More screenshots
Works with the AI Agents you already use
Dataset Cleaning Bottleneck Fix
Profile a dataset first, fix one issue type at a time in dependency order, and reconcile counts after each step.
$5
Dataset Cleaning Bottleneck Fix
Example session with this skill installed
Apply the skill to: Survey dataset stalled on one column.
- Read your context and instructions
- Compiled the dataset cleaning bottleneck
Worked example: A survey dataset of 3,400 rows stalled in cleaning for two weeks because every attempt produced different totals, and the team restarted twice. Findings: Profiling showed the bottleneck was a free-text region field with 214 variants for about 30 real regions, plus a duplicate key issue on 180 rows. Date fields mixed three formats, and one format parsed day and month in reverse for ambiguous dates. Missing values in the outcome field ran at 12 percent, concentrated in one collection week, suggesting a collection gap rather than random loss. Join match rate dropped after an early aggregation step because categories had not yet been standardised. Outcome: Rules were written for region mapping, date parsing with an explicit format list, and duplicate resolution, applied in dependency order with count reconciliation after each step. Cleaning finished in three days, the log reconciled 3,400 raw rows to 3,220 analysis rows with each removal explained, and the collection-week gap was reported as a source fix. This is a worked example produced by applying the skill protocol, not a guarantee of results on new data.
Connects securely to your tools. The creator never sees your data.
About this skill
Cleaning stalls because teams clean by intuition, delete rows without a log, and discover late that a fix broke a join, a total, or a time series, forcing a restart from the raw file. The bottleneck is usually one column or one join: inconsistent categories, mixed date formats, duplicate keys, or free-text fields that resist rules. Cleaning everything at once hides that bottleneck; profiling first exposes it. This skill gives you a full protocol: trigger and scope, an inputs and outputs contract, ordered steps with checks, a decision table, a fill-in template, a checklist, a scoring rubric, a worked example, edge cases, and a pre-delivery quality gate. It also includes a runnable script under scripts/ so the core scoring or checking step can be repeated on new data without redoing the judgement by hand. The focus throughout is bottleneck fixes and workflows that a short free checklist would not cover: what to check first and second, which thresholds change the action, and when to stop and narrow the scope.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse All Claude Skills.
Cleaning improves usability; it does not create information that was never collected. Imputation and exclusion choices change results and must be reported, not hidden. Results depend on input quality: missing inputs, small samples, or unverified sources limit how strongly conclusions can be stated. The skill helps you state those limits honestly rather than hiding them.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 23 days ago