jbvc/safe-command-guard
Enforce safety constraints on system commands before execution. Use this skill whenever the agent needs to run shell commands, terminal operations, or system-level actions. It classifies commands into BLOCKED, CONFIRM, or ALLOWED and prevents dangerous operations from executing.
94
94%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Risky
Do not use without reviewing
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 strong skill description that clearly communicates its purpose as a command safety gate, specifies concrete actions (classification into three categories, blocking dangerous operations), and provides explicit trigger conditions. It uses proper third-person voice throughout and includes natural keywords that would match relevant contexts.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: classifying commands into BLOCKED/CONFIRM/ALLOWED categories, enforcing safety constraints, and preventing dangerous operations from executing. These are clear, concrete capabilities. | 3 / 3 |
Completeness | Clearly answers both what ('classifies commands into BLOCKED, CONFIRM, or ALLOWED and prevents dangerous operations') and when ('whenever the agent needs to run shell commands, terminal operations, or system-level actions') with an explicit 'Use this skill whenever...' clause. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'shell commands', 'terminal operations', 'system-level actions', 'run', 'execute'. These are terms users and agents would naturally use when dealing with command execution. | 3 / 3 |
Distinctiveness Conflict Risk | Occupies a clear niche as a safety/gating layer for command execution. The specific focus on command classification (BLOCKED/CONFIRM/ALLOWED) and safety enforcement makes it highly distinct from other skills that might simply execute commands. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable safety skill with clear workflows, explicit validation checkpoints, and good progressive disclosure. Its main weakness is moderate verbosity—the extensive command lists and evasion examples, while useful as reference, could be tightened or moved to a reference file to save tokens. Overall it effectively serves its purpose as a mandatory safety layer.
Suggestions
Consider moving the detailed BLOCKED/CONFIRM/ALLOWED command lists and evasion detection examples to a reference file (e.g., references/command_lists.md) and keeping only a few representative examples inline, since the guard script already handles classification.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly comprehensive but includes some redundancy. The extensive lists of BLOCKED, CONFIRM, and ALLOWED commands are valuable reference material but could be more concise—Claude already understands most of these danger levels. The evasion detection examples are useful but slightly verbose with comments restating the obvious. | 2 / 3 |
Actionability | Highly actionable with a concrete guard script to run (`scripts/command_guard.py --command "<the_command>"`), specific JSON output format, exact response templates for BLOCKED commands, and clear quick-start examples. The workflow is copy-paste ready and leaves no ambiguity about what to do. | 3 / 3 |
Workflow Clarity | The mandatory workflow is clearly sequenced (Parse → Run guard → Act on verdict → Never bypass), with explicit validation via the guard script, clear branching logic for each verdict level, and a well-defined failure handling section that covers edge cases like unparseable commands or unavailable guard scripts. | 3 / 3 |
Progressive Disclosure | The skill provides a clear overview and detailed inline content that is appropriate for the safety-critical nature of the skill, while pointing to `references/dangerous_commands.md` for deeper regex patterns and edge cases. The 'When To Read References' section clearly signals when to consult the external file, keeping it one level deep. | 3 / 3 |
Total | 11 / 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