CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

forensic-troubleshooter

Orchestrates forensic analysis of failed jobs with event extraction, host correlation, and resolution advisory. Use when: - "Job #X failed", "Why did the execution fail?" - "Analyze the failure", "What went wrong?" - "Root cause analysis of job #X" NOT for execution (use governance-executor) or platform assessment (use governance-assessor).

Quality

83%

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

67%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 orchestrator skill: clear five-step workflow with a stop-on-failure checkpoint, concrete sub-skill delegation, and resolved reference links. The main weakness is redundancy — the Prerequisites, per-step Document Consultation blocks, and Dependencies sections repeat the same skill, server, and reference information two to three times.

Suggestions

Collapse the duplicate 'Document Consultation' paragraphs in steps 2–4 into the existing bullet that already states which reference each sub-skill reads, keeping each mention to one line.

Merge the Dependencies section with Prerequisites so Required Skills, Required MCP Servers, and Reference Documentation are listed once (keep only genuinely new content like Related Skills and Required MCP Tools).

Add brief contingency guidance for mid-workflow failures, e.g., what to do when host-fact-inspector finds an affected host missing from the inventory or when no failed job is returned.

DimensionReasoningScore

Conciseness

The instruction content itself is lean, but it is noticeably duplicated: "Document Consultation (performed by the skill)" blocks repeat inline bullets in steps 2–4, and the Dependencies section re-lists Required Skills, Required MCP Servers, and reference links already given in Prerequisites and the workflow.

3 / 5

Actionability

Steps name each sub-skill, what it does, and which documents it reads, and two worked examples are concrete (job #4451, affected hosts, classification, Red Hat citations, jobs_list), but mid-workflow contingencies (ambiguous classification, missing host, no failed jobs) are unaddressed.

4 / 5

Workflow Clarity

Five clearly sequenced steps with an explicit validation checkpoint ("If any server fails: report and stop") fit the mostly-checkpoints anchor; gaps remain for mid-workflow failure handling such as a host missing from inventory.

4 / 5

Progressive Disclosure

The body appropriately plays an overview role with clearly signaled links to two real reference files (both present in the bundle), but the pointer-stub indirection inside those files and the repeated link/dependency listings are minor organization gaps.

4 / 5

Total

15

/

20

Passed

Description

95%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: third-person voice, concrete actions, explicit use-when triggers quoted as natural user phrases, and clear disambiguation from sibling skills. The only weakness is that the what-line undersells the full workflow (validation, classification, timeline, audit trail) described in the body.

DimensionReasoningScore

Specificity

The description names the domain and three concrete actions — "event extraction, host correlation, and resolution advisory" — but omits other capabilities the body performs (connectivity validation, failure classification, timeline reconstruction, audit summary), which is more than a minor coverage gap.

4 / 5

Completeness

It explicitly answers both what ("Orchestrates forensic analysis of failed jobs with event extraction, host correlation, and resolution advisory") and when (a "Use when" clause with concrete trigger phrases), matching the top anchor's example pattern.

5 / 5

Trigger Term Quality

Quoted natural user utterances ("Job #X failed", "What went wrong?", "Root cause analysis of job #X") plus synonyms (failed/failure/went wrong/root cause) give comprehensive coverage of terms a user would actually say when needing this skill.

5 / 5

Distinctiveness Conflict Risk

It carves a clear niche (forensic analysis of failed jobs) and adds an explicit boundary — "NOT for execution (use governance-executor) or platform assessment (use governance-assessor)" — leaving minimal conflict risk with sibling skills.

5 / 5

Total

19

/

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: 4 deeper-than-1-level

Warning

referenced_paths_exist

Referenced path issues: 4 deeper-than-1-level

Warning

Total

13

/

16

Passed

Repository

RHEcosystemAppEng/agentic-plugins

Path

rh-automation/skills/forensic-troubleshooter/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.