Agent
v1.0.0Define agent identity, personality, voice, and boundaries to create assistants that feel authentic rather than generic.
⭐ 7· 3.1k·40 current·44 all-time
byIván@ivangdavila
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (define agent identity, voice, boundaries) match the provided documents (voice.md, boundaries.md, adaptation.md, templates.md). There are no required binaries, env vars, installs, or code files that would be unexpected for a purely authoring/templating skill.
Instruction Scope
SKILL.md and the subsidiary files focus on voice, boundaries, and learning rules and do not instruct the agent to read arbitrary local files, contact external endpoints, or exfiltrate data. A few guidance points (e.g., 'Act Without Asking' — background maintenance, fixing problems the agent created) encourage autonomous action in allowed domains; this is coherent for an identity/behavior guide but worth reviewing if the agent platform grants tool access (e.g., email/sending requests, spending money) because the guidance presumes a runtime context for autonomy.
Install Mechanism
No install spec and no code files — instruction-only. This minimizes disk writes and arbitrary code execution risk.
Credentials
No environment variables, credentials, or config paths are requested. The declared requirements are proportionate to a documentation/template skill.
Persistence & Privilege
always is false and there are no instructions to modify other skills or system-wide settings. However, the guidance does include allowances for autonomous actions in-scope; if the platform allows the agent to exercise tools/capabilities (network, email, payments), those platform-level privileges should be constrained because the skill's behavioral rules assume the agent may act without asking in some internal contexts.
Assessment
This skill is essentially a style/identity guide and is internally coherent and low-risk by itself. Before installing, confirm how your agent platform enforces: (1) what tools/actions the agent can perform (network, email, payments, file writes), and (2) whether there are sandboxing or approval workflows for actions the skill might consider 'Act Without Asking.' If the platform gives agents broad tool access, tighten permissions or test the skill in a sandbox so its autonomy rules can't trigger external communications or spending without explicit user delegation.Like a lobster shell, security has layers — review code before you run it.
latestvk9755vpm29e28d7nvk3kze945s8121aa
License
MIT-0
Free to use, modify, and redistribute. No attribution required.