data-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 "data-investigation" agent skill from https://github.com/Kilo-Org/kilo-marketplace/tree/main/skills/data-investigation into .cursor/skills/data-investigation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "data-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/Kilo-Org/kilo-marketplace.git --path skills/data-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 Kilo-Org/kilo-marketplace --skill data-investigation -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Kilo-Org/kilo-marketplace data-investigation --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Kilo-Org/kilo-marketplace.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/data-investigation .gemini/skills/data-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 "data-investigation" agent skill from https://github.com/Kilo-Org/kilo-marketplace/tree/main/skills/data-investigation into .gemini/skills/data-investigation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "data-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 Kilo-Org/kilo-marketplace data-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 Kilo-Org/kilo-marketplace --skill data-investigation -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Kilo-Org/kilo-marketplace.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/data-investigation .github/skills/data-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 "data-investigation" agent skill from https://github.com/Kilo-Org/kilo-marketplace/tree/main/skills/data-investigation into .github/skills/data-investigation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "data-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 Kilo-Org/kilo-marketplace --skill data-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 Kilo-Org/kilo-marketplace data-investigation --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Kilo-Org/kilo-marketplace.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/data-investigation .opencode/skills/data-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 "data-investigation" agent skill from https://github.com/Kilo-Org/kilo-marketplace/tree/main/skills/data-investigation into .opencode/skills/data-investigation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "data-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
data-investigation- GitHub stars
- 190
- Token cost
- ~1.5k tokens
- SKILL.md length
- 660 words
- Files
- 1
- Skills in repo
- 85
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
A workflow for conducting rigorous, reproducible data investigations and ad-hoc analyses.
- Works in 5 steps: Frame Before Querying → Build Queries In Escalating Specificity → SQL Hygiene Rules → …
- Tasks that involve Root cause analysis
- SKILL.md covers Purpose, Phase 1: Frame Before Querying, Phase 2: Build Queries In… and Phase 3: SQL Hygiene Rules, plus 4 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Data Investigation is an agent skill from Kilo-Org/kilo-marketplace. A workflow for conducting rigorous, reproducible data investigations and ad-hoc analyses. This skill should be used when investigating a business question, explaining a metric anomaly, validating a hypothesis, performing root cause analysis, or preparing a one-off investigation dashboard or memo.
Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Development, covering Root cause analysis. It works with SQL. The repository describes itself as: Kilo Marketplace - A curated collection of Skills, MCP Servers, and Modes for enhancing AI agent capabilities across the Kilo ecosystem—including Kilo Code (VS Code extension)… The licence is Apache-2.0.
When your agent uses it
- Tasks that involve Root cause analysis
Example prompts
- “/data-investigation”
Workflow steps
5 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit ff51758. 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
No scripts in the folder and no shell commands in SKILL.md (its code samples are sql).
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
github.com
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
Data Investigation loads about 1.5k tokens when it runs. Until then it costs about 79 tokens; SKILL.md has 660 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); files beside SKILL.md are not scanned.
SKILL.md
The full file from Kilo-Org/kilo-marketplace at commit ff51758, republished under its Apache-2.0 licence (© Kilo-Org). 660 words, ~1,480 tokens.
Download SKILL.mdSave it as
.claude/skills/data-investigation/SKILL.md (or your agent's skills folder).- name
- data-investigation
- description
- A workflow for conducting rigorous, reproducible data investigations and ad-hoc analyses. This skill should be used when investigating a business question, explaining a metric anomaly, validating a hypothesis, performing root cause analysis, or preparing a one-off investigation dashboard or memo.
- metadata.category
- data
- metadata.author
- Pedro / Kilo Code
Data Investigation
Use this skill to produce investigations that are fast, correct, reproducible, and communicate a clear conclusion rather than a pile of charts.
Purpose
Every investigation should be answerable in one sentence before the first SQL query is written.
Phase 1: Frame Before Querying
1. Write the one-sentence answer first
Before writing any SQL, write the sentence the conclusion is expected to be.
Example: The cohort size gap is a definition problem rather than a product behavior problem.
If the sentence cannot be written, the question is not yet understood.
2. Classify the investigation type
| Type | Trigger | Approach |
|---|---|---|
| Gap analysis | Why do A and B not match? | Establish the gap, localize it, explain it |
| Root cause | Why did this metric change? | Confirm real, isolate segment, align timing, validate mechanism |
| Hypothesis test | Is X causing Y? | Define what must be true, test sub-claims, confirm or reject |
| Feasibility check | Is this number trustworthy? | Check grain, joins, nulls, definition overlap |
3. State 2-3 competing hypotheses before querying
Never investigate with a single hypothesis. That creates confirmation bias.
