impact — Claude Code skill: dependency analysis and install
The impact Claude Code skill maps what depends on a table, column, or function. It gathers upstream sources, downstream consumers, checks, and a safe change order.
MIT ★ 106 updated 2026-11-06
/plugin marketplace add DataWithBaraa/claude-code-data-engineering-skills
/plugin install data-engineering@data-with-baraaWhat impact does
impact traces the effects of changing a table, column, function, or file. It finds upstream inputs and downstream tables, views, reports, tests, and jobs in SQL and code. Query logs show which roles and teams used downstream tables during the last period.
The skill lists relevant checks and tests, counts the affected tables, data products, consumers, queries, and checks, then lays out the change sequence: what to edit or rebuild, what to compare, and whom to notify. It reads SQL, code, data contracts, query logs, checks, and tests.
The result is a single HTML page with a dependency graph and lists. impact does not make changes, and it only reports dependencies found in code or logs.
What it helps with
- trace the inputs behind a table or function
- find reports and jobs affected by a change
- identify teams and roles querying downstream tables
- plan the order for edits and rebuilds
Example prompts for the agent
- Map the effects of changing the
orderstable and lay out a safe sequence. - Find the objects and tests that depend on the
customer_idcolumn. - Analyze the impact of changing
calculate_totaland produce the HTML result.
How to install impact
1Plugin marketplace
/plugin marketplace add DataWithBaraa/claude-code-data-engineering-skills/plugin install data-engineering@data-with-baraaThis installs the whole data-engineering plugin with all its skills
2Skills CLI (Vercel)
npx skills add DataWithBaraa/claude-code-data-engineering-skills --skill impact -a claude-code3Manually: put the files in place
~/.claude/skills/impact/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/impact/
1Skills CLI (Vercel)
npx skills add DataWithBaraa/claude-code-data-engineering-skills --skill impact -a codex2Manually: put the files in place
.agents/skills/impact/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add DataWithBaraa/claude-code-data-engineering-skills --skill impact -a cursor2Manually: put the files in place
.cursor/skills/impact/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install DataWithBaraa/claude-code-data-engineering-skills skills/impact2Manually: put the files in place
.github/skills/impact/SKILL.md1Skills CLI (Vercel)
npx skills add DataWithBaraa/claude-code-data-engineering-skills --skill impact -a gemini-cli2Platform CLI
gemini skills install https://github.com/DataWithBaraa/claude-code-data-engineering-skills --path skills/impactManually: put the files in place
.devin/skills/impact/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about impact
How do I install impact in Claude Code?
Add the marketplace with /plugin marketplace add DataWithBaraa/claude-code-data-engineering-skills, then install the plugin with /plugin install data-engineering@data-with-baraa.
What does impact do?
It traces an object's dependencies and consumers, identifies affected checks, and creates an HTML page with a graph and change sequence. It does not modify the project.
What sources does impact use to find dependencies?
It reads SQL, code, data contracts, query logs, checks, and tests. Dependencies must appear in code or logs; the skill does not infer them.
Source text
SKILL.md · MIT
--- name: impact description: Use before you change a table, a column or a function, to see what it is built from, what depends on it, who reads it, which checks cover it, and the safe order of the change. argument-hint: "[table, column or function]" --- # Impact The job: the answer to "if I change this, what breaks", before the change is made. Input: the table, the column or the function to change. ## Steps 1. Name the thing to change: a table, a column, a function or a file. 2. Upstream: everything it is built from, layer by layer. 3. Downstream: every table, view, report, test and job that reads it, found in the SQL and the code, never from memory. 4. The consumers: who queried the downstream tables in the last period, from the query logs, by role and team. 5. The checks and the tests that cover it, and the ones that will break. 6. The blast radius in numbers: tables, data products, consumers, queries, checks. 7. The safe order of the change: what to change first, what to rebuild, what to compare, and whom to tell. 8. Give the result as one web page, with the graph and the lists. ## Output One HTML file, like [references/impact.html](references/impact.html): the numbers on top, the graph with the thing to change lit, upstream and downstream, then the consumers, the checks and the safe order of the change. Read it for the layout before you write the page. ## Reads - the SQL, the code, the data contracts, the query logs, the checks and the tests ## Writes - the web page only ## Never - Never makes the change. - Never guesses a dependency: a dependency is one found in the code or in the logs.
© Data With Baraa · MIT · DataWithBaraa/claude-code-data-engineering-skills