message-friendly
v1.0.1Optimizes Markdown-formatted messages for IM platforms (WeChat, DingTalk, etc.) by removing unsupported markup and using clean text layouts.
⭐ 0· 144·0 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
The skill's name, description, SKILL.md rules, and _meta.json filter are coherent: all describe Markdown-to-IM plain-text conversion. Nothing requested (no env, no binaries, no installs) is out-of-scope for that purpose. Note: the ownerId in the provided _meta.json (kn70py...) does not match the registry ownerId (kn7c6r...), which could be a metadata inconsistency worth verifying.
Instruction Scope
SKILL.md gives explicit, narrowly-scoped rules for converting Markdown elements to plain text (headings, emphasis, lists, links, images, code blocks, tables, dividers, emojis). It does not instruct the agent to read unrelated files, access credentials, or call external endpoints. No open-ended "gather whatever context you need" language is present.
Install Mechanism
No install spec and no code files — this is instruction-only. That minimizes risk because nothing is downloaded or written to disk by the skill itself.
Credentials
The skill declares no required environment variables, credentials, or config paths. The actions described do not need secrets or external service access, so the requested environment access is proportionate.
Persistence & Privilege
Top-level flags show always:false, but _meta.json includes "trigger": "auto", a channel filter and a high priority (10). That suggests the skill is intended to auto-run when messages in the listed channels match the filter (presence of Markdown tokens). This is reasonable for a formatter, but you should be aware it may be invoked automatically in matched channels rather than only on explicit user invocation.
Assessment
This skill is internally consistent and low-risk: it only describes how to reformat Markdown into IM-friendly plain text and asks for no credentials or installs. Before installing, verify the author/source (ownerId mismatch in metadata might be a packaging error), and test the skill with non-sensitive sample messages to confirm it behaves as you expect. Note that auto-trigger metadata means it may run automatically in channels that match its filter (e.g., messages containing Markdown characters) — if you don't want automatic invocation, confirm how your platform controls skill triggers. Finally, remember link extraction will produce plain-text URLs and image placeholders locally in the output — the skill does not indicate any external transmission, but avoid sending private secrets through it during testing.Like a lobster shell, security has layers — review code before you run it.
latestvk970w294ry1jj1xj8r2gxcye9d839y7y
License
MIT-0
Free to use, modify, and redistribute. No attribution required.