
Factory Collect
Experimental workflow for collecting and triaging product feedback, product telemetry...
Install
npx skills add BuilderIO/skills --skill factory-collect -g -a claude-code -y- Repository
- BuilderIO/skills4.6k
- Category
- Engineering
- Updated
- 7d ago
- License
- MIT
- Context cost
- Lightabout 733 tokens
- Runs scripts
- No, instructions only
What it does
Experimental workflow for collecting and triaging product feedback, product telemetry, runtime errors, and issue reports. Use when scanning configured signal sources and applying separate fix, reply, or close rules.
Factory Collect
Read .agent-factory/config.yaml and apply the optional
skill_prompts.factory-collect entry as additional project guidance. Collect
only the sources named by workflows.collect.sources. For repeated patterns
across time or sources, use factory-lookback.
Collect and verify coverage
- Resolve each source ID to the connected read tool and exact scope recorded in the config. Sources may include support or chat feedback, issue trackers, product analytics or telemetry, and error monitoring.
- Use the configured time range or source cursor. Follow pagination to the end and record the filters, range, cursor/page coverage, and source counts.
- Keep
empty,unavailable, andtruncateddistinct. A missing connector, partial page, or failed query is not an empty source. - Preserve source links, timestamps, useful version or environment dimensions, and relevant discussion. Avoid copying secrets or unnecessary personal data.
- For telemetry, report the metric and aggregation window. Distinguish event counts from unique users or affected sessions unless the source provides a reliable identity definition.
Triage and act
Classify each item as a verified defect, repeated symptom, feature request, subjective feedback, duplicate, out of scope, or needing more evidence. Group related reports while retaining each source record and reporter.
Implement only when workflows.collect.implement allows the change and the
repository is in scope. Stop for configured risk conditions, unclear product
intent, or evidence that cannot be reproduced. Verify the changed behavior
with the configured checks and a representative reproduction.
