Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →jacksonjp0311-gif/harvest-proposal-pipeline
Automate ICE-Crawler ingestion → registry update → proposal stub creation.
Passed 20 of 21 test cases with the skill, and 3 of 21 without it.
and 17 more in the full report
18 fixed3 passed either way1 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 17 test cases the skill fixed. Same model, same prompt, with and without the skill.
Inside the ICE-Crawler root, under what directory pattern are the timestamped fossil run outputs stored?
| Checked | Without skill | With skill |
|---|---|---|
| Identifies the run folder pattern state/runs/run_<timestamp> | Missed | Passed |
The instructions your model reads when the skill loads.
This skill runs the whole flow when you say so:
ice-crawler-harvester/extractions) is appended automatically.Helper script: scripts/harvest_pipeline.py
cd <skills_repo>\skills\harvest-proposal-pipeline
python scripts\harvest_pipeline.py <repo_url> --candidate <skill-name> --max-files 80 --max-kb 256
repo_url — cloneable Git URL (raw/tree/blob URLs are fine; orchestrator normalizes).--candidate (optional) — proposed skill name. When supplied, a stub JSON is written under skills/extraction-proposer/proposals/.--max-files / --max-kb — bounds for Glacier selection + per-file size.ICE_CRAWLER_ROOT to the local path of your ICE-Crawler clone before running this script.python -m engine.orchestrator … inside $env:ICE_CRAWLER_ROOT with timestamped state/runs/run_<ts>.artifact_manifest.json to count files.skills/ice-crawler-harvester/extractions/index.jsonl with: repo, run_dir, manifest path, file count, summary path.skills/ice-crawler-harvester/extractions/<repo-slug>/SUMMARY.md, including an auto-generated “Auto-detected Candidates” section with suggested algorithms/tools.--candidate is provided, saves skills/extraction-proposer/proposals/<skill-name>.json prefilled with provenance, candidate description, notable file list, and suggested skill structure.Run folder: the ICE-Crawler fossil (state/runs/run_<timestamp>).Summary: path to SUMMARY.md (includes auto-detected candidate bullets).Proposal stub: JSON file to review in extraction-proposer/proposals/ (if --candidate supplied).extraction-proposer/catalog/ and mark the status (approved, rejected, etc.) so the catalog becomes the definitive list of green-lit algorithms.skill-creator.test cases passed, vs 3 / 21 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.