CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

secure-agent

Secure an agent by applying a policy from the catalog. Handles multiple starting points: from an existing API Manager instance, from an agent asset in Exchange, or from scratch by publishing the agent first. Use when the user wants to secure an agent, add rate limiting, apply OAuth2, enforce IP allowlisting, or protect any agent with a policy — regardless of where they are in the setup process.

Quality

83%

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

77%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 operational skill: every step is executable via complete tool-call specs, error messages are anticipated with recovery guidance, and multiple entry paths are explicitly mapped. The main weaknesses are redundancy (the same warnings repeated 3-4 times across steps, tips, and troubleshooting) and a monolithic single-file structure that inlines content which would sit better in separate reference files.

Suggestions

State the getExchangePolicyTemplates-vs-listPolicyTemplates warning once (in Step 8) and trim its repetitions in Tips, Gateway Compatibility, and the Troubleshooting '400 Error' section, which duplicates Step 8's Common issues.

Move the Troubleshooting and Tips and Best Practices sections into a one-level-deep reference file (e.g. references/troubleshooting.md), keeping SKILL.md as a navigable overview of the nine steps and execution paths.

Consolidate the gatewayVersion "1.0.0" default guidance — currently repeated in Step 4's output description, Step 6's input description, and Step 6's Common issues — into a single location.

DimensionReasoningScore

Conciseness

The body is dense with non-obvious operational specifics (isCloudHub must be null, flat deployment body, exact error strings), but key warnings are repeated verbatim in multiple places — the getExchangePolicyTemplates-vs-generic-endpoint warning appears four times and the gatewayVersion "1.0.0" default three times — and the Troubleshooting section largely duplicates per-step Common issues.

3 / 5

Actionability

Every step provides a complete, copy-paste-ready YAML tool-call specification with inputs wired from prior step outputs, an exact JSON request body structure, and concrete guidance for building configurationData from the Step 8 schema. This fully matches the 'copy-paste ready, covers common cases' anchor.

5 / 5

Workflow Clarity

The multi-step process is explicitly sequenced with a mermaid flowchart, three named execution paths with exact step lists and skip-to guidance, per-step prerequisites and 'What happens next' transitions, a completion checklist, and error-recovery loops tied to specific error messages (409 → list deployments first, validation error → use null, 403 → check Manage Policies permission).

5 / 5

Progressive Disclosure

No bundle files exist and all content — nine full API call specs, troubleshooting, and best-practices tips — is inlined in a single ~640-line file. Headers, a flowchart, and a consistent per-step format keep it navigable, but the Troubleshooting and Tips sections are prime candidates for one-level-deep reference files, matching the 'could be better organized; content that should be separate is inline' anchor.

3 / 5

Total

16

/

20

Passed

Description

83%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: it states concrete capabilities in third person, explicitly covers multiple starting points, and includes a well-formed 'Use when...' clause with natural trigger phrases covering the main policy types. The only gaps are incomplete synonym coverage and minor overlap risk with sibling policy-application skills when the trigger phrase omits the word 'agent'.

DimensionReasoningScore

Specificity

Names several concrete actions — 'applying a policy from the catalog', 'publishing the agent first', three distinct starting points — plus concrete policy types (rate limiting, OAuth2, IP allowlisting). Not 5 because it omits major parts of what the skill does (creating an API Manager instance, deploying to a gateway).

4 / 5

Completeness

Explicitly answers both questions: 'what' ('Secure an agent by applying a policy from the catalog. Handles multiple starting points: from an existing API Manager instance, from an agent asset in Exchange, or from scratch') and 'when' with concrete triggers ('Use when the user wants to secure an agent, add rate limiting, apply OAuth2, enforce IP allowlisting...'). This matches the top anchor exactly.

5 / 5

Trigger Term Quality

Contains natural phrases users would actually say — 'secure an agent', 'add rate limiting', 'apply OAuth2', 'enforce IP allowlisting', 'protect any agent with a policy'. Not 5 because common synonyms such as 'throttling', 'authentication', or 'traffic management' are missing.

4 / 5

Distinctiveness Conflict Risk

Consistently scoped to agents ('secure an agent', 'agent asset in Exchange', 'protect any agent'), which distinguishes it from the closely related secure-api and secure-mcp-server skills. Not 5 because generic policy triggers like 'add rate limiting' or 'apply OAuth2' said without the word 'agent' could route to the secure-api sibling skill.

4 / 5

Total

17

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (647 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository

mulesoft/mulesoft-dx

Path

skills/secure-agent/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.