ClawHub

Workreply Skill

v1.2.0

WorkReply is an AI workplace reply coach for professional messages that need the right balance of clarity, diplomacy, and authority. It drafts responses for...

⭐ 0· 177·0 current·0 all-time
bywes@imwyvern
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
Name/description (workplace reply drafting) match the content of SKILL.md and README; no extra binaries, env vars, or unrelated capabilities are requested.
✓
Instruction Scope
SKILL.md contains prose rules and templates for composing replies and interview coaching; it does not direct the agent to read files, environment variables, network endpoints, or send data elsewhere. No broad or vague instructions to 'gather whatever context you need' are present.
✓
Install Mechanism
This is an instruction-only skill with no install spec and no code files, so nothing is downloaded or written to disk. Low install risk.
✓
Credentials
No required environment variables, credentials, or config paths are declared or referenced in the documentation; the requested access is proportionate to a composition/assistant skill.
✓
Persistence & Privilege
Skill is not marked always:true and does not request persistent/system-level changes. It is user-invocable and allows model invocation (the platform default), which is normal for a skill of this type.
Assessment
This skill appears coherent and low-risk because it's instruction-only and asks for no credentials. Before using it: (1) Review and edit any generated reply before sending (LLMs can hallucinate or choose phrasing you may not want). (2) Avoid pasting sensitive company secrets, private attachments, or legally privileged content into prompts. (3) Confirm templates and suggested CC/BCC strategy comply with your company policies. (4) If you do not want the agent to invoke skills autonomously, keep it user-invocable only or disable autonomous invocation in your agent settings. Finally, note the package source/homepage is unknown — that affects provenance but not the internal coherence of this instruction-only skill.

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

latestvk976dyeehy6a2h08fr74jrt1w58401v9

License

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

Runtime requirements

💕🔥 Clawdis

Comments