# evalstate/fast-agent repository brief

> This is an EasyGlobe-authored bilingual repository brief, not a redistributed third-party Skill and not an installable copy of the repository. Review the upstream repository before use.

## English

Code, Build and Evaluate agents - excellent Model and Skills/MCP/ACP/A2A Support

EasyGlobe verified this public, non-fork, non-archived repository at commit `610a2f575c469134479f2101f92255aa4bc642a3`. The sampled tree contains 2 `SKILL.md` files and at least one sampled file has valid `name` and `description` frontmatter. Its primary directory category is Office Documents. Static sampling did not find the high-risk credential-exfiltration or destructive-root-delete patterns checked by the research pipeline; this is not a full security audit.

## 中文

evalstate/fast-agent 是一个面向办公文档工作流的 GitHub Skill 仓库。EasyGlobe 在提交 `610a2f575c469134479f2101f92255aa4bc642a3` 对公开、非 fork、未归档的默认分支进行了抽样核验：仓库树包含 2 个 `SKILL.md` 文件，且至少一个抽样文件具有有效的 `name` 与 `description` frontmatter。静态抽样未命中本流水线检查的凭据外传或根目录破坏性命令模式；这不等同于完整安全审计，使用前仍应检查上游仓库。

## Repository metadata

| Field | Value |
| --- | --- |
| Repository | [evalstate/fast-agent](https://github.com/evalstate/fast-agent) |
| Hot rank / score | 64 / 46.68 |
| Stars at verification | 3897 |
| Default branch | `main` |
| Sampled commit | `610a2f575c469134479f2101f92255aa4bc642a3` |
| Last push | 2026-08-20T21:22:32Z |
| Verified | 2026-08-21T03:25:24.715Z |
| License | Apache-2.0 |
| SKILL.md paths in sampled tree | 2 |

## Representative valid Skill evidence

| Path | Frontmatter name | Frontmatter description | SHA-256 |
| --- | --- | --- | --- |
| `examples/hf-toad-cards/skills/pr-writing-review/SKILL.md` | pr-writing-review | Extract and analyze writing improvements from GitHub PR review comments. Use when asked to show review feedback, style changes, or editorial improvements from a GitHub pull request URL. Handles both explicit suggestions and plain text feedback. Produces structured output comparing original phrasing with reviewer suggestions to help refine future writing. | `9a9960b41f6de9b8ebe997439dedb703125cd21ce40846ad9795c53f1665f2c8` |
| `examples/hf-toad-cards/skills/session-investigator/SKILL.md` | session-investigator | Investigate fast-agent session and history files to diagnose issues. Use when a session ended unexpectedly, when debugging tool loops, when correlating sub-agent traces with main sessions, or when analyzing conversation flow and timing. Covers session.json metadata, history JSON format, message structure, tool call/result correlation, and common failure patterns. | `d8df6fafb1dc731ec88908b6be427bb4600f76f1d2506f6c5378b68df41f24ef` |

Source: https://github.com/evalstate/fast-agent