impact
Skill84 starsChanged 13 days agoMITView on GitHub
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.
16 other projects use a version of this.
Adopted by
Most recently taken up by
- jskswamy/skillstheir own version, first seen Nov 8, 2026
- paulocsb/worldcup-fifa-pooltheir own version, first seen Nov 8, 2026
- ai-agent-lead/skillstheir own version, first seen Nov 1, 2026
- ShiftinBits/constellation-claudetheir own version, first seen Nov 1, 2026
- stoa-platform/stoatheir own version, first seen Nov 1, 2026
- natalinio/project-second-braintheir own version, first seen Oct 20, 2026
Used with
Projects with it also use debug.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
AnthropicSkilldebug
Structured debugging session — reproduce, isolate, diagnose, and fix. Trigger with an error message or stack trace, "this works in staging but not prod", "something broke after the deploy", or when behavior diverges from expected and the cause isn't obvious.
Also in 4 projects that use this
Other versions16 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 16
- mbwsims/claude-universe★ 71same name
- Anuj7411/sipcode★ 46same name
- drafthq/draft★ 40same name
- huiruru/ecoguilt★ 9same name
- stoa-platform/stoa★ 9same name
- gonimar/claude-web-studio★ 4same name
- ai-agent-lead/skills★ 3same name
- jskswamy/skills★ 3same name
- Jsnnmsc/10000x-engineer★ 2same name
- ShiftinBits/constellation-claude★ 2same name
6 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository16 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- big-reviewSkill
- contractSkill
- cost-reviewSkill
- data-productSkill
- docsSkill
- incidentSkill
- knowledge-refreshSkill
- metadataSkill
- migrationSkill
- profileSkill
- pr-reviewSkill
- qualitySkill
- reconcileSkill
- test-dataSkill
- toolkitSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 16 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 38
Never makes the change.
- Distinctive: line 39
Never guesses a dependency: a dependency is one found in the code or in the logs.
“Common” is measured: kept by at least 6 in 10 of the 16 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
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
- Name the thing to change: a table, a column, a function or a file.
- Upstream: everything it is built from, layer by layer.
- Downstream: every table, view, report, test and job that reads it, found in the SQL and the code, never from memory.
- The consumers: who queried the downstream tables in the last period, from the query logs, by role and team.
- The checks and the tests that cover it, and the ones that will break.
- The blast radius in numbers: tables, data products, consumers, queries, checks.
- The safe order of the change: what to change first, what to rebuild, what to compare, and whom to tell.
- Give the result as one web page, with the graph and the lists.
Output
One HTML file, like 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.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.