AutoSkillECNU-ICALK/AutoSkill
Enables AI agents to automatically distill experience from each task into reusable skills and to keep invoking and itera…
No ratings yet
Rate this skill
Stars597
Forks58
Watchers597
Open Issues3
InstallOne-line install
UnconfirmedWhether this repository follows the Agent Skills spec (that is, whether it contains a SKILL.md) has not been verified yet. Until that is settled, clone it and use what you need:
git clone https://github.com/ECNU-ICALK/AutoSkill.git
OverviewOverview
Key Features
Enables AI agents to automatically distill experience from each task into reusable skills and to keep invoking and iterating on them in later sessions, solving the problem that agents forget what they learned and cannot reuse experience. Key capabilities include: 1. Experience-driven skill generation: extracts reusable skill entries from task execution records to form a skill library that later sessions can load directly; 2. Continual learning and long-term capability accumulation: organizes skill evolution by time-based versions (e.g., 2026-05-09, 2026-03-23) so agent capability accumulates with use instead of starting from scratch each time; 3. Universal skill format: describes skills from different sources and versions in a consistent structure for easy installation, migration, and cross-project reuse; 4. Local skill installation: provides an installable AutoSkill Local Skill package that lands the skill library in a local environment for direct agent use; 5. Document-scenario adaptation: packages skills for document-processing scenarios via AutoSkill4Doc so document tasks can also reuse the experience-distillation mechanism.
Use Cases
Experience distillation and skill reuse during long-running agent operation, continual learning across sessions, versioned maintenance and migration of skill libraries, and skill packaging for document-processing tasks.
Target Roles
AI / Algorithm Engineer, Backend Developer, Full-stack / Indie Developer, Product Manager (PM).
TopicsTopics
RatingUser ratings
Nobody has rated this skill yet. Yours would be the first on the site — your vote becomes the initial average.
RepositoryRepository
| Skill ID | 1332 |
|---|---|
| Data source | GitHub |
| Repository | ECNU-ICALK/AutoSkill |
| Category | AI & Agents / Agent Skills & Continual Learning |
| Primary language | Python |
| License | Not specified |
| Default branch | main |
| GitHub repository ID | 1149469661 |
| Node ID | R_kgDORIOD3Q |
| Rank | #1106 (position within the source ranking) |
| Site-wide popularity rank | #1272 (computed live from Stars, across all 5833 entries) |
GrowthStar / Fork growth
One snapshot per day, tracking how Stars and Forks changed
- Now597
- Previous point · 09-28 595
- vs previous point +2
- 2 data points 13 days
- Now58
- Previous point · 09-28 58
- vs previous point ±0
- 2 data points 13 days
TimelineTimeline
Repository created2026-02-04 06:31:379 months ago
Data last updated2026-10-26 12:08:5922 days ago
Last commit2026-05-10 07:40:226 months ago
CommitLatest commit
Version [latest] committed by DrJZhou. Update Category: Codebase Iteration & Routine Maintenance. Commit details: Emphasize personal skill reuse. This update updates core functional modules and advances project iteration.