ClawHub

Practice Session Check-in

v1.0.1

Public-safe practice session intake, start confirmation, reminder flow, completion check, and follow-up tracking.

⭐ 0· 64·0 current·0 all-time
by@ztl970
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
The name and description (practice intake, confirmation, reminder, completion, follow-up) match the SKILL.md instructions. The skill requests no binaries, env vars, or installs — all appropriate for a reusable instruction template.
ℹ
Instruction Scope
SKILL.md stays within the declared scope and explicitly forbids collecting sensitive or identifying data. One implementation gap: the instructions expect the assistant to 'send a reminder at the confirmed time' but there is no code/install/scheduler or delivery channel in the package — this is normal for an instruction-only template, but you should verify how your agent/platform will actually schedule and deliver reminders before relying on it.
✓
Install Mechanism
No install spec and no code files that execute — lowest risk. The skill is instruction-only, so it won't drop binaries or archives on disk.
✓
Credentials
The skill requires no environment variables, credentials, or config paths. There are no requests for unrelated secrets or system access in the instructions.
ℹ
Persistence & Privilege
Defaults are conservative: always:false and model invocation allowed (the platform default). agents/openai.yaml sets allow_implicit_invocation: true, which permits the agent to call this skill implicitly — that is expected for a user-invocable helper. This is not excessive on its own, but be aware implicit invocation means the agent may call the template when it thinks it's relevant.
Assessment
This skill is an instruction/template only and does not ask for credentials or install software — good for public-safe use. Before enabling it in production, confirm how your agent/platform will actually deliver scheduled reminders (calendar integration, messaging, or a scheduler) because the skill itself provides no delivery mechanism. Also: keep examples and inputs generic (no real names, institutions, or private schedules) and verify what implicit-invocation policy your agent platform uses so you control when the skill can be called automatically.

Like a lobster shell, security has layers — review code before you run it.

latestvk97fp4cmj651eyhbmtqhsz034h83mze1

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments