Group Summarizer
v1.0.0Synthesizes member-parent markdown reports into a continuous narrative.
⭐ 0· 100·0 current·0 all-time
byDean Lee@deanleefumu
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name and description match the runtime instructions: the skill reads markdown reports, groups by parent folder (team member), synthesizes narrative updates, and writes a markdown output. It does not request unrelated credentials or binaries.
Instruction Scope
The SKILL.md explicitly instructs the agent to read all markdown files under ~/openclaw_agent/src/temp_sync/ recursively and write a summarized file to ~/openclaw_agent/src/latest_summaries/daily/{{date}}.md. This is appropriate for the stated task, but it does grant the skill access to any files placed under that path (so the directory contents should be limited to the intended reports).
Install Mechanism
There is no install spec and no code shipped with the skill (instruction-only), so nothing is downloaded or written to disk by an installer.
Credentials
The skill declares no environment variables, credentials, or config paths beyond the two explicit file paths it reads/writes; requested access is proportional to the task.
Persistence & Privilege
The skill writes persistent output to a target path in the agent workspace. always is false (not force-included). The skill can be invoked autonomously by the agent (disable-model-invocation is false by default), so consider invocation policies if you want to avoid automatic runs.
Assessment
This skill appears coherent and does only what it describes: read markdown reports from ~/openclaw_agent/src/temp_sync/, synthesize them, and write a dated markdown file. Before installing or enabling it: (1) confirm that only intended team-report files are placed under ~/openclaw_agent/src/temp_sync/ (avoid storing unrelated or sensitive files there); (2) ensure the target output directory is acceptable and has proper permissions/backup policies; (3) if you do not want the agent to run this autonomously, disable autonomous invocation or control when the skill is invoked; (4) test the skill on a small sample folder to verify formatting and that no unintended content (meta or generation artifacts) is included in the summaries.Like a lobster shell, security has layers — review code before you run it.
latestvk978553r1p8e2kmtte1np8phwn837t57
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🦞 Clawdis