CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

host-fact-inspector

Correlate job failures with host system facts to determine platform drift and resource issues. Use when: - After job failure analysis identifies affected hosts - "Check the system facts for failed hosts" - "Is the host healthy?", "Check disk space on server-01" - "Why is the service failing on this host?" NOT for: analyzing job events (use job-failure-analyzer first) or resolution guidance (use resolution-advisor after).

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

82%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, highly actionable workflow with concrete tool parameters, a correlation table, an output template, and a worked example. The main weaknesses are structural redundancy between the Prerequisites and Dependencies sections and the absence of error-recovery branches for host lookup failures.

Suggestions

Merge the "Prerequisites" and "Dependencies" sections into one to remove the duplicated MCP server and tool listings.

Add a recovery branch to the workflow for when hosts_list returns no match or hosts_variable_data_retrieve returns no cached facts (e.g., fall back to inventory-wide search or report facts as unavailable).

Keep the error-to-fact correlation table only in references/aap/job-troubleshooting.md (or only inline) instead of maintaining it in both places.

DimensionReasoningScore

Conciseness

The body is lean and free of concept explanations Claude already knows, but "Prerequisites" and "Dependencies" duplicate the same MCP server/tool information, and "When to Use This Skill" restates the frontmatter guidance. These are minor trims, not pervasive verbosity.

4 / 5

Actionability

Fully executable guidance: concrete MCP tool calls with parameters (hosts_list with search/page_size, hosts_variable_data_retrieve with id/format), an error-to-fact correlation table with thresholds ("Disk utilization > 90%"), a complete output report template, and a worked end-to-end example. Copy-paste ready for the common case.

5 / 5

Workflow Clarity

Clear 5-step sequence with an enforced-first document consultation and a stale-facts caveat, but there is no recovery branch for a host-not-found lookup or missing facts. The operations are read-only so no destructive-cap applies; the missing error-recovery loops keep it below anchor 5.

4 / 5

Progressive Disclosure

Well-signaled one-level-deep reference to references/aap/job-troubleshooting.md (which exists in the bundle) and good section organization. Minor gaps: the correlation table is duplicated inline rather than living solely in the reference, and the references bundle contains files not referenced from the body.

4 / 5

Total

17

/

20

Passed

Description

87%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: concrete third-person capability statement, explicit "Use when" triggers with quoted natural phrases, and clear NOT-for boundaries that disambiguate sibling skills. Only minor gaps in action coverage and trigger synonym breadth.

DimensionReasoningScore

Specificity

"Correlate job failures with host system facts to determine platform drift and resource issues" names the domain and several concrete actions (correlate failures with facts, determine platform drift, determine resource issues) with no padding. It lists more distinct actions than the anchor-3 example but is not a comprehensive multi-action list like the anchor-5 PDF example.

4 / 5

Completeness

Explicitly answers "what" in third person ("Correlate job failures with host system facts to determine platform drift and resource issues") and "when" with a concrete "Use when:" list of trigger phrases, plus an explicit "NOT for" boundary. This matches the anchor-5 pattern of the good example.

5 / 5

Trigger Term Quality

Quotes natural user phrases ("Check the system facts for failed hosts", "Is the host healthy?", "Check disk space on server-01", "Why is the service failing on this host?") giving good keyword coverage. A few natural variations (e.g., memory/CPU checks, platform mismatch) are missing, keeping it below the comprehensive anchor 5.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (host-fact correlation after job failures) and explicitly disambiguates from siblings via "NOT for: analyzing job events (use job-failure-analyzer first) or resolution guidance (use resolution-advisor after)". Minimal conflict risk.

5 / 5

Total

18

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 3 deeper-than-1-level

Warning

referenced_paths_exist

Referenced path issues: 3 deeper-than-1-level

Warning

Total

13

/

16

Passed

Repository

RHEcosystemAppEng/agentic-plugins

Path

rh-automation/skills/host-fact-inspector/SKILL.md

Revision

df1d156

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill