ClawHub

Handover Sync

v0.1.0

Summarize end-of-session development progress and sync project handoff documentation in Chinese or English. Use when the user asks to summarize today's chang...

⭐ 0· 69·0 current·0 all-time
by@loo-y
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Pending
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
The name/description (produce end-of-session summaries and sync handoff docs) matches the instructions: inspecting repo state, loading language-specific templates, and updating handover.md/README.md. No unrelated capabilities or secrets are requested.
ℹ
Instruction Scope
The SKILL.md explicitly instructs the agent to run git commands (git status/diff/log) and to read/write repo files (handover.md, README.md, templates). This is expected for a documentation-sync skill, but it does grant the skill permission to read and modify repository files—review edits before committing.
✓
Install Mechanism
No install spec and no bundled code; the skill is instruction-only so nothing is downloaded or installed. Low install risk.
✓
Credentials
No environment variables, credentials, or config paths are required. The requested access (git/file read/write) is proportionate to the task.
✓
Persistence & Privilege
always is false and there are no privileged persistence requests. The skill can be invoked autonomously by an agent (platform default), which is normal; it does not demand forced inclusion or cross-skill config changes.
Assessment
This skill appears coherent and low-risk for its purpose, but note it will inspect and modify repository files (run git commands and edit handover.md/README.md). Before installing or allowing autonomous runs: (1) ensure the agent has appropriate repo permissions and backups, (2) require a review/confirmation step for commits or PRs created by the skill, and (3) spot-check the templates and sample outputs to confirm language and formatting meet your expectations. If you prefer manual control, invoke the skill only on demand rather than allowing unattended/autonomous runs.

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

latestvk97fsymq5j4yevakn1q5r0jja983ew7n

License

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

Comments