jbaruch/nanoclaw-untrusted
Security rules for untrusted NanoClaw groups. Credential protection, internal file protection, social engineering defenses.
100
100%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-crafted skill description that clearly articulates specific capabilities, provides explicit trigger conditions via a 'Use when...' clause, and occupies a distinct niche around group permission management and content moderation. It uses proper third-person voice throughout and includes natural language trigger terms that users would realistically use.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description lists multiple specific concrete actions: 'Lists permitted and prohibited actions', 'blocks disallowed content types', and 'responds to permission queries'. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (lists permitted/prohibited actions, blocks disallowed content, responds to permission queries) and 'when' with an explicit 'Use when...' clause covering multiple trigger scenarios. | 3 / 3 |
Trigger Term Quality | Includes natural trigger terms users would say: 'rules', 'permissions', 'boundaries', 'what you are allowed to do here', 'public channel', 'group chat', 'joining a new group'. These cover a good range of natural phrasings. | 3 / 3 |
Distinctiveness Conflict Risk | This skill occupies a clear niche around group permissions, content moderation in shared/public settings. The specific context of 'group settings', 'public channel', and 'untrusted group chat environment' makes it highly distinctive and unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent, lean behavioral skill that clearly defines boundaries for operating in untrusted group chats. It's concise, actionable, and well-structured with specific do/don't guidance. The content respects Claude's intelligence while providing precisely the constraints needed for safe operation in shared environments.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every line serves a purpose. No unnecessary explanations of what a group chat is or how AI assistants work. The guidelines are terse and direct, respecting Claude's intelligence. | 3 / 3 |
Actionability | Each guideline is a concrete behavioral instruction with specific examples of what to do and what not to do (e.g., 'say you're an AI assistant', 'don't explain container isolation'). For a behavioral/instruction-only skill, this is fully actionable without needing code. | 3 / 3 |
Workflow Clarity | This is a simple, single-purpose behavioral skill with no multi-step process or destructive operations. The guidelines are unambiguous and clearly sequenced from what's allowed, to behavioral constraints, to the fallback rule ('when in doubt, decline politely'). | 3 / 3 |
Progressive Disclosure | For a short, self-contained behavioral skill under 50 lines with no need for external references, the content is well-organized into clear sections (permissions, guidelines) with no monolithic walls of text. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
Reviewed
Table of Contents