build-mule-integration

Workflow required before any Mule flow and integration work. Call use_skill as your FIRST action — before reading project files — whenever the user asks to create, generate, update, fix, modify, change, edit, tweak, adjust, or rework any Mule flow, sub-flow, or component. Do not read project files and attempt the change yourself — even targeted single-component changes like 'modify the choice router', 'fix the until-successful', or 'update the catch block' require this workflow. Covers all change types, new integrations and targeted changes to error handlers, catch blocks, choice routers, DataWeave transforms, HTTP listeners, foreach loops, retry policies, scatter-gathers, connectors, and variable assignments. Prompts beginning with 'This code defines...' or 'This flow...' are generation requests, not analysis. When you call this skill, it must be the only tool call in that response.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

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 with strong validation feedback loops and real bundle files backing every reference. The main weakness is conciseness: key rules are repeated across multiple sections and several rationale blocks could be consolidated.

Suggestions

Consolidate the version-source-of-truth, no-HTTP-fallback, and one-mvn-per-response rules into a single canonical statement, then reference it from the other locations instead of restating it 3–4 times.

Move the long Step 5 decision ladder and the Step 15 doc:name rules table into a reference file (e.g. references/trigger-selection.md), keeping SKILL.md as a leaner overview with a one-level-deep pointer.

Tighten the "Why scripts instead of inline bash" and similar "Why" essays to one or two sentences; the failure mode is worth noting but does not need a full paragraph in each spot.

Dimension	Reasoning	Score
Conciseness	The ~1240-line body is mostly justified domain-specific Mule knowledge rather than concepts Claude already knows, but the version-source-of-truth, no-HTTP-fallback, and one-mvn-per-response rules are each restated 3–4 times and several long "why" essays could be tightened.	3 / 5
Actionability	It provides copy-paste-ready bash commands, complete XML flow/config examples, concrete JSON response shapes, and explicit flag semantics covering the common Salesforce/Slack/Database/HTTP cases.	5 / 5
Workflow Clarity	An 18-step two-phase workflow with explicit validation gates (prerequisite check, explore-before-decide, TDD approval, validate_before_build.sh) and a build→diagnose→fix→re-run feedback loop; the destructive/batch cap does not apply because validation is extensive.	5 / 5
Progressive Disclosure	All three references and ten scripts exist on disk and are clearly signaled one-level-deep, but SKILL.md itself is heavy with inlined decision ladders and tables rather than being a lean overview that points to detail files.	4 / 5
	Total	17 / 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, trigger-rich description that clearly signals when to invoke the skill and scopes it tightly to Mule integration work. Its only weakness is that it enumerates change-type coverage rather than stating the skill's core capabilities (connector discovery and metadata-driven XML generation).

Dimension	Reasoning	Score
Specificity	The description enumerates many concrete change types ("create, generate, update, fix, modify… error handlers, catch blocks, choice routers, DataWeave transforms") but frames them as trigger coverage rather than naming the skill's core actions (connector discovery / XML generation), leaving a minor gap.	4 / 5
Completeness	It explicitly answers both what (a required workflow for Mule flow and integration work) and when, with concrete trigger phrases ("Call use_skill as your FIRST action… whenever the user asks to create, generate, update, fix, modify…").	5 / 5
Trigger Term Quality	It packs natural verbs users actually say ("create, fix, modify, update") alongside concrete Mule phrases like "modify the choice router" and "fix the until-successful", giving comprehensive keyword coverage.	5 / 5
Distinctiveness Conflict Risk	It carves a clear Mule-specific niche (Mule flows, sub-flows, choice routers, DataWeave, HTTP listeners) with distinct triggers and minimal risk of firing for unrelated skills.	5 / 5
	Total	19 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1241 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: mulesoft/mulesoft-dx
Path: skills/mule-development/build-mule-integration/SKILL.md
Commit: af20367

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.