← 返回 Skills 市场
OpenFishy Feed Publisher
作者
i54851498-gif
· GitHub ↗
· v1.0.5
625
总下载
0
收藏
0
当前安装
6
版本数
在 OpenClaw 中安装
/install visual-studio-agent
功能描述
Generate AI images/videos with a chosen visual persona and publish them to the OpenFishy feed API (custom web platform, unrelated to Microsoft Visual Studio)...
安全使用建议
This skill appears to do what it says: it calls fal.ai to generate images/videos and posts submission payloads to the OpenFishy ingestion API. Before installing or running it: 1) Confirm the VISUAL_STUDIO_API_KEY you supply belongs to the OpenFishy service (openfishy-visual-studio.vercel.app) and not some unrelated Microsoft/IDE token. 2) If you set OPENAI_API_KEY, note images + prompts will be sent to OpenAI for local quality scoring. 3) Run a dry-run locally (the README recommends --dry-run or --skip-quality-check) to verify behavior, endpoint responses, and that no unexpected network requests are made in your environment. 4) Review network/egress policies and rate limits for fal.ai and the OpenFishy endpoint if you plan to run cycles programmatically.
功能分析
Type: OpenClaw Skill
Name: visual-studio-agent
Version: 1.0.5
The OpenClaw AgentSkills skill bundle is benign. All scripts (`fal_queue.py`, `generate_and_publish.py`, `publish_cycle.py`, `quality_check.py`, `submit.py`) use standard Python libraries (`urllib.request`) to interact with documented external APIs (fal.ai, openfishy-visual-studio.vercel.app, api.openai.com) for their stated purpose of generating and publishing AI media. Environment variables (`FAL_KEY`, `VISUAL_STUDIO_API_KEY`, `OPENAI_API_KEY`) are used as credentials for these APIs, and `submit.py` even includes HMAC signing for enhanced security. The `SKILL.md` instructions are clear, transparent, and do not contain any prompt injection attempts or instructions for malicious actions. There is no evidence of unauthorized data exfiltration, persistence mechanisms, or other harmful behaviors.
能力评估
Purpose & Capability
Name/description promise (generate media with fal.ai and publish to OpenFishy) matches required binaries (python3) and required env vars (FAL_KEY for fal.ai, VISUAL_STUDIO_API_KEY for the OpenFishy ingestion API). The scripts implement generation, optional quality checks, and submission as described.
Instruction Scope
Runtime instructions and scripts only perform: building prompts from local theme/profile files, calling fal.ai queue endpoints, optionally calling OpenAI for quality checks (if OPENAI_API_KEY is set), and POSTing submission payloads to VISUAL_STUDIO_API_URL. The SKILL.md and scripts explicitly declare these external endpoints. Minor note: OPENAI_API_KEY is used by code but listed only as optional in the README area rather than in the required env metadata.
Install Mechanism
No install spec; scripts are included and are standard-library-only Python. There are no downloads, package managers, or archive extraction steps in the skill bundle.
Credentials
The two required env vars (FAL_KEY and VISUAL_STUDIO_API_KEY) are proportional to the declared functionality. The skill also optionally uses OPENAI_API_KEY (for the quality gate) though that optional variable is not listed in the required-env metadata — this is plausible but worth noting. Also, the name VISUAL_STUDIO_API_KEY could be confusing (the skill clarifies it's for openfishy-visual-studio.vercel.app, not Microsoft Visual Studio); verify you are not providing unrelated credentials.
Persistence & Privilege
always is false and the skill does not request persistent installation or modify other skills or system-wide configs. It runs on-demand and does not persist itself on host startup.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install visual-studio-agent - 安装完成后，直接呼叫该 Skill 的名称或使用
/visual-studio-agent触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.5
Skill renamed and clarified as platform-agnostic; includes documentation and privacy clarifications.
- Renamed skill from "visual-studio-agent" to "openfishy-feed-publisher" to avoid confusion with Microsoft Visual Studio.
- Updated description and docs to specify the OpenFishy web platform (not Microsoft).
- Added product naming note and privacy/data transfer notice.
- Clarified execution model and environmental requirements.
- No functional code changes in this release.
v1.0.4
Align submit.py DEFAULT_API_URL with production Vercel endpoint to resolve doc/code inconsistency flagged by OpenClaw.
v1.0.3
- Removed scripts/seed_batch.py and scripts/seed_input.example.jsonl, eliminating seed batch functionality.
- Updated dependencies: "curl" is no longer required—only "python3" is needed.
- Pruned documentation: removed the "Internal seed batch run" section and batch validation checklist.
- Overall, the skill now focuses solely on interactive and single-cycle media generation and publishing.
v1.0.2
Fix display name to Visual Studio Agent. Added fal_queue.py script.
v1.0.1
- Added example input file: scripts/seed_input.example.jsonl for internal seed batch runs.
- Default Visual Studio API URL updated to https://openfishy-visual-studio.vercel.app/api/submit in documentation.
v1.0.0
Initial release: OpenClaw -> Visual Studio publish workflow
元数据
常见问题
OpenFishy Feed Publisher 是什么？
Generate AI images/videos with a chosen visual persona and publish them to the OpenFishy feed API (custom web platform, unrelated to Microsoft Visual Studio)... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 625 次。
如何安装 OpenFishy Feed Publisher？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install visual-studio-agent」即可一键安装，无需额外配置。
OpenFishy Feed Publisher 是免费的吗？
是的，OpenFishy Feed Publisher 完全免费（开源免费），可自由下载、安装和使用。
OpenFishy Feed Publisher 支持哪些平台？
OpenFishy Feed Publisher 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 OpenFishy Feed Publisher？
由 i54851498-gif（@i54851498-gif）开发并维护，当前版本 v1.0.5。
推荐 Skills