Data Cleanup Skill

Full FREE body

Copy Back to Skills

Pack body is English. UI language controls translate chrome labels only.

### Data Cleanup Skill
TYPE: SKILL
### Data Cleanup Skill
TYPE: SKILL
PURPOSE: Encode a reusable professional method for data cleanup.
WHEN TO USE: When the task explicitly requires data cleanup or this capability is a necessary step in a larger workflow.
WHEN NOT TO USE: When unrelated, when a materially better specialized Skill applies, or when required evidence is unavailable.
REQUIRED INPUTS: Objective; source material/context; constraints; required output.
OPERATING INSTRUCTIONS:
1. Confirm the actual objective from supplied context without unnecessary questions.
2. Identify only material relevant to data cleanup.
3. Execute the named task systematically and within scope.
4. Preserve supplied facts and label assumptions/uncertainty.
5. Produce concrete usable output, not generic commentary.
6. Self-check for omissions, contradictions, unsupported claims and constraint violations.
RULES: Never fabricate evidence, metrics, citations, functionality, execution, or completion. Do not silently alter user facts.
QUALITY BAR: A competent professional should be able to use the output immediately without reconstructing the method.
OUTPUT CONTRACT: Result; evidence/reasoning basis where relevant; assumptions/unknowns; risks/exceptions; next action.
FAILURE HANDLING: If evidence is insufficient, return the strongest supported partial result and identify only missing information that materially blocks completion.
EXAMPLE INVOCATION: Use the Data Cleanup Skill on [material] and return the result using this Skill's output contract.
RELATED USE: May be composed with compatible Kimi, MCP or AgentSwarm workflows only where those capabilities are actually available in BSV.
TASK-SPECIFIC METHOD FOR “Data Cleanup Skill”:
1. Define done: what artifact proves data cleanup succeeded.
2. Collect only inputs required for data cleanup; ignore unrelated context.
3. Execute data cleanup in a checklist pass: prepare → analyze → draft → self-check.
4. Emit the concrete artifact expected for data cleanup (not generic advice).
5. List blockers/unknowns that would change the result.
FREE: YES
PRIMARY ACTION: COPY / USE