Agent Skill evaluation harness for paired variants, trace artifacts, and runner adapters
☆79Nov 6, 2026Updated this week
Alternatives and similar repositories for skill-eval-harness
Users that are interested in skill-eval-harness are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- RLM-first backend for the Pi coding agent: a small local model writes code, runs it, verifies, and iterates. Code generation first, with …☆13Oct 23, 2026Updated 2 weeks ago
- Agent-skills marketplace for Coddy, Claude Code, Codex and Cursor: RPA BDD workflow, Logika (Chelpanov formal logic), token-cost, MikroTi…☆40Updated this week
- md+git knowledge base: FTS5 search (bm25+trigram/fuzzy), HTML+graph, code-ontology linter, Claude Code plugin☆125Nov 4, 2026Updated last week
- A curated collection of Claude Code skills, organized by category☆46Jul 20, 2026Updated 3 months ago
- Video generation skills for AI agents like Claude Code, Cursor, and Codex. Orchestrates Google Veo 3, Seedance, Higgsfield, ElevenLabs an…☆19Jun 14, 2026Updated 4 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Pi extension: interactive dashboards, charts, diagrams and maps in the terminal. The agent draws with OpenUI Lang; you click, hover and p…☆15Nov 3, 2026Updated last week
- ☆295Aug 25, 2026Updated 2 months ago
- Easy to use! Claude API Streamlit Version! Build your project upon this!☆12Aug 2, 2023Updated 3 years ago
- Travel-planning skill for AI agents: live flights, tours, hotels and excursions with prices and booking links.☆21Oct 20, 2026Updated 3 weeks ago
- ☆27Oct 4, 2026Updated last month
- Containerized environment for running coding agents with auditability on macOS and Linux☆14Updated this week
- Explainer videos from HTML (HyperFrames → MP4) with AI narrator, music and mixing — Claude Code / Codex skills on NeuralDeep models☆33Sep 30, 2026Updated last month
- Systems and distributed systems, built from first principles. Rust and C++.☆17Nov 4, 2026Updated last week
- Turns any OpenAPI/Swagger API into an CLI with set of commands. One CLI command per endpoint.☆268Sep 22, 2026Updated last month
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Deterministic code quality gate for AI coding agents (Claude Code, Codex, pi): git hooks that block test tampering, hold the CRAP bar on …☆21Oct 4, 2026Updated last month
- Shared memory for Pi, optional archive encryption, and a side chat for your agent's inner voice. Edit useful facts, search saved history,…☆20Nov 4, 2026Updated last week
- A curated collection of production-ready skills for Claude Code created by Extractum Team.☆47Nov 3, 2026Updated last week
- Keep your sensitive credentials out of the agents you build and the coding agent you use. Test any agent with planted fake keys, or see w…☆19Updated this week
- Supervise Codex CLI and Claude Code workers from OpenClaw with async progress, routed delivery, wake, resume, and automation support.☆24Jul 21, 2026Updated 3 months ago
- Generate realistic multi-agent workflow traces with LLM-enriched content, semantic validation, and PM4Py compatibility. pip install open-…☆16Apr 8, 2026Updated 7 months ago
- ☆1,240May 31, 2026Updated 5 months ago
- Enhanced UX for managing local Pi extensions and community packages☆18May 17, 2026Updated 5 months ago
- Коллекция промтов для комфорной работы с Cursor☆19Jan 21, 2026Updated 9 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- ☆21Jul 31, 2026Updated 3 months ago
- Hermes Bot Mode – X/Twitter Marketing Agency Team. Specialist bots for running a tweet-based marketing agency inside Hermes Desktop Bot M…☆14Aug 20, 2026Updated 2 months ago
- ☆15May 5, 2026Updated 6 months ago
- Experiment-driven improvement of agent skills and code: evaluate candidates, keep measured gains and revert regressions in autonomous or …☆20Sep 20, 2026Updated last month
- FIRM Protocol — Self-Evolving Autonomous Organization Runtime. Authority is earned, not assigned.☆20Apr 17, 2026Updated 6 months ago
- ☆44Apr 14, 2026Updated 6 months ago
- Secure local trace capture and inspection for Codex and Claude agent sessions.☆78May 27, 2026Updated 5 months ago
- Code Graph mcp solutions for AI agents with ontology and sentence. Supports extra large codebases☆47Updated this week
- ☆18Dec 28, 2024Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆18Apr 21, 2026Updated 6 months ago
- Practices, protocols, and skills for AI-driven software development. Skills and safety hooks for Claude Code, Codex, OpenCode, Cursor, An…☆177Updated this week
- Architecture-first skill lifecycle for AI agents. BinEval binary scoring with threshold-blind, cross-family-calibrated judges, gated self…☆212Aug 3, 2026Updated 3 months ago
- ☆12Apr 16, 2026Updated 6 months ago
- AI-first personal health quantification: Apple Health → SQLite → CLI → AI analysis☆13Nov 4, 2026Updated last week
- Open Plannotator reviews inside Herdr Browser panes.☆26Jul 29, 2026Updated 3 months ago
- Standalone, portable workstream system for Claude Code☆25Updated this week
Are these results useful?