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-market-insight-agentgit 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-market-insight-agent)<a href="https://agentmods.dev/skills/bytedance/agentkit-samples/byted-market-insight-agent"><img src="https://agentmods.dev/badge/skills/bytedance/agentkit-samples/byted-market-insight-agent/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-market-insight-agent"><img src="https://agentmods.dev/badge/skills/bytedance/agentkit-samples/byted-market-insight-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00269 | $0.01947 |
| Opus 5 | $0.00134 | $0.00974 |
| Sonnet 5 | $0.00054 | $0.00389 |
| Haiku 4.5 | $0.00027 | $0.00195 |
Grade A, and why
byted-market-insight-agent 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 7d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Market Insight Agent — 火山引擎市场洞察助手
用途与设计目标
本 Skill 旨在为 Agent 提供一个统一、稳定且无感的市场洞察服务调用入口。它整合了 market-insight-agent-v2-optimized（零依赖 Gateway 版本）和 market-insight-agent-portable-sdk（官方 SDK 版本）的优点，实现了以下目标：
- 统一调用路径：无论底层采用 API Gateway 还是官方 SDK，对 Agent 而言，始终通过
scripts/client.py中list_custom_subs_task、pull_post、query_clue_info三个函数以相同的方式调用。 - 动态 Provider 选择：默认优先使用 API Gateway 方式。同时，Skill 能够根据当前环境（如环境变量配置）和运行时状态（如某条链路连续失败）动态地、智能地选择最佳调用路径。
- SDK 自动安装：当需要使用 SDK 路径但环境中未安装
volcengine-python-sdk时，Skill 会自动尝试安装，实现真正的“开箱即用”。 - 状态与凭证持久化：Skill 会将其运行状态（如上次成功的 Provider）和用户提供的凭证（若通过“最小化询问”获得）持久化到 Skill 私有的
persist/目录中，实现会话间的状态保持和凭证复用。 - 最小化询问：仅在完全没有可用凭证或所有链路均认证失败时，才向 Agent 层发出明确的“最小化询问”请求，由 Agent 决定何时以及如何向用户获取凭证，避免了不必要的打扰。
触发场景
当需要与火山引擎市场洞察服务交互时，应使用本 Skill。具体场景包括但不限于：
- 品牌声量监测：获取关于特定品牌或产品的社交媒体讨论。
- 竞品动态追踪：监控竞争对手的市场活动、用户反馈。
- 行业趋势分析：通过分析公开数据发现行业热点与变化。
- 热点话题总结：对特定事件或话题进行深入的内容挖掘与分析。
- 监控任务管理：查询、管理在市场洞察平台创建的订阅/监控任务。
- 商机线索查询：拉取由 AI 生成的、包含 ACOR 评估、公司画像等的结构化商机线索。
Provider 选择策略
Skill 内部通过 scripts/auth_resolver.py 实现了一套智能的 Provider 选择策略，其决策顺序如下：
- 会话粘性优先：如果上一次调用成功，则优先复用该 Provider（Gateway 或 SDK），以保证链路稳定性。
- 默认优先级：在没有历史成功记录的情况下，默认按以下顺序尝试：
- API Gateway：检查是否存在
ARK_SKILL_API_BASE和ARK_SKILL_API_KEY环境变量。此路径无任何第三方 Python 库依赖，是首选。 - 官方 SDK：检查是否存在
VOLCSTACK_ACCESS_KEY_ID和VOLCSTACK_SECRET_ACCESS_KEY环境变量。
- API Gateway：检查是否存在
- 动态降级：如果某个 Provider 连续出现鉴权失败（401/403）或网络不可达，它将被临时标记为“降级”状态，在一段时间内自动切换到备用 Provider。
- 最小化询问触发：当上述所有路径均因缺少凭证而无法使用时，Skill 会抛出
MissingCredentialsError，并附带清晰的提示，告知 Agent 层应如何向用户请求凭证。
更多细节请参考 references/usage.md。
危险操作限制
为了确保安全与合规，本 Skill 严格遵守以下限制：
- 不执行
aime skill upload或aime skill enable：Skill 的打包和部署应由用户或上层 CICD 流程明确发起，Skill 本身不包含任何自动上传或启用的逻辑。 - 不硬编码凭证：所有 API Key、AK/SK 等敏感信息均通过环境变量或持久化的
persist/auth.json文件读取，代码中不包含任何硬编码的凭证。 - 日志脱敏：在打印 Debug 日志时，会自动对 API Gateway 地址、API Key 等敏感信息进行脱敏处理，仅打印非敏感的调用摘要。
- 持久化目录隔离：所有持久化文件（状态、凭证）均存储在 Skill 根目录下的
persist/目录中，确保与工作空间的其他部分隔离。
What ships with it
8 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.
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.
- 7d ago First seen · 81 lines · 269 tokens per session scan A 1b1663e1f816
byted-market-insight-agent is a skill published in the GitHub repository bytedance/agentkit-samples (450 stars, last pushed 7d ago), licensed Apache-2.0. It adds 269 tokens to every session and 1,947 once invoked, about $0.0013 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
ensembl-database
Query Ensembl genome database REST API for 250+ species. Gene lookups, sequence retrieval, variant analysis, comparative genomics, orthologs, VEP predictions, for genomic research.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.
aatmf-t10-confidentiality-breach
AATMF T10 — Integrity & Confidentiality Breach. System prompt extraction, training-data extraction, model-weight leakage, private-key recovery.
sidewinder-rattlesnake
Adversary-emulation profile for SideWinder (G0121 / Rattlesnake / T-APT-04 / Razor Tiger), India's suspected state-sponsored cyber-espionage actor.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
sn-image-imitate
An image tool that creates new content while following the visual style and layout of a single reference image.