Crucial Conversations Coach
v1.0.0Friendly executive life coach for crucial conversations based on the "Tools for Talking When Stakes Are High" methodology. Mimics the "Crucial Conversations Coach" GPT. Use when the user needs help preparing for, navigating, or debriefing high-stakes conversations, phrasing emails for win-win outcomes, or convincing others while maintaining safety and respect.
⭐ 3· 2.1k·6 current·6 all-time
byMark Pors 🦖@pors
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name, description, and included files all describe a conversational coaching persona using the 'Crucial Conversations' methodology. There are no unrelated dependencies, credentials, binaries, or config paths requested that would be inconsistent with a coaching skill.
Instruction Scope
SKILL.md gives clear, bounded instructions for assessing situations, drafting and refining messages, and references the included theory.md for technique details. It does not instruct the agent to read arbitrary system files, access environment variables, contact external endpoints, or collect unrelated data.
Install Mechanism
No install spec or code; instruction-only skills have minimal attack surface because nothing is written to disk and no external installers are run.
Credentials
The skill declares no required environment variables, credentials, or config paths. This is proportionate for a coaching persona that only needs conversational input.
Persistence & Privilege
always is false and the skill is user-invocable; it does not request persistent system privileges or modify other skills. Model invocation is enabled (default), which is expected for a conversational skill.
Assessment
This skill appears coherent and safe from a packaging perspective, but keep in mind: (1) Any sensitive or personally identifying information you share with the skill will be sent to whichever model/runtime your agent uses — avoid sharing secrets, private medical/legal details, or credentials. (2) The skill provides coaching based on a book's methodology; it is not a substitute for professional legal, medical, or psychiatric advice. (3) Because it can be invoked by the agent, verify your agent policies if you want to restrict autonomous invocation. If you need stricter privacy, review where your agent sends model queries or avoid entering sensitive details into the conversation.Like a lobster shell, security has layers — review code before you run it.
latestvk973r9bz9g76560z9rp1hjk8th80cac8
License
MIT-0
Free to use, modify, and redistribute. No attribution required.