用于上下文工程、多 Agent 架构和生产 Agent 系统的 Agent 技能的全面集合。用于构建、优化或调试需要有效上下文管理的 Agent 系统。A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, or debugging agent systems that require effective context management.
active 2025-12-21 → 2026-08-06 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 229 days from 2025-12-21 to 2026-08-06. Pushes: 79 total, peak 8 in a day. Pull requests: 42 total, peak 6 in a day. Issues: 7 total, peak 2 in a day. Comments: 13 total, peak 2 in a day. Stars: 5,253 total, peak 515 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| muratcankoylan | 112 | 75 | 25 | 7 |
| cursor[bot] | 4 | 4 | 0 | 0 |
| Gujiassh | 4 | 0 | 2 | 2 |
| xiaolai | 2 | 0 | 1 | 1 |
| 04cb | 2 | 0 | 2 | 0 |
| erikpr1994 | 2 | 0 | 0 | 1 |
| CarlosArbeyBuritica | 1 | 0 | 0 | 0 |
| hande-k | 1 | 0 | 1 | 0 |
| morgan2049 | 1 | 0 | 1 | 0 |
| alhwaryasmh-cell | 1 | 0 | 0 | 0 |
| DeepDarkOdyssey | 1 | 0 | 0 | 1 |
| xue1213888 | 1 | 0 | 1 | 0 |
| luojiyin1987 | 1 | 0 | 1 | 0 |
| georgeguimaraes | 1 | 0 | 0 | 1 |
| TiagoJacinto | 1 | 0 | 1 | 0 |
| costezki | 1 | 0 | 1 | 0 |
| christso | 1 | 0 | 1 | 0 |
| liyin2015 | 1 | 0 | 1 | 0 |
| Hnturk | 1 | 0 | 1 | 0 |
| irilibee | 1 | 0 | 1 | 0 |
Recent activity
Latest issues, pull requests and releases
- Pull request#90irilibee2026-05-31 22:19
- Issue comment#85xiaolai2026-04-26 06:56fix: add missing YAML frontmatter to llm-as-judge agent files
- Pull request#85xiaolai2026-04-26 06:52
- Issue comment#70muratcankoylan2026-04-12 00:35test: cover rubric dataclass weights in evaluator
- Pull request#75Gujiassh2026-04-11 11:09
- Issue comment#56Gujiassh2026-04-11 06:08fix hosted-agents pre-sync duplicate writes
- Pull request#69morgan20492026-04-05 14:28
- Pull request#66TiagoJacinto2026-03-22 20:44
- Issue comment#34muratcankoylan2026-03-22 17:26I see every plugin installed in marketplace is same
- Issue comment#34DeepDarkOdyssey2026-03-19 02:54I see every plugin installed in marketplace is same
- Pull request#53Gujiassh2026-03-10 14:11
- Issue comment#42Gujiassh2026-03-10 06:58interleaved_thinking - Skill directory name is not a valid OpenCode skill name
- Pull request#5181442253092026-03-03 22:49
- Pull request#5004cb2026-03-01 21:09
- Pull request#5004cb2026-03-01 05:03
- Issue#45muratcankoylan2026-02-27 04:38Fix typos in documentation
- Pull request#46luojiyin19872026-02-27 04:38
- Pull request#47Hnturk2026-02-27 04:36
- Pull request#47muratcankoylan2026-02-27 04:36
- Pull request#44hande-k2026-02-26 23:40
- Issue#43CarlosArbeyBuritica2026-02-26 00:05Verific
- Issue#42pomazanbohdan2026-02-24 19:28interleaved_thinking - Skill directory name is not a valid OpenCode skill name
- Pull request#36liyin20152026-02-02 01:48
- Pull request#33muratcankoylan2026-01-13 17:30
- Pull request#33muratcankoylan2026-01-13 17:30
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 5,253 stars here means stars gained during the window, not the repo's star count.