bytedance/agentkit-samples is a collection of examples and tutorials for Volcengine AgentKit, an AI-agent development platform for building, deploying, and operating agent applications. Developers use the samples to learn agent creation, multi-agent collaboration, memory, retrieval, MCP integrations, media generation, customer service, and other workflows. The catalogue skills provide agent workflows based on these examples.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add bytedance/agentkit-samples --skill byted-mediakit-voiceover-editinggit clone --depth 1 https://github.com/bytedance/agentkit-samplesWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/bytedance/agentkit-samples/byted-mediakit-voiceover-editing)<a href="https://agentmods.dev/skills/bytedance/agentkit-samples/byted-mediakit-voiceover-editing"><img src="https://agentmods.dev/badge/skills/bytedance/agentkit-samples/byted-mediakit-voiceover-editing/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/bytedance/agentkit-samples/byted-mediakit-voiceover-editing"><img src="https://agentmods.dev/badge/skills/bytedance/agentkit-samples/byted-mediakit-voiceover-editing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 6 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 10 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 15 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Prompt Injection · line 203 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 90 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 250 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 278 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00104 | $0.04707 |
| Opus 5 | $0.00052 | $0.02354 |
| Sonnet 5 | $0.00021 | $0.00941 |
| Haiku 4.5 | $0.00010 | $0.00471 |
Grade A, and why
byted-mediakit-voiceover-editing scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.
一、模式与凭据
1.1 三种执行模式
| 模式 | 说明 | 所需环境变量 | ASR 方式 |
|---|---|---|---|
| apig | SkillHub 网关代理,Bearer Token 认证 | ARK_SKILL_API_BASE + ARK_SKILL_API_KEY(容器注入)+ VOLC_SPACE_NAME + ASR_API_KEY + ASR_BASE_URL |
豆包语音大模型 |
| cloud | 直连火山引擎 OpenAPI,HMAC 签算 | VOLC_ACCESS_KEY_ID + VOLC_ACCESS_KEY_SECRET + VOLC_SPACE_NAME + ASR_API_KEY + ASR_BASE_URL |
豆包语音大模型 |
| local | 完全本地执行,无需云端服务 | 无(可选 EXECUTION_MODE=local) |
Qwen3-ASR 本地推理 |
优先级:apig > cloud > local。自动检测按此顺序依次检查环境变量,缺参时打印 .env 路径与缺失变量列表并自动降级。
1.2 凭据配置
.env文件位置:<SKILL_DIR>/.env- 脚本先读进程环境变量,再用
.env补全未设置的项(不覆盖容器注入) ARK_SKILL_*通常由部署容器注入,不必手写到.env- 缺参不阻塞:不使用终端
input()交互,缺参时打印提示信息并自动降级到可用模式 - Agent 推荐用户通过编辑
.env文件或Agent 文件写入工具来配置变量,避免终端粘贴问题 - 安全:控制台创建仅含所需权限的密钥;测试请用独立点播空间;
.env勿提交仓库
1.3 模式意图识别(Agent 必读)
当用户在对话中表达模式切换意图时,Agent 应识别并执行:
| 用户表达 | 识别为 | 操作 |
|---|---|---|
| "用本地模式" / "不走云端" / "离线处理" | EXECUTION_MODE=local |
写入 .env 或传 --mode local |
| "用云端" / "用火山引擎" / "走 AK/SK" | EXECUTION_MODE=cloud |
写入 .env 或传 --mode cloud |
| "走网关" / "用 apig" / "用 SkillHub" | EXECUTION_MODE=apig |
写入 .env 或传 --mode apig |
隔离要求:各任务的模式选择相互独立。一个任务中切换到 local 不应影响另一个任务的模式。Agent 应在每次任务开始时重新检测或遵循用户当次指定。
二、执行约束(STRICT — NO EXCEPTIONS)
- 仅使用以下脚本,禁止创建新脚本
- 按顺序执行所有步骤,跳步即任务失败
- 执行任何脚本前必须先
cd <SKILL_DIR>/scripts - 每个 CHECKPOINT 必须验证产物后再继续
- 任何步骤失败必须立即停止并报告,不得继续
- Step 4/5/6 输出禁止简化版、占位符、示例或省略内容
- 最终输出必须保持原样,不能做任何修改
- 审核页是否自动打开由
TALKING_VIDEO_AUTO_EDIT_REVIEW_AUTO_OPEN决定(强制):Agent 不得额外执行open/start/xdg-open等命令 - 超时设置:音视频处理时长较长,宿主超时时间应设置为 60 分钟
What ships with it
59 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- examples/edl.json 1.8 KB
- examples/step6_speech_cut.json 371 B
- examples/track_witdh_request.json 2.1 KB
- examples/web-sdk.js 47 KB runs code
- LICENSE 642 B
- README.md 7.9 KB
- references/内置/ASR语义纠错.md 2.8 KB
- references/内置/EDL编辑决策格式.md 4.3 KB
- references/内置/目标平台配置.md 3.5 KB
- references/执行步骤/1. 环境检查.md 2.8 KB
- references/执行步骤/2. 语气词提示与用户行为更新.md 2.1 KB
