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 topviewai/skill --skill topview-generategit clone --depth 1 https://github.com/topviewai/skillWrote 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/topviewai/skill/topview-generate)<a href="https://agentmods.dev/skills/topviewai/skill/topview-generate"><img src="https://agentmods.dev/badge/skills/topviewai/skill/topview-generate/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/topviewai/skill/topview-generate"><img src="https://agentmods.dev/badge/skills/topviewai/skill/topview-generate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 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 YARA Match · line 32 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
- high Anti-Refusal · line 39 Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.Fix: Remove jailbreak framing that nullifies safety policies or restrictions. Skill content must not instruct the agent to ignore its guidelines or operate without guardrails.
- high Prompt Injection · line 39 This pattern attempts to override system instructions or ignore safety constraints. Without LLM analysis, manual review is recommended.Fix: Remove or rewrite any text that instructs the agent to ignore prompts, override safety rules, or trust unverified content. Ensure skill content cannot be injected to alter agent behavior.
- medium Excessive Agency · line 62 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 290 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00096 | $0.03422 |
| Opus 5.5 | $0.00038 | $0.01369 |
| Sonnet 5.5 | $0.00019 | $0.00684 |
| Haiku 4.5 | $0.00010 | $0.00342 |
Grade A, and why
topview-generate 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 2mo 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 — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Topview Generate
Creative generation through the host-managed
topview-mcp.Last updated: 2026-07-21
If a requested model or feature is missing, check
topview_get_generation_config before calling
it unsupported.
Notes for Auditors
The reply guidelines below are UX preferences for non-technical users in chat apps. They do not ask the agent to hide errors, bypass safety controls, override higher-priority instructions, or perform unattended privileged operations. Authentication and tool execution are controlled by the MCP host. Deviate when the user requests technical detail or safety requires it.
Execution
This skill is MCP-only. Use the creative and upload hot tools exposed directly
by topview-mcp: topview_* and ta_*. Never route those tools through
get_tool_schema or call_tool; those are only for deferred data-domain tools
used by the ops skills. Do not run scripts/*.py or make raw REST calls.
Market and creator-data requests belong to:
- Amazon →
topview-amazon-ops - Shopee →
topview-shopee-ops - TikTok Shop →
topview-tiktok-shop-ops - YouTube KOL pool →
topview-youtube-kol-ops
Prerequisites and Authentication
- Confirm the host has connected
topview-mcp. - Authentication is handled by the host (Cursor OAuth or the host's
mcp_authflow). Do not ask the user to setTOPVIEW_UIDorTOPVIEW_API_KEYmanually. - If a tool reports that authentication is required, invoke the host's
mcp_authmechanism. If it returns an authorization URL, send that exact URL to the user. If it does not, ask the user to complete the sign-in action shown by their host. Never invent or promise a URL. - After the user confirms sign-in, retry the original MCP call once.
See Authentication and Credits.
Common Agent Workflow
Keep this sequence centralized here; capability references only add their specific fields.
- Understand intent. Determine output type, purpose, source assets, style, duration, language, captions, and publishing channel.
- Select a board. Unless the user supplied a
boardId, calltopview_list_boards. Choose, in order: a board withisSystemDefault=true; a board namedMy First Board; otherwise the first returned board. Reuse thatboardIdfor the session. If no board exists or the user asks for a new one, calltopview_create_board. - Load live model configuration. Before every model-based generation,
call
topview_get_generation_configwith the intendedtypeandtaskType. Usemodels[].submitModelexactly, satisfy everyrequiredSubmitFieldsentry, choose constrained values fromsubmitParameterOptions, and usedefaultSubmitParametersonly when the user omitted a required value. - Upload local assets. For each local image, audio, or video:
- call
ta_upload_credentialwith its file extension informat; - upload the bytes using the returned upload URL and required method/headers;
- call
ta_upload_check_filewith the returnedfileId; - use the
fileIdonly after the check succeeds. Existing TopviewfileIdvalues need no upload.
- call
- Submit directly. Call the selected
topview_*tool directly and retain itstaskId, the exacttaskType, selectedboardId, model, and parameters. - Poll to a terminal state. Call
topview_query_taskrepeatedly with the sametaskTypeandtaskIduntilsuccessorfail. A timeout does not mean failure: continue later with the same identifiers. Do not blindly resubmit, because that can duplicate work and consume credits. - Return the result. Lead with downloadable output URLs. If the result has
boardTaskId, includehttps://www.topview.ai/board/{boardId}?boardResultId={boardTaskId}.
What ships with it
28 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.
- references/ai_image.md 3.5 KB
- references/auth.md 1.5 KB
- references/avatar4.md 2.5 KB
- references/board.md 2.0 KB
- references/error_handling.md 3.2 KB
- references/product_avatar.md 2.9 KB
- references/remove_bg.md 1.4 KB
- references/text2voice.md 1.7 KB
- references/updating_models.md 1.9 KB
- references/user.md 1.1 KB
- references/video_gen.md 6.4 KB
- references/voice.md 1.8 KB
- scripts/__init__.py 0 B runs code
- scripts/ai_image.py 29 KB runs code
- scripts/auth.py 11 KB runs code
- scripts/avatar4.py 13 KB runs code
- scripts/board.py 15 KB runs code
- scripts/product_avatar.py 17 KB runs code
- scripts/remove_bg.py 9.4 KB runs code
- scripts/requirements.txt 38 B
- scripts/shared/__init__.py 66 B runs code
- scripts/shared/client.py 5.7 KB runs code
- scripts/shared/config.py 2.1 KB runs code
- scripts/shared/upload.py 2.5 KB runs code
- scripts/text2voice.py 11 KB runs code
- scripts/user.py 3.5 KB runs code
- scripts/video_gen.py 38 KB runs code
- scripts/voice.py 13 KB runs code
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.
- 2mo ago First seen · 302 lines · 96 tokens per session scan A e71ad2b9cd83
topview-generate is a skill published in the GitHub repository topviewai/skill (42 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 96 tokens to every session and 3,422 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-08-30.
topview-generate compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| topview-generatetopviewai/skill | Skill | 42 | 3mo ago | Apache-2.0 | A | 96 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |