CtrlK
BlogDocsLog inGet started
Tessl Logo

sysadmin

System administration expert for Linux, macOS, Windows, services, and monitoring

64

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./crates/openfang-skills/bundled/sysadmin/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

87%

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

The body is a lean, highly actionable reference with concrete per-platform commands and clean section organization. Its only notable gap is the absence of an explicit validate→fix→retry feedback loop for destructive operations, which holds workflow clarity at mid-tier.

Suggestions

Add a short explicit feedback loop for destructive operations, e.g. for service changes: make change → check 'systemctl status' and logs → if failed, revert and re-diagnose.

Consider a brief ordered 'Troubleshooting workflow' sequence (diagnose → identify cause → apply least-destructive fix → verify) to turn the reference into a sequenced process with checkpoints.

DimensionReasoningScore

Conciseness

The body is lean and command-focused with compact bullet lists and inline commands; it assumes Claude's competence and never pads with explanations of concepts Claude already knows. Not score 2 because there is no unnecessary explanation to trim.

3 / 3

Actionability

Provides concrete, executable, copy-paste-ready commands per platform (e.g. 'top', 'htop', 'systemctl start|stop|restart|status|enable|disable', 'cp file file.bak.$(date +%Y%m%d)'). Not score 2 because the guidance is real commands rather than pseudocode or incomplete instructions.

3 / 3

Workflow Clarity

Safety checkpoints are embedded as principles ('Always back up configuration files before modifying them', 'Always check service status and logs after making changes') and escalation guidance exists ('try SIGTERM first, then escalate'), but there is no explicit ordered multi-step workflow with a validate→fix→retry feedback loop for destructive/batch operations like process kills or service changes, which caps workflow clarity at 2. Not score 1 because checkpoints are present; not score 3 because no structured feedback loop is shown.

2 / 3

Progressive Disclosure

The skill is under 50 lines with no external references and is organized into clear, well-signaled sections (Diagnostics, Service Management, Security Hardening, Pitfalls), matching the rubric's allowance that simple skills can score 3 with just well-organized sections. Not score 2 because the organization is clean and nothing that should be externalized is inline.

3 / 3

Total

11

/

12

Passed

Description

65%

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

The description identifies the domain and target platforms clearly with natural trigger terms, but it lacks explicit 'Use when...' trigger guidance and describes the skill's role rather than concrete actions, leaving it solidly mid-tier.

Suggestions

Add an explicit trigger clause, e.g. 'Use when managing servers, configuring services, troubleshooting system issues, or hardening infrastructure across Linux, macOS, or Windows.'

Replace the role-based phrasing with concrete third-person actions ('Configures services, diagnoses system issues, hardens security') to lift specificity.

Sharpen distinctiveness by naming scope boundaries or specific tasks (e.g. 'service management, diagnostics, security hardening') to reduce overlap with generic ops skills.

DimensionReasoningScore

Specificity

Names the domain and scope areas ('Linux, macOS, Windows, services, and monitoring') but describes the role rather than concrete actions like 'configure', 'troubleshoot', or 'harden'. Not score 1 because it is not vague like 'Helps with documents'; not score 3 because it lists no multiple specific concrete actions comparable to 'Extract text and tables from PDF files, fill forms, merge documents'.

2 / 3

Completeness

States what the skill is ('System administration expert for...') but has no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 2 per the rubric guidelines. Not score 1 because the 'what' is present and reasonable; not score 3 because there is no explicit 'when to use'.

2 / 3

Trigger Term Quality

'Linux, macOS, Windows, services, monitoring' are natural terms a user would say ('help me with my Linux server', 'set up monitoring'), giving good coverage across platforms and ops topics. Not score 2 because the keywords span the common variations users actually voice rather than just a single relevant term.

3 / 3

Distinctiveness Conflict Risk

'System administration' is a reasonably distinct niche with platform qualifiers, but 'services' and 'monitoring' could overlap with general infrastructure or ops skills. Not score 1 (not generic like 'code and documents'); not score 3 because there are no sharp explicit triggers to fully distinguish it from adjacent ops skills.

2 / 3

Total

9

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
RightNow-AI/openfang
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.