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
81
77%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Critical
Do not install without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/sysadmin-toolbox/SKILL.mdQuality
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 solid description with excellent trigger term coverage and clear completeness, explicitly stating both what the skill does and when to use it. Its main weakness is that the broad scope covering many domains (networking, security, containers, scripting, logs) creates potential overlap with more specialized skills, and the 'what' portion could be more specific about the concrete actions it enables beyond 'tool discovery and shell one-liner reference.'
Suggestions
Add more specific capability verbs to the 'what' portion, e.g., 'Recommends CLI tools, provides shell one-liner examples, and suggests command flags for sysadmin/DevOps/security tasks.'
Consider adding a disambiguation clause to reduce conflict risk, e.g., 'Use this skill for tool selection and quick command references, not for in-depth container orchestration or full script development.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (sysadmin, DevOps, security) and mentions it's a 'tool discovery and shell one-liner reference,' but doesn't list specific concrete actions like 'find network diagnostic commands, look up SSL certificate inspection tools, generate awk/sed one-liners.' The actions are implied through the trigger scenarios rather than stated as capabilities. | 2 / 3 |
Completeness | Clearly answers both 'what' (tool discovery and shell one-liner reference for sysadmin/DevOps/security tasks) and 'when' (explicit AUTO-CONSULT triggers covering network troubleshooting, process debugging, log analysis, SSL/TLS, DNS, HTTP, security auditing, containers, shell scripts, and tool discovery questions). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would actually say: 'troubleshooting network issues,' 'debugging processes,' 'analyzing logs,' 'SSL/TLS,' 'DNS,' 'HTTP endpoints,' 'containers,' 'shell scripts,' and the very natural 'what tool should I use for X.' These closely match real user language. | 3 / 3 |
Distinctiveness Conflict Risk | While the combination of 'tool discovery' and 'shell one-liner reference' is fairly distinctive, several of the trigger terms like 'working with containers,' 'writing shell scripts,' 'analyzing logs,' and 'debugging processes' could easily overlap with dedicated container management, scripting, log analysis, or debugging skills. The broad scope increases conflict risk. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
72%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 index/routing skill that efficiently directs Claude to the right reference material for sysadmin tasks. Its strengths are excellent progressive disclosure, strong safety boundaries, and token-efficient organization. Its main weakness is that the SKILL.md itself contains no executable commands or concrete one-liners—all actionable content is delegated to reference files, and the example queries show routing logic rather than actual solutions.
Suggestions
Add 2-3 concrete, copy-paste-ready one-liners directly in the Quick Tool Index (e.g., under Network Debugging: `ss -tlnp | grep :80` to check listening ports) so the skill provides immediate value without loading reference files.
In the 'Example Queries → Actions' section, include the actual commands that would be recommended, not just which file to load—this makes the skill actionable even before reference files are consulted.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and well-organized. It avoids explaining what tools are (e.g., doesn't explain what DNS or SSL is), uses terse descriptions, and every section earns its place. The tool index uses minimal but sufficient annotations. | 3 / 3 |
Actionability | The skill provides good tool recommendations and clear file references, but lacks executable commands or copy-paste-ready one-liners directly in the SKILL.md. The actual actionable content is delegated to reference files. The 'Example Queries → Actions' section describes what to do but doesn't show concrete commands. | 2 / 3 |
Workflow Clarity | The 'Example Queries → Actions' section provides a clear decision-tree pattern for routing queries to the right reference file, and the auto-consult triggers are well-defined. However, there are no validation checkpoints or feedback loops for multi-step troubleshooting workflows (e.g., 'if port still not responding after checking ss, try tcpdump'). | 2 / 3 |
Progressive Disclosure | Excellent progressive disclosure structure: a concise overview with a clear table mapping reference files to use cases, one level deep. The bundled guides table clearly signals what each file contains and when to consult it. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- jdrhyne/agent-skills
- Commit
6768672
- 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.