CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

run-service-scan-and-view-results

Executes a scanner and views discovered services (such as AI agents, MCP servers, and API metadata). Use when running a scan, checking scan status, viewing scan history, reviewing discovered services from external platforms, or importing services into Anypoint Exchange.

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

81%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 highly actionable, well-sequenced workflow skill: complete invocation specs, explicit error handling, and validation checkpoints make it copy-paste ready end to end. Its main cost is token weight from redundant framing sections and inline reference material that could be trimmed or split out.

Suggestions

Merge 'Overview' and 'What you'll build' into a single two-sentence intro, and cut the 'What You've Built' section, which restates information already given in the steps and completion checklist.

Move the Troubleshooting section and the 'Understanding Staging Status' reference table into a separate reference file (e.g. references/troubleshooting.md), keeping the core three-step workflow lean in SKILL.md.

Drop the repeated 'What you'll need' lists in Steps 2-3 since those inputs are already bound via variables from earlier steps.

DimensionReasoningScore

Conciseness

The body is mostly dense, specific, and useful, but carries real redundancy: 'Overview' and 'What you'll build' overlap, the 'What You've Built' section restates earlier content, and per-step 'What you'll need' lists repeat the same inputs. This fits 'mostly efficient but could be tightened' better than the minor-trim-only anchor.

3 / 5

Actionability

Fully executable, copy-paste-ready invocation blocks (api URNs, operationIds, inputs with JSONPath bindings, outputs with extraction paths) plus concrete error codes (409 Conflict, 404 Not Found, 503 Service Unavailable) with per-code remedies; the common cases are covered.

5 / 5

Workflow Clarity

Three clearly sequenced steps, each with expected outcome and common issues, gated on an explicit status check (COMPLETED before viewing staging assets), a completion checklist, troubleshooting symptom→cause→solution loops, and a concrete polling interval (30-60s). Validation is present, so the batch-operation cap does not apply.

5 / 5

Progressive Disclosure

No bundle files exist; the skill is self-contained with well-organized, clearly headed sections and unambiguous navigation. Minor gap: the ~80 lines of troubleshooting and staging-status reference material could be split into a separate reference file to slim the core workflow.

4 / 5

Total

17

/

20

Passed

Description

78%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 explicit and well-enumerated 'Use when...' clause and natural trigger terms rooted in a distinct niche. The main weakness is that the 'what' portion states only two actions, leaving capability coverage thinner than the trigger list implies.

Suggestions

Expand the 'what' portion to enumerate the concrete capabilities (e.g., 'Triggers a scan, monitors run status and history, and lists discovered staging services with their publication status') so capability coverage matches the trigger list.

Add common trigger variants such as 'scan results', 'scan progress', or 'published services' to broaden natural keyword coverage.

DimensionReasoningScore

Specificity

The 'what' names exactly two concrete actions ("Executes a scanner and views discovered services") with a helpful parenthetical of service types, matching the anchor for 1-2 concrete actions rather than several; the richer activity list (importing, checking status) only appears in the 'when' clause.

3 / 5

Completeness

Explicitly answers both questions: a clear 'what' ("Executes a scanner and views discovered services...") followed by an enumerated 'Use when...' clause with concrete trigger phrases, mirroring the top anchor example.

5 / 5

Trigger Term Quality

Natural trigger phrases users would actually say — "running a scan", "checking scan status", "viewing scan history", "reviewing discovered services", "importing services into Anypoint Exchange" — give good keyword coverage, though common variants like "scan results" or "scan progress" are missing.

4 / 5

Distinctiveness Conflict Risk

Clear niche (Anypoint Exchange service scanning, MCP/AI-agent discovery) with distinct triggers; only minor overlap risk with the closely related sibling skill 'setup-service-scanner', since "running a scan" could match both.

4 / 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

mulesoft/mulesoft-dx

Path

skills/run-service-scan-and-view-results/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.