Skip to content
Back to the index

skill-harness

PyPIInfrastructure

PulseGate's liveness check found it on 14 Sep 2026; it is registered on GitHub and PyPI and has been in the index since 26 Jul 2026. How this is checked

Skill-harness is a Python evaluation tool for reusable AI agent skills. It assesses whether a skill earns its place by returning clear KEEP, CUT, or CAN'T-TELL-YET verdicts instead of manufactured scores. It offers first-class support for Claude Code and is designed for developers building robust agent systems.

Inferred · not functionally tested

Open SourceMITCLI
Visit PyPI
1star
1alternative
3features
2026since

Overview

3 features

Purpose: Determining whether a reusable AI agent skill is valuable enough to keep in a library without relying on arbitrary numerical scores.

Inferred · not functionally tested

Audience: AI developers

Inferred · not functionally tested

Functions: agents

Inferred · not functionally tested

Interfaces: API: unknown · MCP: unknown · CLI: indicated (inferred, not tested) · Self-hosting: unknown

Recorded constraints: pricing: open_source · license: MIT · platforms: CLI · deployment: cli

Constraint provenance is unknown; confirm requirements with the publisher.

Record sources: pypi.org · github.com. These links do not verify the individual claims.

In the Agent evaluation & testing space, skill-harness takes a focused approach. Inferred · not functionally tested: It focuses on determining whether a reusable AI agent skill is valuable enough to keep in a library without relying on arbitrary numerical scores. Inferred · not functionally tested: It is built as an open-source project for AI developers. Basis unknown · not verified: The project is open source (MIT). Basis unknown · not verified: It ships for the command line.

It is developed by MrBinnacle, and it first shipped in 2026. The project is developed in the open on GitHub with 196 commits in the last 90 days. Inferred · not functionally tested: Among its 3 catalogued features are skill evaluation, binary decisions, and Claude Code support.

Summary written by a language model from the project’s public pages.

Tasks: Inferred · not functionally tested

  • Skill evaluation
  • Binary decisions
  • Claude Code support

Topics: Inferred · not functionally tested

Tags
agent-skillseval-harnessllm-evaluationskill-ab-testing
AI capabilities
TextCode

JSON profile · Text profile · Access guide

Built with & integrations

AI providers
anthropicopenai
Runs on
CLI

Trust & compliance

License
MIT
Public signals
HTTPSOpen SourceGitHub · ★ 1Active maintenance

Indexing history

1

What PulseGate has recorded for this listing

  1. Indexed26 Jul · 20:58 UTC
    skill-harness seen via PyPI Bulk Enumerator
    Source: PyPI Bulk Enumerator · Open

Frequently asked questions about skill-harness

What does skill-harness do?
Inferred · not functionally tested: Skill-harness focuses on determining whether a reusable AI agent skill is valuable enough to keep in a library without relying on arbitrary numerical scores. It is catalogued under Agent evaluation & testing on PulseGate.
Who is skill-harness for?
Inferred · not functionally tested: skill-harness is an open-source project built for AI developers.
Is skill-harness free?
Basis unknown · not verified: Yes — skill-harness is open source under the MIT license and free to use.
What platforms does skill-harness run on?
Basis unknown · not verified: skill-harness runs on the command line.
Is skill-harness still active?
PulseGate's liveness check found it on 14 Sep 2026. Its GitHub repository shows 196 commits in the last 90 days.
What are alternatives to skill-harness?
Similar projects tracked by PulseGate include skill-eval-harness, skilldistill, and skillfabric-ai.skill-eval-harnessskilldistillskillfabric-ai
Who develops skill-harness?
skill-harness is developed by MrBinnacle.
How long has skill-harness been around?
skill-harness first shipped in 2026.

Similar projects

Closest matches by what these projects do