impact
Skill2 starsChanged 2 months agoMITView on GitHub
Surface the blast radius of a change — which modules, services, users, or data get touched, directly or downstream — plus what to do about it.
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
- DataWithBaraa/claude-code-data-engineering-skillstheir own version, first seen Nov 1, 2026
Used with
Projects with it also use debug and docs.
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
Microsoft AzureSkilldocs
Also in 3 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
- DataWithBaraa/claude-code-data-engineering-skills★ 84same name
- 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
- 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 repository10 other files it gives its agents.
- 3wSkill
- catchupSkill
- clear-viewSkill
- decisionSkill
- first-principleSkill
- one-lineSkill
- scopeSkill
- tldrSkill
- tradeoffSkill
- visSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 5 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 16 edited versions we read keep these.
5
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 23
If a dependency is uncertain, mark it "uncertain — verify" inline on that item rather than guessing.
- Distinctive: line 65
Don't list what *could* break in theory.
- Distinctive: line 68
Don't write "Who notices: users" with nothing after it.
- Distinctive: line 71
Don't make the bottom line a recap ("this touches 4 services and the data pipeline").
- Distinctive: line 74
If no request was supplied, ask: "Impact of what change?"
“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
Goal: engineer knows who and what gets touched by a change before it ships — not what could break, just what's connected.
Rules
- Respond in the same language the user wrote in. If they write in Chinese, reply in Chinese. Technical terms (JWT, Redis, API…) stay in English.
- Max 10 lines. Hard limit.
- Directly affected = code/data/config that the change literally touches.
- Downstream affected = things that consume or depend on what was touched, even if not edited directly.
- Who notices = the human side — which users, teams, or on-call gets a visible effect.
- If a dependency is uncertain, mark it "uncertain — verify" inline on that item rather than guessing. Don't give it its own section.
- Bottom line = the one move that matters given this blast radius — who to warn, what order to do it in, or which item to verify first. Not a summary of the sections above.
- No emoji.
Output format
**Directly affected**
- [module/file/service — what changes about it]
**Downstream affected**
- [what depends on it, and how]
**Who notices**
- [users / team / on-call — what they'd see, and when]
**Bottom line:** [the one move that matters — who to warn, what order, what to verify first]Example
/impact users.id 從 int 改成 bigint
**Directly affected**
- `users` table — column type change (int → bigint)
- `models/user.py` — ORM column type must match or writes fail silently
**Downstream affected**
- Any service joining on `users.id` — 4 services, all must handle the wider type
- Analytics pipeline reading raw `users` dumps — schema mismatch breaks nightly load
- Uncertain — verify: the legacy PHP admin panel may hardcode int parsing
**Who notices**
- On-call, during the migration window — brief write lock on `users`
- Data team, next morning — dashboards break until the pipeline schema is updated
**Bottom line:** tell the data team before you start, not after — their nightly load is the one thing that breaks silentlyAnti-examples
Don't list what could break in theory. This skill maps what's connected; speculation about failure modes belongs in a review, not here.
Don't write "Who notices: users" with nothing after it. Name what they'd actually see and when — a visible effect or nothing.
Don't make the bottom line a recap ("this touches 4 services and the data pipeline"). They just read that. Give them the move.
If no request was supplied, ask: "Impact of what change?"
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.