- references/执行步骤/3. URL到ASR流水线与候选生成.md 2.8 KB
- references/执行步骤/4. ASR语义纠错.md 3.3 KB
- references/执行步骤/5. 口播剪辑.md 8.2 KB
- references/执行步骤/5.5 审核逻辑确认.md 2.0 KB
- references/执行步骤/6a. 数据预处理.md 2.3 KB
- references/执行步骤/6b. 审核与导出.md 4.5 KB
- references/执行步骤/6c. VOD导出任务提交与查询.md 1.5 KB
- references/用户规则/1-核心原则.md 435 B
- references/用户规则/10-顺句词删除.md 1.2 KB
- references/用户规则/2-语气词检测.md 1.7 KB
- references/用户规则/3-静音段处理.md 969 B
- references/用户规则/4-重复句检测.md 4.4 KB
- references/用户规则/5-卡顿词.md 932 B
- references/用户规则/6-句内重复检测.md 1.5 KB
- references/用户规则/7-连续语气词.md 559 B
- references/用户规则/8-重说纠正.md 1.5 KB
- references/用户规则/9-残句检测.md 2.1 KB
- references/用户规则/README.md 2.1 KB
- references/用户规则/变更记录.md 324 B
- scripts/api_manage.py 60 KB runs code
- scripts/apply_review_to_export.py 14 KB runs code
- scripts/asr_volc.py 6.4 KB runs code
- scripts/execution_mode.py 13 KB runs code
- scripts/export_server.py 12 KB runs code
- scripts/ffmpeg_utils.py 15 KB runs code
- scripts/local_asr.py 6.1 KB runs code
- scripts/local_av_separation.py 3.5 KB runs code
- scripts/local_denoise.py 1.2 KB runs code
- scripts/local_export.py 8.8 KB runs code
- scripts/local_media_ops.py 5.8 KB runs code
- scripts/local_subtitle.py 8.6 KB runs code
- scripts/merge_asr_words.py 4.4 KB runs code
- scripts/output_dir_resolve.py 4.8 KB runs code
- scripts/pipeline_url_to_asr.py 28 KB runs code
- scripts/prepare_export_data.py 62 KB runs code
- scripts/project_paths.py 2.1 KB runs code
- scripts/requirements-local.txt 486 B
- scripts/requirements.txt 79 B
- scripts/serve_review_page.py 22 KB runs code
- scripts/setup.sh 13 KB runs code
- scripts/step2_confirm_config.py 11 KB runs code
- scripts/track_cut_realign.py 6.9 KB runs code
- scripts/vod_direct_export.py 24 KB runs code
- scripts/vod_local_upload.py 20 KB runs code
- scripts/vod_transport.py 5.0 KB runs code
- scripts/volc_request.py 4.8 KB runs code
- templates/env.md 1.7 KB
- templates/review-page/index.html 66 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 298 lines · 104 tokens per session scan A 1d30035b1986
byted-mediakit-voiceover-editing is a skill published in the GitHub repository bytedance/agentkit-samples (453 stars, last pushed 2d ago), licensed Apache-2.0. It adds 104 tokens to every session and 4,707 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
tcapi
A helper for managing Tencent Cloud resources through Tencent Cloud's command-line API tool. Tencent Cloud is a cloud-services provider offering products such as virtual servers, storage, networks, and containers.
Market Research Brief
Generate a structured market research brief from a feature idea and supplied business context: market landscape, competitor intelligence, opportunity assessment, and a go-to-market recommendation. Use for market, research, competitor, and product launch requests.
Release Notes Generator
Generate professional software release notes from a commit log: classify changes, write user-facing summaries, draft a publishable announcement, and assess release readiness. Use for release, changelog, version, and deploy requests.
plugin-init
A project starter for creating Zhin.js plugins, which are installable packages that extend the Zhin.js bot framework. It sets up the required files, folders, package metadata, entry point, and documentation.
plugin-publish
A release guide for publishing Zhin.js plugins to npm, the JavaScript package registry, and to the Zhin plugin marketplace. It covers package metadata, versioning, release checks, and submission requirements.
plugin-develop
A development guide for adding features to Zhin.js plugins, such as chat commands, AI tools, middleware, scheduled tasks, and console pages. Zhin.js is the plugin system it targets.