Reconciles data sources using stable identifiers (Pay Number, driving licence, driver card, and driver qualification card numbers), producing exception reports and “no silent failure” checks. Use when you need weekly matching with explicit reasons for non-joins and mismatches.
Security Analysis
high confidenceThe skill's instructions, files, and requirements are coherent with its stated purpose (data reconciliation and exception reporting); it is instruction-only, requests no credentials, and has no install steps.
Name/description describe reconciliation of datasets by stable IDs and the provided SKILL.md, matching-rules.md, and CSV template all implement that workflow. The skill requests no binaries, env vars, or installs — consistent with a guidance/template skill that operates on user-provided CSV/XLSX files.
Runtime instructions focus on mapping, normalization, key validation, joins, exception categorization, and stop-and-ask gates. They explicitly require user-provided datasets and do not instruct reading unrelated system files, environment variables, or contacting external endpoints. The guidance to be read-only by default limits destructive actions.
No install spec and no code files are included; this is an instruction-only skill. That minimizes the surface for arbitrary code execution or supply-chain risk.
The skill declares no required environment variables, credentials, or config paths — proportional for a documentation/plan-style reconciliation skill. Note: the skill is designed to process sensitive PII (pay numbers, licence numbers etc.), so operational data-handling controls are important even though the skill itself requests no secrets.
always is false and the skill does not request persistent system privileges. Autonomous invocation (model invocation enabled) is the platform default and reasonable here; nothing indicates the skill needs elevated or permanent presence.
Guidance
This skill appears coherent and low-risk from a packaging perspective, but it will be used to process sensitive identifiers (pay numbers, driving licence/card numbers). Before using: 1) ensure datasets you provide are allowed to be processed by the agent and comply with your data-protection rules (consider anonymizing or using synthetic data for testing); 2) confirm where exception reports are written and that storage/access controls are appropriate; 3) verify the agent's runtime will not upload data to external services you don't control; 4) test the matching rules on a small sample to confirm the join priority and thresholds behave as expected; 5) if you need automated remediation, update the SKILL.md to document safeguards — otherwise keep it read-only and require explicit approval for any edits. If you want stronger assurance, request an implementation (code) that you can review or run in an isolated environment.
Latest Release
v1.0.0
- Initial release of the data-reconciliation-exceptions skill. - Reconciles multiple data sources using stable identifiers (Pay Number, driver documents). - Produces comprehensive exception reports with explicit reasons for each non-match or mismatch. - Implements “no silent failure” checks—pipelines stop when anomalies or tolerance breaches are detected. - Provides clear input requirements, configurable normalization, and threshold options. - Outputs a detailed CSV report categorizing every record (matched, missing, duplicate, mismatch, invalid).
More by @KOwl64
Published by @KOwl64 on ClawHub
