Slide Deck
v1.0.0Generate beautiful HTML slide presentations from markdown or plain text. Dark theme, smooth animations, speaker notes. Output is a single HTML file that open...
⭐ 0· 66·0 current·0 all-time
byHa Le@vanthienha199
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
medium confidencePurpose & Capability
Name and description (HTML slide generation from markdown/text) align with the instructions: templates, slide rules, and output filename behavior all support the stated purpose. There are no unexpected credentials, binaries, or config paths requested.
Instruction Scope
SKILL.md limits itself to generating an HTML slide file from user content and saving it to the current directory. It references external CDN-hosted reveal.js and highlight plugins for runtime behavior; the document otherwise stays within the stated purpose. Note: it instructs file-saving to the current directory and prescribes a particular descriptive filename (one odd example uses 'agenttrace-presentation.html'), which is a minor inconsistency but not a security violation by itself.
Install Mechanism
No install spec, no code files, and no downloads. Instruction-only skills are lower risk because nothing is written or executed by the skill package itself.
Credentials
The skill requests no environment variables or credentials. There are no unexplained secret accesses or broad environment requirements.
Persistence & Privilege
Skill is not always-enabled and does not request persistent privileges. It instructs saving output to the current directory (normal for a file-generation skill) but does not modify other skills or system-wide configs.
Assessment
This skill is mostly coherent and appears to do what it says: generate an HTML slide deck from provided text/markdown. Before installing or using it, consider the following: (1) The SKILL.md asks for a 'self-contained' HTML file but uses CDN-hosted JS/CSS (reveal.js from jsdelivr). That means the resulting file will fetch external code at runtime (when opened) — if you require a fully offline single-file bundle, request that assets be embedded instead. (2) The template pulls scripts and styles from a public CDN; opening the generated file executes code from that CDN in your browser. If you have strict supply-chain or network policies, review or host trusted copies of those assets locally. (3) The file-naming guidance contains an odd example ('agenttrace-presentation.html') which looks like a leftover artifact; confirm the filename and save location before accepting writes to your filesystem. (4) Because it’s instruction-only, the package itself does not write code to disk, but the agent will save output files to the current directory — ensure you trust the agent’s working directory and check the generated HTML before sharing. If you want higher assurance, ask the skill author to (a) produce a true single-file bundle with embedded reveal.js assets or (b) remove the odd filename example and clarify exact save behavior.Like a lobster shell, security has layers — review code before you run it.
latestvk97cse9x24xzj80az77rwvmasd83qf9c
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
