ds-blast-radius — Claude Code skill: what it does, how to install
The ds-blast-radius Claude Code skill checks what a change might break beyond its diff, then tests a key safety claim by running code. Use it to inspect risky or untrusted changes before shipping.
MIT 550 installs ★ 320 updated 2026-10-28
npx skills add aicodeking/deepseek-stack --skill ds-blast-radius -a claude-codeWhat ds-blast-radius does
The skill examines a change and looks for effects beyond the edited lines. It follows library calls, async ordering, and data that crosses into APIs, databases, files, or code written in other languages. The review focuses on the facts that the change depends on for safety.
For each key fact, the skill grades the evidence, from a code reference to a test against the running app. When practical, it runs a script or test against the exact code in question. The report includes breakage found, commands and test output, plus claims that remain unproven. If it finds a real break, it reports the reproduction and stops. It does not make fixes.
What it helps with
- trace breakage beyond the changed lines
- test a key condition behind a risky change
- follow data across API or database boundaries
- verify a claim by running a test against real code
- report confirmed failures and unresolved claims
Example prompts for the agent
- Check what this diff could break and test the key safety claim against the code.
- Trace the blast radius of the change in
cache.ts. - Run
/ds-blast-radiuson this untrusted change and report the evidence.
How to install ds-blast-radius
1Skills CLI (Vercel)
npx skills add aicodeking/deepseek-stack --skill ds-blast-radius -a claude-code2Manually: put the files in place
~/.claude/skills/ds-blast-radius/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/ds-blast-radius/
1Skills CLI (Vercel)
npx skills add aicodeking/deepseek-stack --skill ds-blast-radius -a codex2Manually: put the files in place
.agents/skills/ds-blast-radius/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add aicodeking/deepseek-stack --skill ds-blast-radius -a cursor2Manually: put the files in place
.cursor/skills/ds-blast-radius/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install aicodeking/deepseek-stack skills/ds-blast-radius2Manually: put the files in place
.github/skills/ds-blast-radius/SKILL.md1Skills CLI (Vercel)
npx skills add aicodeking/deepseek-stack --skill ds-blast-radius -a gemini-cli2Platform CLI
gemini skills install https://github.com/aicodeking/deepseek-stack --path skills/ds-blast-radiusManually: put the files in place
.devin/skills/ds-blast-radius/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add aicodeking/deepseek-stack --skill ds-blast-radius -a opencodeClaude.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 ds-blast-radius
How do I install ds-blast-radius in Claude Code?
Run npx skills add aicodeking/deepseek-stack --skill ds-blast-radius -a claude-code. The skill file is at ~/.claude/skills/ds-blast-radius/SKILL.md.
What does ds-blast-radius do?
It investigates what a change could break beyond its diff and tests key safety claims by running code. Its report covers confirmed breakage and facts that remain unproven.
How does ds-blast-radius verify a change?
It grades evidence for each key claim, from a source reference to a test against the running app. When practical, it runs a script or test against the exact code involved.
Source text
SKILL.md · MIT
--- name: ds-blast-radius description: "Find what a change could break outside its own diff, then prove the key safety fact by running real code. Use before shipping a risky or untrusted change, for 'what could this break', 'blast radius of X', or /ds-blast-radius." --- # ds-blast-radius Listing callers is easy. The job is finding the breakage that a text search will not show, and proving the change is safe with a run instead of an argument. ## Steps 1. Read the change: the diff, the symbols it adds, changes or removes, and the behavior it now has that the diff does not spell out. 2. Find the one or two facts the change is safe because of, for example "this only removes cache entries that are already expired". Most risk clears if that fact holds. Spend your effort here. 3. Look where search stops. Read the source of libraries you call at their pinned version. Check timing: async ordering, teardown, retries. Follow data that leaves the code: API responses, database columns, file formats, config, other languages reading the same data. 4. Grade each key fact by how far you proved it: 1. you said so (worthless alone), 2. you pointed at a real file and line, 3. you traced the failure path and showed it cannot be reached, 4. you ran a script or test against the real code that fails loudly if you are wrong, 5. you reproduced it in the running app. 5. Push each key fact to level 4 when it is cheap. Usually that is one small script calling the exact function in question. 6. Report: the key facts, their proof level with the command and output, any real breakage found, and what stayed unproven. ## Stop when - Every key fact is at level 4 or higher, or you have said why it could not be, and the report is written. - Or you found a real break. Report it with the repro and stop. ## Rules - A convincing write-up is not proof. Show output. - Do not fix anything here. Hand fixes to the normal flow.
© aicodeking · MIT · aicodeking/deepseek-stack