SkillX

Name: SkillX Review
Item: SkillX
Rating: 3.2
Author: Aaron Matthews

Skill Development Usable

Works inClaude Code

Usable Scanned — metadata only

Automates the construction of structured skill knowledge bases for AI agents, making it easier to scale agent capabilities without manual curation.

A research framework from ZJU NLP that automatically builds a reusable, plug-and-play skill knowledge base for LLM agents from their own execution trajectories. It distills experience into a three-level hierarchy — planning, functional, and atomic skills — that can be injected into weaker base agents without retraining, reporting roughly 10% absolute gains on AppWorld, BFCL-v3, and tau2-Bench. Note: the README lists the codebase as a planned release; code is not yet published.

Build reusable agent skill libraries from execution experience
Transfer skills from a strong backbone agent to weaker base agents without retraining
Improve success rates and efficiency for long-horizon, tool-using agents

270 starsMIT (commercial OK)FreeQuick setup

Usable rating — This tool is functional but has notable gaps. Review the evaluation notes below before deploying.

Why it matters

Automates the construction of structured skill knowledge bases for AI agents, making it easier to scale agent capabilities without manual curation. Helps teams systematically grow what their agents can do.

Best for

AI engineering teams building agent systems who need a scalable method for defining and managing agent skills.

Works in

Claude Code Claude Cowork Claude Chat

Source

https://github.com/zjunlp/SkillX

By zjunlp

How to Get It

Option 1: Claude Desktop App (Code Mode)Click the + button next to the prompt box → Plugins → Add plugin. Search and click Install. Skills work in Claude Code only.

Option 2: Paste into Claude CodeCopy the command below and paste it into your conversation. Claude will install it.

Command

See repository README

Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.

First thing to try

After installing, paste this into Claude:

Help me build reusable agent skill libraries from execution experience

CostFree

Trust Signals Auto-scanned

Stars270Contributors4Last updated2026-07-05LicenseMIT (OK for commercial use)Known CVEsNone foundSources: GitHub Advisory Database + OSV.dev · Scanned 2026-08-16 · scanner v1

Community Pulse Quiet

No community discussions found yet. This doesn't mean the tool isn't good — it may be new or serve a niche use case.

Reviewer notes

Auto-scanned review. These are observations, not a security certification.

catalog_hygiene stale-eval refresh: Scored from trust signals (evidence-eval-v1): 270 GitHub stars; 4 contributors; last commit 44d ago; license MIT.

Things to check

Recently discovered. Looks promising but has limited community feedback so far. We added it early so you can evaluate it before the crowd finds it.

How to evaluate tools before deploying →

Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.

Evaluation Scores

Evaluation

Ease of Use

3/5

Versatility

3/5

Reliability

4/5

Security

3/5

Overall score3.25 / 5.00 UsableEvaluatedAug 2026

catalog_hygiene stale-eval refresh: Scored from trust signals (evidence-eval-v1): 270 GitHub stars; 4 contributors; last commit 44d ago; license MIT.

← Back to the Claude Observatory