Deck Narrative Planner
v1.0.0把材料转成 PPT/Deck 叙事结构，生成每页一句标题、证据需求与过渡逻辑。；use for presentation, deck, storytelling workflows；do not use for 直接生成花哨视觉稿, 编造证据.
⭐ 0· 191·0 current·0 all-time
byvx：17605205782@52yuanchangxing
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description, declared requirements (python3), resource files (spec/template/examples) and the included script all align with a tool that converts input materials into a structured deck narrative. There are no unrelated required binaries, env vars, or config paths.
Instruction Scope
SKILL.md keeps scope narrow: produce structured drafts, list missing info, and only run the included local script if environment permits. The script can also scan directories and many file types and runs local file reads (markdown, code, csv, etc.) and pattern scanning for potentially sensitive tokens — this is appropriate for auditing content but means the user must avoid pointing the tool at sensitive system directories or secrets. The SKILL.md explicitly warns not to fabricate evidence and to avoid external system changes.
Install Mechanism
No install spec — instruction-only plus a local Python script. This is low-risk: nothing is downloaded from external URLs and the script depends only on the Python standard library.
Credentials
No environment variables, credentials, or config paths are requested. The lack of requested secrets matches the described functionality.
Persistence & Privilege
The skill is not forced-always or otherwise persistent. It is user-invocable and can be run by the agent (normal behavior). It does not modify other skills or system-wide configs.
Assessment
This skill appears to do what it says: generate a structured deck narrative from given materials using a local Python script and templates. Before running/installing: (1) review the scripts/run.py if you are concerned (it is included and readable); (2) do not point the tool at system/root or directories containing secrets — the script can recursively read many file types and will report file contents/headings and look for secret-like patterns; (3) prefer running with --dry-run or confined to a sandboxed project directory; (4) avoid providing sensitive personal data or credentials as input; (5) the skill does not perform network calls or require credentials, so network/data exfiltration risk is low when used as intended.Like a lobster shell, security has layers — review code before you run it.
latestvk970fajh6gxd8bv2g5n2cg0465831grv
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🖼️ Clawdis
OSmacOS · Linux · Windows
Binspython3