Social Carousel Writer
v1.0.0LinkedIn and Instagram carousel script writer. Generate complete slide-by-slide carousel content with hooks, value slides, and CTAs that drive saves and shar...
⭐ 0· 97·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description match the provided artifacts: SKILL.md and analyze.sh both implement a carousel-writer prompt and examples. There are no unrelated binaries, credentials, or config paths required.
Instruction Scope
Runtime instructions and the included analyze.sh remain focused on generating carousel text/design notes. Minor inconsistency: SKILL.md 'What You Get' states a 20-hashtag set, while the analyze.sh prompt requests 30 hashtags split into 3 tiers (10/10/10). The script invokes the local 'openclaw agent' CLI and python3 to format output — expected for this skill but worth noting because it executes a local tool.
Install Mechanism
No install spec is present (instruction-only). The only file is a short shell script; nothing is downloaded or written to arbitrary locations.
Credentials
The skill declares no required environment variables, no secrets, and does not attempt to access system config paths. The analyze.sh script also does not read or require environment credentials.
Persistence & Privilege
Flags are default (always: false). The skill does not request persistent system presence or modify other skills/settings. It does call the local OpenClaw CLI when run, which is normal for an instruction that delegates work to a local agent.
Assessment
This skill appears to do what it says: generate slide-by-slide carousel scripts. Before running: (1) review the repository yourself (or the analyze.sh) to confirm it contains only the prompt and harmless parsing logic; (2) be aware the provided script runs your local 'openclaw agent' CLI and python3 — that will use whatever model/credentials your local agent is configured with; (3) note the small content mismatch (SKILL.md promises 20 hashtags but the script requests 30) — decide which behavior you want and, if needed, edit the prompt locally; (4) because allowed-tools includes Bash, only run the script from sources you trust and inspect any skill that executes shell commands to ensure no unexpected side effects.Like a lobster shell, security has layers — review code before you run it.
latestvk974m27npc9z9447vff5yvq6fs83ewc9
License
MIT-0
Free to use, modify, and redistribute. No attribution required.