PyRank
MrBinnacle

skill-harness

How do you KNOW if a 'skill' is any good - deterministically? This runs controlled skill-vs-no-skill experiments. It doesn't just ask, “Did the skill work?” It asks “Did we actually give the skill to the model, did the comparison remain fair, what changed, what did it cost, and do we have enough evidence to say that confidently?”
PyPI GitHub
More links
Download Stats Changelog Documentation Issues
Verified repo
Monthly downloads
240
Weekly downloads
63
GitHub stars
13

Downloads in the 30 and 7 days to October 10, 2026. Refreshed weekly.

Package Information

Latest Version
0.3.0
Requires Python
>=3.12
Licence
MIT
Last Release
1 month ago
Author
MrBinnacle
First Release
July 26, 2026
Total Releases
4
Python Versions
3.12 3.13
No reported malware or high/critical advisories · Details

The current version has no OSV.dev malware reports and no critical or high-severity vulnerabilities.

Package Insights

What's this?
Score breakdown - each component scores 0-100, weighted by percentage
Maintenance
60
Popularity
19
Adoption
23
Community
10
Provenance
100
How the maintenance status was determined
Last commit
10 days ago
Monthly downloads
240
• Active
Activity within 30 days
Stable
Activity within 31-180 days
Minimal
Activity within 181-365 days, or no activity data
At Risk
No activity for > 365 days, but > 10,000 monthly downloads
Archived
Repository flagged as archived on GitHub
How the popularity category was determined
Monthly downloads
240
Stars
13
Stars per 1k downloads
54.17
Industry Standard
> 10,000,000 monthly downloads
Hidden Gem
< 0.5 stars per 1k downloads and > 100,000 monthly downloads
Community Favorite
> 5 stars per 1k downloads
Rising Star
Balanced ratio of stars to downloads
• Unknown
Fewer than 1,000 monthly downloads, or no star data
Needs at least 1,000 monthly downloads to classify popularity.
How download momentum is calculated
Week daily avg
9
Month daily avg
8
Momentum
—
((week_daily_avg - month_daily_avg) / month_daily_avg) * 100
Momentum not reported for packages with < 5,000 monthly downloads — percentages are noisy at low volume.
More insights and metrics
Python version support tiers
requires_python
>=3.12
Cutting Edge
Minimum supported version is 3.14 or newer
• Modern
Minimum supported version is 3.11 to 3.13
Legacy
Supports 3.10 or older (or Python 2)
Unknown
No requires_python specified or unparseable
License categories
License
MIT
• Permissive
MIT, Apache, BSD, ISC, Unlicense, CC0, etc.
Copyleft
GPL, LGPL, AGPL, MPL, EPL, etc.
Proprietary
Commercial, all rights reserved, custom EULAs
Unknown
No license specified, or none of the above match
How the release cadence was determined
Last release
40 days ago
Total releases
4
Releases/year
17.8
• Rapid
Last release within 365 days and > 12 releases/year
Regular
Last release within 365 days
Slow
Last release 366-730 days ago
Stalled
Last release > 730 days ago, or no releases
Unknown
No usable release date available
How contributor risk was determined
Contributors
2
Monthly downloads
240
High Load
≤ 2 contributors and ≥ 50,000 monthly downloads
Moderate Load
< 10 contributors and ≥ 500,000 monthly downloads
Low Load
< 25 contributors and ≥ 5,000,000 monthly downloads, or sole maintainer with ≥ 10,000 monthly downloads
• Balanced
Enough contributors for the package's popularity
Unknown
No contributor data available
Engagement
25
 
Issue Burden
-
per 1k stars
Discussions
-
per 1k stars
Fork Ratio
200.0%
contrib / forks
Stale Release
No
 
PR Velocity
Active
 
Not all downloads include detailed metadata. Breakdowns reflect the subset that does.

Downloads by OS

No OS data available

Python Versions

No Python version data available

Top Countries

1. US US
9
2. TW TW
2

Weekly Downloads

GitHub Stars

Dependencies

8
16 optional dependencies

Used By

0
Not used by any tracked packages

Repository details

Forks
1
Issues
46
Last Commit
1 week ago
Contributors
2
Open PRs
2
Archived
No

Data and sources

Tracking Since
September 26, 2026
Data Updated
October 11, 2026
Data Freshness
Fresh
Keywords
ab-testing agent-skills ai-agents claude-code eval-harness evals llm-evaluation prompt-evaluation skill-evaluation
Sources and methodology