sysadmin-toolbox
Tool discovery and shell one-liner reference for sysadmin, DevOps, and security tasks. AUTO-CONSULT this skill when the user is: troubleshooting network issues, debugging processes, analyzing logs, working with SSL/TLS, managing DNS, testing HTTP endpoints, auditing security, working with containers, writing shell scripts, or asks 'what tool should I use for X'. Source: github.com/trimstray/the-book-of-secret-knowledge
Install with Tessl CLI
npx tessl i github:jdrhyne/agent-skills --skill sysadmin-toolbox86
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
82%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-structured description with excellent trigger term coverage and clear 'when to use' guidance via the AUTO-CONSULT clause. Its main weakness is the broad scope covering many domains (networking, security, containers, scripting) which could cause conflicts with more specialized skills, and the lack of specific concrete actions beyond 'tool discovery' and 'reference'.
Suggestions
Add 2-3 specific concrete actions like 'find the right CLI tool for a task', 'provide one-liner examples', 'suggest diagnostic commands' to improve specificity
Consider narrowing scope or adding differentiating language like 'for quick reference lookups' to reduce overlap with dedicated container, security, or scripting skills
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (sysadmin, DevOps, security) and mentions 'tool discovery' and 'shell one-liner reference' but doesn't list specific concrete actions like 'parse logs', 'test SSL certificates', or 'query DNS records'. | 2 / 3 |
Completeness | Clearly answers both what ('Tool discovery and shell one-liner reference') and when ('AUTO-CONSULT this skill when the user is: troubleshooting network issues, debugging processes...'). The explicit trigger list with 'AUTO-CONSULT' provides clear guidance. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'troubleshooting network issues', 'debugging processes', 'analyzing logs', 'SSL/TLS', 'DNS', 'HTTP endpoints', 'containers', 'shell scripts', and the explicit 'what tool should I use for X' pattern. | 3 / 3 |
Distinctiveness Conflict Risk | While it has specific triggers, terms like 'working with containers', 'writing shell scripts', and 'analyzing logs' could overlap with container-specific skills, bash scripting skills, or log analysis tools. The broad scope increases conflict potential. | 2 / 3 |
Total | 10 / 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 reference skill that excels at organization and progressive disclosure. It efficiently indexes tools and points to detailed references without bloat. The main weakness is the lack of executable examples—the skill tells you which tools to use but doesn't show how to use them inline, relying entirely on external reference files.
Suggestions
Add 2-3 executable one-liner examples directly in the Quick Tool Index (e.g., `ss -tulpn` for connection monitoring, `dig +short example.com` for DNS) to make the skill immediately actionable without loading references
Include at least one complete example in the 'Example Queries → Actions' section showing the actual command output, not just the action to take
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely lean and efficient. No unnecessary explanations of what tools are or how they work—just tool names, brief purpose descriptions, and organized references. Every line serves a purpose. | 3 / 3 |
Actionability | Provides good tool recommendations and reference file pointers, but lacks executable code examples. The 'Example Queries → Actions' section describes what to do but doesn't show actual commands. The Quick Tool Index lists tools without usage examples. | 2 / 3 |
Workflow Clarity | For a reference/discovery skill, the workflow is clear: identify the problem domain → consult the appropriate reference file → find the tool/command. The 'When to Auto-Consult' and 'Example Queries → Actions' sections make the decision tree explicit. | 3 / 3 |
Progressive Disclosure | Excellent structure with a clear overview, well-organized quick index, and explicit one-level-deep references to detailed files. The table format for reference files with 'Use When' guidance is particularly effective for navigation. | 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
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.