CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

72%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured reference skill: lean body, clear navigation to real one-level-deep reference files, and concrete tool routing. The main gap is the unvalidated batch refresh workflow, and there is minor trimmable redundancy (duplicated trigger list, environment-specific scheduling details).

Suggestions

Add validation around the refresh workflow — e.g. verify each extracted file is non-empty (line-count check) or back up and diff references before replacing them — to lift the workflow-clarity cap.

Drop the duplicated "When to Auto-Consult" list (the description already carries it) and remove environment/time-specific details like the weekly refresh schedule and the absolute ~/clawd-duke-leto path.

Make commands copy-paste complete, e.g. replace "git -c commit.gpgsign=false commit ..." with a full example invocation.

DimensionReasoningScore

Conciseness

The body is efficient — terse index entries like "`mtr` - traceroute + ping combined" and no explanations of concepts Claude already knows. Not 5 because the "When to Auto-Consult" section duplicates the description's trigger list, and "References auto-refresh weekly (Sundays 5am ET)" plus the absolute path "~/clawd-duke-leto/skills/..." are time- and environment-specific details that could be trimmed.

4 / 5

Actionability

Routing guidance is concrete and executable ("Load shell-oneliners.md, search for netstat/ss/lsof commands", "recommend testssl.sh or sslyze") and includes real commands like "git -c commit.gpgsign=false commit ...". Not 5 because few commands are copy-paste complete — the git example ends in an ellipsis and refresh.sh takes an optional "[skill-dir]" placeholder — and much of the guidance is 'search for X' direction rather than ready commands.

4 / 5

Workflow Clarity

The lookup workflow is unambiguous via the "Example Queries → Actions" section, but the refresh workflow ("./scripts/refresh.sh [skill-dir]") is a batch operation that overwrites all five reference files with no validation or verification steps described in the body. Per the rubric cap for batch operations without validation, workflow clarity cannot exceed 3; not 2 because the primary lookup sequence is clear and well-sequenced.

3 / 5

Progressive Disclosure

The body is a lean overview with a "Reference Files" table whose "Use When" column clearly signals when to open each of the five references, all of which exist and contain no further nested references (verified one level deep). The "Example Queries → Actions" section adds explicit navigation; this matches anchor 5's clear overview with well-signaled one-level-deep references.

5 / 5

Total

16

/

20

Passed

Description

82%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description with an excellent, explicit trigger list and a clear what/when structure. Its main weaknesses are the content-type framing instead of concrete action verbs and a trigger breadth that invites conflicts with more specialized skills.

Suggestions

Replace the content-type framing with concrete actions, e.g. "Recommends CLI tools and provides shell one-liners for network debugging, DNS, SSL/TLS, log analysis, and security auditing" instead of "Tool discovery and shell one-liner reference".

Narrow or qualify overlapping triggers (e.g. "choosing tools for containers/Docker work" rather than "working with containers") to reduce conflict risk with dedicated shell-scripting or container skills.

DimensionReasoningScore

Specificity

"Tool discovery and shell one-liner reference for sysadmin, DevOps, and security tasks" names the domain and two deliverables but frames itself as a content type rather than listing several concrete actions Claude performs. It matches anchor 3 (domain plus 1-2 concrete actions) and not 4, which requires a list of several specific actions with only minor gaps.

3 / 5

Completeness

It explicitly answers both parts: the what ("Tool discovery and shell one-liner reference for sysadmin, DevOps, and security tasks") and the when with concrete trigger phrases ("AUTO-CONSULT this skill when the user is: ..."). This matches the anchor 5 example structure exactly; 4 would require the 'when' to be less explicit than this enumerated list.

5 / 5

Trigger Term Quality

The trigger list "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'" gives comprehensive natural-phrase coverage across the skill's domains, including the exact meta-query a user would type. Not 4 because no commonly said domain phrase is conspicuously missing.

5 / 5

Distinctiveness Conflict Risk

Broad triggers like "writing shell scripts", "analyzing logs", and "working with containers" overlap heavily with dedicated single-domain skills (shell-scripting, log-analysis, container skills), matching anchor 3's 'could still overlap with similar skills'. Not 4 because the ~10-domain breadth creates more than minor overlap risk; not 2 because the tool-recommendation framing ('what tool should I use for X') keeps the niche identifiable.

3 / 5

Total

16

/

20

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

bap-jorkim/agent-skills-fork-feb-25

Path

skills/sysadmin-toolbox/SKILL.md

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.