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 superalp1985/fame-knowledge-agent-gateway --skill jianmu-ppt-mastergit clone --depth 1 https://github.com/superalp1985/fame-knowledge-agent-gatewayWrote 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/superalp1985/fame-knowledge-agent-gateway/jianmu-ppt-master)<a href="https://agentmods.dev/skills/superalp1985/fame-knowledge-agent-gateway/jianmu-ppt-master"><img src="https://agentmods.dev/badge/skills/superalp1985/fame-knowledge-agent-gateway/jianmu-ppt-master/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/superalp1985/fame-knowledge-agent-gateway/jianmu-ppt-master"><img src="https://agentmods.dev/badge/skills/superalp1985/fame-knowledge-agent-gateway/jianmu-ppt-master.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00085 | $0.00674 |
| Opus 5.5 | $0.00034 | $0.00270 |
| Sonnet 5.5 | $0.00017 | $0.00135 |
| Haiku 4.5 | $0.00009 | $0.00067 |
Grade A, and why
jianmu-ppt-master 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Jianmu PPT Master
Authority Order
- Jianmu Knowledge Network and project docs are authoritative.
- Frozen contracts in
src/contracts.py, module routing, task manifests, and quality gates are authoritative. - This skill is a fallback guide for PPT production technique only.
- If this skill conflicts with Jianmu knowledge, follow Jianmu and note the conflict in the handoff/audit artifact.
Core Workflow
For PPT generation inside Jianmu Agent Studio:
- Preserve the current API contract: upstream sends
PptDraftRequest; worker returnsTaskResultartifacts. - Read the topic, audience, outline, speaker notes, and style from the request. Do not invent a new user-facing brief if the request already contains one.
- Use Jianmu constraints from
build_prompt_constraints()as hidden production constraints, not visible slide text. - Produce a useful local fallback even when external PPTAgent/DeepPresenter/cloud providers are unavailable.
- Save both editable source and presentation artifact when possible:
00_ppt_request.md00_handoff_audit.json04_ppt_draft.md04_ppt_draft.pptx- optional cloud request/response artifacts
Slide Quality Rules
- One slide should carry one teaching job.
- Prefer title + 3 to 5 compact bullets, or title + one structured comparison/process/table.
- Avoid exposing worker names, routing internals, prompts, hidden constraints, or governance language in visible slides.
- Keep titles concrete and content-bearing.
- Use speaker notes as the main source for detailed teaching points.
- When source material is thin, create a conservative deck skeleton instead of fabricating facts.
- For official/course delivery, prioritize clarity, traceability, and editability over decorative visual complexity.
Fallback Generation Pattern
When advanced workers are unavailable:
- Convert outline headings into section slides.
- Split speaker notes into up to 8 detail slides.
- Export Marp markdown first.
- Convert markdown to PPTX via the local Node/pptxgenjs script if available.
- Record export errors as artifacts instead of failing silently.
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 · 67 lines · 85 tokens per session scan A c55d8cf1e6f3
jianmu-ppt-master is a skill published in the GitHub repository superalp1985/fame-knowledge-agent-gateway (10 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 85 tokens to every session and 674 once invoked, about $0.0003 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 2026-08-31.
jianmu-ppt-master compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| jianmu-ppt-mastersuperalp1985/fame-knowledge-agent-gateway | Skill | 10 | 4mo ago | Apache-2.0 | A | 85 | Claude Code, Codex |
| orbit-notionnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 117 | Claude Code, Codex |
| instrument-data-to-allotropeanthropics/knowledge-work-plugins | Skill | 35k | 2d ago | Apache-2.0 | A | 123 | Claude Code |
| apify-youtube-transcript-scrapersickn33/agentic-awesome-skills | Skill | 49k | yesterday | MIT | A | 48 | Claude Code |
| legal-holdanthropics/claude-for-legal | Skill | 9.9k | 3d ago | Apache-2.0 | A | 68 | Claude Code |
| ppt-reviewOrkas-AI/Orkas | Skill | 9.0k | yesterday | MIT | A | 2 | Claude Code, Codex |
| feishuHmbown/CodeWhale | Skill | 41k | 5d ago | MIT | A | 33 | Claude Code, Codex |