Order hypotheses by plausibility and note which one is currently expected to be correct and why.
Phase 2: Build Queries In Escalating Specificity
1. Establish first, explain second
Step 1 always confirms the anomaly is real and measures its magnitude. Do not jump to cause until the effect is confirmed.
select
<time_bucket>,
<source_a_count> as metric_a,
<source_b_count> as metric_b,
<source_a_count> - <source_b_count> as gap,
round(100.0 * (<source_a_count> - <source_b_count>) / nullif(<source_a_count>, 0), 1) as pct_gap
from ...
order by 12. Localize by breaking one dimension at a time
After confirming the gap, break it down along one dimension per step:
- By time: when did it appear?
- By segment: who is affected?
- By signal/source: which path is missing?
3. Align timing with upstream changes
Once the anomaly start date is known, check:
- git commits to relevant models, ETL jobs, or application code
- schema migrations or source changes
- metric definition changes
- external events such as launches, campaigns, or pricing changes
A credible root cause must explain why the metric changed when it did.
4. Validate the mechanism
After identifying a candidate cause, confirm it mechanically:
- Does the affected population match the predicted population?
- What does the counterfactual look like?
- Does a second independent signal support the explanation?
Do not stop at correlation.
5. Quantify each hypothesis before concluding
For every candidate explanation, produce a number.
Examples:
H1 accounts for 1,240 usersH2 accounts for 1,050 users
If a hypothesis cannot be quantified, it is not yet validated.
Phase 3: SQL Hygiene Rules
Show full SKILL.md (264 more words)Show less
Use stable time bounds for investigations
Investigation SQL should be reproducible. Favor fixed bounds over rolling windows unless the analysis is intentionally operational and evergreen.
-- Prefer fixed investigation scope
where created_at >= '2026-02-16'
and created_at < '2026-04-04'Add explicit grain comments in important CTEs
-- grain: one row per user
with users as (
...
)Prefer named comparison outputs over raw aggregates
Bad:
select count(*) from ...Better:
select
count(*) as users_in_scope,
count(distinct org_id) as orgs_in_scope
from ...Keep diagnostic queries small and discardable
Diagnostic SQL exists to answer one question. Do not build giant reusable queries too early.
Phase 4: Communication Rules
Lead with the answer
The first sentence of the written output should state the conclusion.
Bad:
I looked at several possible explanations for the discrepancy.
Good:
The discrepancy is caused by internal users being excluded from the dashboard query but included in the warehouse baseline.
Separate evidence from interpretation
Use a structure like:
- Conclusion
- Evidence
- Why alternative hypotheses were rejected
- Recommended next action
Include the limiting assumption
Every investigation should state the biggest assumption that could change the answer.
Example:
This conclusion assumes backend event timestamps are complete for the affected week; if ingestion was delayed, the gap may be overstated.
Phase 5: Output Standard
Every completed investigation should leave behind:
- One-sentence answer
- Final supporting SQL or notebook
- A note on rejected hypotheses
- Any follow-up question or unresolved ambiguity
Common Failure Modes
- Treating a metric definition dispute as a product issue
- Comparing sources with different grain or freshness
- Accepting the first plausible explanation without quantification
- Writing one giant query too early
- Ending with charts instead of an answer
Related Skills
- Use the
answering-natural-language-questions-with-dbtworkflow when the goal is answering a business question rather than debugging why analysis or metrics disagree.
© Kilo-Org, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/data-investigation of Kilo-Org/kilo-marketplace.
Open the folder on GitHubat commit ff51758
Compare with similar skills
Data 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 |
|---|---|---|---|---|---|---|
| Data Investigation this skillKilo-Org/kilo-marketplace | 190 | — | ~1.5k | Automated safety check: Pass | Apache-2.0 | |
| Review PRapache/shardingsphere | 21k | — | ~6.4k | Automated safety check: Pass | Apache-2.0 | |
| SQL Root Cause Analysiszj-unicom-ai/UniEmployee | 358 | — | ~433 | Automated safety check: Pass | MIT | |
| Analyze Issueapache/shardingsphere | 21k | — | ~6.5k | Automated safety check: Pass | Apache-2.0 | |
| Logfire Querypydantic/skills | 140 | — | ~2.2k | Automated safety check: Pass | MIT | |
| Perfetto Trace Analysisjameshnsears/QuoteUnquote | 100 | 2 repos | ~1.7k | Automated safety check: Pass | Apache-2.0 |
Similar skills
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.
Analyze Issue
apache/shardingsphere
Used to analyze Apache ShardingSphere community issues. An agent skill from apache/shardingsphere.
- Official
Logfire Query
pydantic/skills
Query and analyze Logfire telemetry data — traces, logs, spans, metrics, summaries, and SQL results.
Perfetto Trace Analysis
jameshnsears/QuoteUnquote
Analyzes Perfetto traces to find the root cause of latency, memory, or jank issues in Android apps.
Diagnose Clickhouse Errors
FrankChen021/datastoria
Diagnose ClickHouse runtime query failures when the user wants database-level cause and fix guidance from an error or numeric error code, not source-code root cause analysis.
More from Kilo-Org/kilo-marketplace
All 85 skills in this repoAzureML Project Scaffolding
Kilo-Org/kilo-marketplace
Sets up and maintains AzureML-ready Python projects as uv workspaces with devcontainers, a Makefile and job YAML, so local runs match cloud jobs and experiments stay reproducible.
Jupyter Notebook Builder
Kilo-Org/kilo-marketplace
Creates, inspects, edits and runs Jupyter notebooks, scaffolding experiment or tutorial notebooks from templates and preferring a Jupyter MCP server over raw JSON edits.
Tableau Dashboard Creator
Kilo-Org/kilo-marketplace
Takes a plain-language dashboard request through brand setup, data exploration, planning, an interactive HTML mock and a Tableau implementation spec.
Elasticsearch File Ingest
Kilo-Org/kilo-marketplace
Ingest and transform data files (CSV/JSON/Parquet/Arrow IPC) into Elasticsearch with stream processing and custom transforms.
Nifi Flow Layout
Kilo-Org/kilo-marketplace
A skill your agent uses when arranging Apache NiFi processors, process groups, ports, comments, numbering, crossing connections, dense fan-in/fan-out, or reusable readable canvas layouts.
Splunk Ingest Processor Setup
Kilo-Org/kilo-marketplace
Render Cisco Data Fabric ingest-time routing workflows and Splunk Cloud Platform Ingest Processor setup plans with SPL2 pipelines, source types, destinations, lifecycle handoffs, queue and…
Related
Works with
Categories
Questions about Data Investigation
What does Data Investigation do?
A workflow for conducting rigorous, reproducible data investigations and ad-hoc analyses. Data Investigation is an agent skill from Kilo-Org/kilo-marketplace. A workflow for conducting rigorous, reproducible data investigations and ad-hoc analyses.
When should I use Data Investigation?
Data Investigation fits situations like: tasks that involve Root cause analysis.
How do I install Data Investigation in Claude Code?
Run `npx skills add Kilo-Org/kilo-marketplace --skill data-investigation -a claude-code`. Or copy the skill folder (skills/data-investigation in Kilo-Org/kilo-marketplace) into .claude/skills/data-investigation in your project. Claude Code loads it when a task matches its description.
How do I install Data Investigation in Codex?
Run `npx skills add Kilo-Org/kilo-marketplace --skill data-investigation -a codex`. Or copy the skill folder (skills/data-investigation in Kilo-Org/kilo-marketplace) into .agents/skills/data-investigation in your project. Codex loads it when a task matches its description.
Can I use Data 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 Kilo-Org/kilo-marketplace --skill data-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/data-investigation, .gemini/skills/data-investigation, .github/skills/data-investigation and .opencode/skills/data-investigation in your project.
What does Data Investigation need to run?
SKILL.md names no scripts, command-line tools or credentials: Data Investigation is instructions for the agent only.
Does Data Investigation access the network?
SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.
Is Data 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. Review the folder before installing.
What licence does Data Investigation use?
Data Investigation is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Data Investigation use?
About 1.5k tokens (SKILL.md is roughly 5.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Data Investigation?
Skills that share tags, products or a category with Data Investigation: Review PR (apache/shardingsphere, 21k stars), SQL Root Cause Analysis (zj-unicom-ai/UniEmployee, 358 stars), Analyze Issue (apache/shardingsphere, 21k stars) and Logfire Query (pydantic/skills, 140 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Data Investigation?
Kilo-Org (a GitHub organization) maintains it in Kilo-Org/kilo-marketplace, which has 190 GitHub stars. The repository holds 85 skills in this directory. The repository was last updated on September 28, 2026.
Source: Kilo-Org/kilo-marketplace on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.