From fuse-ai-pilot
Use when marking a task as complete, finishing a feature, or claiming a bug is fixed. Ensures functional resolution is verified with evidence before closing.
How this skill is triggered — by the user, by Claude, or both
Slash command
/fuse-ai-pilot:verificationThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
**Sniper validates CODE QUALITY. Verification validates FUNCTIONAL RESOLUTION.** Both are needed before closing any task.
Sniper validates CODE QUALITY. Verification validates FUNCTIONAL RESOLUTION. Both are needed before closing any task.
Sniper catches linter errors, SOLID violations, and code style issues. Verification ensures the original request is actually fulfilled -- the right behavior, the right output, the right fix. A task can pass sniper with zero errors and still be functionally wrong.
| Aspect | Sniper | Verification |
|---|---|---|
| Focus | Code quality | Functional correctness |
| Checks | Linting, SOLID, style | Acceptance criteria, regressions, side effects |
| Runs | After any code change | Before marking task as complete |
| Result | Clean code | Solved problem |
When invoked, follow the 6-step verification process below before marking any task as completed.
Step 1: Re-read the original request Go back to the original issue, task description, or user message. Read it word by word. Do not rely on memory or assumptions.
Step 2: List ALL acceptance criteria Extract every explicit and implicit requirement from the original request. Number them. If the request is vague, list what a reasonable user would expect.
Step 3: Verify each criterion with evidence For each criterion, provide concrete evidence of resolution:
Step 4: Check for regressions Run the full test suite. Compare results before and after. No new failures, no new warnings.
Step 5: Check for side effects Review every modified file. Confirm no accidental changes to unrelated code. Verify dependencies and configuration are unchanged unless required.
Step 6: Confirm functional resolution State explicitly: "Original problem is FUNCTIONALLY resolved" with a summary of evidence, or list what remains unresolved.
| Resource | Path | Content |
|---|---|---|
| Checklist | references/checklist.md | Full verification checklist with all categories |
| Common Misses | references/common-misses.md | Frequently forgotten verification items |
Verification runs between eLicit and eXamine in the APEX workflow:
Analyze -> Plan -> Execute -> eLicit -> [VERIFICATION] -> eXamine (sniper)
This ensures functional correctness is confirmed before code quality validation. A task is only complete when both verification and sniper pass.
| Rule | Reason |
|---|---|
| Never skip re-reading the original request | Prevents solving the wrong problem |
| Evidence required for every criterion | "It works" is not evidence |
| Full test suite, not just new tests | Catches regressions |
| Review ALL modified files | Catches accidental side effects |
| Both verification AND sniper must pass | Quality without correctness is useless |
npx claudepluginhub fusengine/agents --plugin fuse-ai-pilotEnforces evidence-based completion discipline: run verification commands (tests, lints, type checks, builds) before claiming work is done. Prevents false completion by requiring captured output.
Enforces evidence-based verification by running fresh tests, builds, linters, reviewing outputs before claiming work done, committing, or PRing.
Enforces evidence-based verification before claiming tasks, features, or PRs complete. Requires pasting test outputs, command runs, and behavioral checks; rejects vague assertions.