跪拜 Guibai
← All articles
Artificial Intelligence · AI Programming · Agent

Usora Turns AI Debugging Sessions Into Reusable, Versioned Skills

By 彼日花 ·
Read original on juejin.cn ↗ Google Translate ↗ Alt translation

AI coding agents are fragmenting into separate ecosystems (Codex, Claude, Kimi, Gemini), each with its own skill silos. Usora proposes a cross-agent protocol where hard-won debugging and design methods become personal engineering assets that survive model and tooling changes.

Summary

Repeatedly re-teaching an AI agent the same debugging steps wastes the context, methods, and validation criteria already discovered. Usora introduces a Foundry pipeline that observes real development activities — fixing a memory leak, refactoring a module, designing a CI workflow — and extracts only the practices worth keeping into structured Skills. These Skills carry versions, provenance, test records, and changelogs, evolving like code rather than sitting as lost markdown in a chat history.

The system separates concerns across multiple AI agents: any agent can propose a Candidate Skill from observed practice, but a designated Maintainer (defaulting to Codex) reviews, tests, versions, and publishes. This keeps a personal Skill Hub from becoming an uncontrolled auto-generated dump while still leveraging different models for different tasks.

A planned Skill Market would let developers share battle-tested Skills — such as a Vue memory-leak analysis or a React performance audit — that have been validated across real projects. The longer vision is a Capability Network where people, agents, and Skills interconnect, with humans deciding what is worth preserving.

Takeaways
A Foundry pipeline collects, analyzes, and extracts candidate Skills from real AI collaboration sessions rather than converting every activity directly into a Skill.
Skills are versioned artifacts with source traces, changelogs, validation records, and test histories — not static markdown prompts.
Multiple AI agents can propose Candidate Skills, but only a designated Maintainer can review, test, version, and publish them, preventing uncontrolled modification.
The default Maintainer role is assigned to Codex, while Claude, Kimi, Gemini, and others contribute Candidates.
A planned Skill Market would allow developers to discover, install, use, improve, and contribute Skills validated across real projects.
The long-term goal is a Capability Network connecting developers, designers, architects, PMs, researchers, and multiple AI agents through shared, evolving Skills.
Conclusions

The core waste in AI-assisted development is not rewriting prompts but losing the accumulated context, judgment criteria, and workflow that a session already produced.

Treating a debugging method as a versioned engineering asset — with provenance, testing, and rollback — is a category shift from prompt libraries, which are usually static text.

The Candidate/Maintainer split solves a real governance problem: multi-agent collaboration without surrendering quality control to every model that touches the hub.

A cross-agent Skill protocol directly pushes back against the vendor lock-in emerging as each AI coding tool builds its own proprietary skill format and ecosystem.

Concepts & terms
Foundry
The Usora pipeline that observes raw AI collaboration activities, analyzes them, extracts candidate methods, and evaluates which are worth casting into formal Skills.
Candidate Skill
A proposed Skill generated by any AI agent from observed practice; it requires Maintainer review, testing, and approval before publication.
Maintainer
The designated role (defaulting to Codex) responsible for reviewing, evaluating, testing, versioning, and publishing Skills to keep the hub trustworthy.
Skill Market
A planned marketplace where developers can discover, install, and contribute Skills that have been validated through real-world project use across different AI agents.
Capability Network
The long-term vision where people in different roles, multiple AI agents, and shared Skills interconnect, forming a distributed infrastructure of reusable engineering methods.
From the discussion

The core tension is whether capturing AI debugging sessions as reusable skills pays off or just bloats context. One side argues that skill accumulation quickly becomes a disaster because every skill description consumes context, and recall accuracy rarely justifies the cost in real-world, environment-dependent problems. The counterpoint acknowledges the risk but reframes the problem as one of curation — recall, context control, and ruthless skill retirement — rather than raw accumulation. A separate concern notes that agents may soon absorb this functionality natively, making the tool redundant; the response shifts the value proposition to user-owned, cross-agent portability rather than competing with built-in features.

Skill descriptions injected into context carry a real cost, and at scale (dozens of skills) the descriptions become chaotic, turning the system into a disaster.
Most problems are tightly coupled to their specific scenario and environment, so the benefit of general reusable skills often fails to outweigh the context and recall overhead.
The real challenge is not how many skills to accumulate but how to handle recall, context budgeting, and skill retirement — including injecting zero skills when none are needed.
Agent platforms may soon build this capability natively, threatening the tool's relevance.
The tool's value lies in user-owned, cross-agent reusable capabilities rather than competing with agent-native features.
Featured comments
胡安民 1 likes

Consider one issue: context and recall accuracy. Most of the time it's not that people don't want to do these things, but that the cost outweighs the benefit. The majority of problems depend on the scenario and environment. And once you have too many skills, they bloat — many skill descriptions become chaotic. With dozens of skills, it turns into a disaster. Skill descriptions are injected into the context, and that comes at a cost. I had this same idea a long time ago, but later abandoned it after developing it. There's still a saying that rings true: "For an Agent, what you deliberately choose not to do is more important than what you do."

彼日花

This point is definitely worth considering. I also agree that more skills is not always better. What matters more down the line may not be "how much you accumulate," but how to handle recall, context control, and skill retirement — even injecting none when they aren't needed. "For an Agent, not doing something is more important than doing something" is very insightful. Thanks for sharing.

See top comments, translated →
Source: juejin.cn ↗ Google Translate ↗ Backup ↗