by zorazrw · Agent Tool · ★ 50
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours.
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 50 |
| Forks | 9 |
| Language | Python |
| Category | Agent Tool |
| License | CC-BY-SA-4.0 |
| Quality Score | 71/100 |
| Open Issues | 4 |
| Last Updated | 2025-04-24 |
| Created | 2025-04-09 |
| Platforms | browser, python |
| Est. Tokens | ~37k |
ASI: Inducing Programmatic Skills for Agentic Tasks Quick Start :rocket: Step 0: Setup Step 1: Solving WebArena Tasks Make sure you set the WEBSITE urls before running WebArena tasks. To solve a particular webarena task (e.g., example 21), run the following command: Step 2: Evaluate Trajectory Correctness Step 3: Inducing Workflow Actions To clean an episode, r
These tools work well together with agent-skill-induction for enhanced workflows:
Looking for a agent-skill-induction alternative? If you're comparing agent-skill-induction with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Web-Use is a CDP powered Browser Agent
Physical AI runtime for embodied agents — governed action, verified experience, physical memory, and skill evo
Gradient descent, but the parameters are agents — a parallel, asynchronous framework for self-evolving agents
Gradient descent, but the parameters are agents — a parallel, asynchronous framework for self-evolving agents
[NAACL2025] LiteWebAgent: The Open-Source Suite for VLM-Based Web-Agent Applications
An agent-first mobile runtime built on OpenClaw: control apps, learn reusable skills, and connect phones.
Explore other popular agent tool tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: