Principle Comparator
v1.0.3Compare two sources to find shared and divergent principles — discover what survives independent observation.
⭐ 0· 1.1k·2 current·2 all-time
byLee Brown@leegitw
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 SKILL.md all describe extracting and comparing principles; there are no declared binaries, env vars, or installs that would be out of scope for that purpose.
Instruction Scope
SKILL.md provides a focused, explicit methodology (normalization, alignment, N-count rules) and does not instruct reading system files or unrelated env vars. It explicitly states it uses the agent's configured model for processing; if that model is cloud-hosted, the user's data will be sent to that provider as part of normal agent operation (this is expected but worth noting).
Install Mechanism
No install spec and no code files — instruction-only skill. No downloads or on-disk installs are requested.
Credentials
The skill declares no required environment variables, credentials, or config paths. The SKILL.md does not reference hidden secrets or unrelated credentials.
Persistence & Privilege
always is false and there is no request for permanent agent presence or changes to other skills/configurations. Autonomous invocation (model-invocation not disabled) is the platform default and is not combined with other concerning privileges.
Scan Findings in Context
[no_regex_findings] expected: The static scanner found no code-level patterns — expected because this is an instruction-only skill (SKILL.md only). Absence of findings is not a substitute for reading the instructions, which was done above.
Assessment
This skill appears internally consistent and appropriate for comparing two sources' principles. Before installing or using it, consider: (1) If you send sensitive or confidential texts, those will be processed by whatever model your agent is configured to use (e.g., a cloud LLM) — redact secrets if needed. (2) The skill normalizes language and may lose nuance; review its normalized/prioritized outputs rather than treating them as definitive. (3) N=2 agreement is a validation heuristic, not proof; verify independently for critical conclusions. If those caveats are acceptable, the skill's scope and requested access are proportionate.Like a lobster shell, security has layers — review code before you run it.
agreementvk9792v7a3n9hjzx3x6j2j5y4yx83k2tealignmentvk9792v7a3n9hjzx3x6j2j5y4yx83k2teanalysisvk9792v7a3n9hjzx3x6j2j5y4yx83k2tecommon-groundvk9792v7a3n9hjzx3x6j2j5y4yx83k2tecomparisonvk9792v7a3n9hjzx3x6j2j5y4yx83k2tediffvk9792v7a3n9hjzx3x6j2j5y4yx83k2telatestvk9792v7a3n9hjzx3x6j2j5y4yx83k2teopenclawvk9792v7a3n9hjzx3x6j2j5y4yx83k2teprinciplesvk9792v7a3n9hjzx3x6j2j5y4yx83k2tesynthesisvk9792v7a3n9hjzx3x6j2j5y4yx83k2te
License
MIT-0
Free to use, modify, and redistribute. No attribution required.