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 uses natural language terms users would employ. It occupies a distinct niche around group permission management and content moderation, making it easy to distinguish from other skills. The description uses proper third-person voice throughout.
| 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 | The description carves out a clear niche around group permissions, content moderation in shared/public settings. The combination of 'group settings', 'permissions', 'public channel', and 'untrusted group chat' 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 skill that clearly defines behavioral boundaries for untrusted group chat environments. It provides specific, actionable guidance with concrete examples of what to say and what to avoid, all in a compact format. The bold lead sentences followed by elaboration make it easy to scan and internalize.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every line earns its place. No unnecessary explanations of what a group chat is or how AI assistants work. The guidelines are tight and assume Claude's intelligence. | 3 / 3 |
Actionability | Each guideline is concrete and specific: exact phrases to use ('I can't do that in this chat'), specific behaviors to avoid (don't explain container isolation), clear decision rules (follow owner's lead, decline when in doubt). No code needed for this instruction-only skill. | 3 / 3 |
Workflow Clarity | This is a simple behavioral skill, not a multi-step process. The single-task guidance is unambiguous with clear boundaries: what to do, what not to do, and how to handle edge cases (owner present, uncertain situations). Per scoring notes, simple skills can score 3 if clear. | 3 / 3 |
Progressive Disclosure | Under 50 lines, well-organized with clear section headers ('What you can do here' and 'Behavioral guidelines'). No need for external references given the scope. Content is appropriately structured for its size. | 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