Agent Sorting Hat
v0.1.0Diagnose agent role drift, team-structure problems, operating issues, and role misalignment; then redesign roles, boundaries, and team placement before perso...
⭐ 0· 32·0 current·0 all-time
by@child2d
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The name/description (agent role/team redesign) match the SKILL.md instructions. There are no unexpected required binaries, env vars, or installs — everything the skill asks the agent to do (read role/persona/team docs, diagnose, produce role maps and a change plan) is consistent with the stated purpose.
Instruction Scope
The SKILL.md is specific about steps (read role/persona/team docs, identify task chain, diagnose, redesign placement, then refine persona). It explicitly limits reading to 'only the files needed', and does not ask to call external endpoints or collect unrelated system data. However, the phrase 'read only the files needed' is somewhat open-ended and could be interpreted broadly by an agent; verify runtime access controls to ensure it only reads intended persona/team documents.
Install Mechanism
Instruction-only skill with no install spec and no code files. This minimizes surface area (no downloads, no archives, no third-party packages).
Credentials
The skill declares no environment variables, no credentials, and no config paths. Its recommended actions (reading persona/team docs and producing role maps) align with that. As a precaution, confirm that the agent runtime won't grant this skill access to unrelated secret files in the environment or registry.
Persistence & Privilege
always is false and autonomous invocation is the platform default; the skill does not request persistent presence or modify other skills or system-wide settings. This level of privilege is proportionate for a diagnostic/consulting skill.
Assessment
This skill appears coherent and low-risk because it is instruction-only and requests no credentials or installs. Before enabling it: (1) review and restrict which files the agent can access so the skill only reads intended persona/team documents (avoid exposing secrets or system configs), (2) test the skill on non-sensitive example agents to confirm its behavior matches expectations, and (3) review any structural change plans it produces before applying edits. If you are uncomfortable with autonomous invocation, consider limiting how or when the agent can call this skill.Like a lobster shell, security has layers — review code before you run it.
latestvk97fdxc55pcv9x140przngmpxx840wda
License
MIT-0
Free to use, modify, and redistribute. No attribution required.