CtrlK
BlogDocsLog inGet started
Tessl Logo

connector-delivery

Implements new RobustMQ MQTT connector integrations end-to-end using project conventions. Use when the user asks to add, implement, or support a new connector type such as webhook, opentsdb, clickhouse, influxdb, cassandra, mqtt bridge, or protocol-compatible targets.

67

Quality

80%

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

75%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, actionable end-to-end delivery playbook with concrete file paths, function signatures, and validation steps. It is held back from top marks by minor redundancy, the absence of an explicit validation feedback loop, and lack of any reference-file split.

Suggestions

Add an explicit feedback loop to step 8 (e.g., 'If cargo check fails, fix errors and re-run until it passes') to push workflow clarity to 5.

Collapse the 'File Matrix' into the per-step file lists or keep only one to remove redundancy and improve conciseness.

Consider extracting the failure-strategy semantics (discard/discard_after_retry/dead_message_queue) into a references/ file linked from the body to improve progressive disclosure.

DimensionReasoningScore

Conciseness

Lean, bullet-driven content that assumes Claude's competence and avoids concept explanation; the 'File Matrix (must touch)' section partially duplicates the per-step file lists and could be trimmed.

4 / 5

Actionability

Highly concrete guidance with exact file paths, required struct derives, function signatures (validate, init_sink, send_batch, cleanup_sink), a specific cargo check command, and a copy-paste completion template; no actual Rust code snippet is a minor gap.

4 / 5

Workflow Clarity

An explicitly sequenced 8-step workflow with a dedicated validation/checks step and checklists; the validation step lacks an explicit 'if it fails, fix and re-run' feedback loop, which keeps it just below a 5.

4 / 5

Progressive Disclosure

Well-organized single-file structure with clear section headers and no nested references; with no bundle files present the content is appropriately self-contained, though some detail (e.g., failure-strategy semantics) could live in a reference file.

4 / 5

Total

16

/

20

Passed

Description

86%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, third-person description with explicit what/when structure and rich trigger terms. Its only weakness is that it describes one composite end-to-end action rather than enumerating several distinct concrete capabilities.

Suggestions

Expand the 'what' to list 2-3 distinct concrete actions (e.g., 'define config metadata, implement the sink runtime, wire registration and admin API') to raise specificity.

Tighten the 'protocol-compatible targets' clause to a concrete example so the trigger boundary is unambiguous.

DimensionReasoningScore

Specificity

Names the domain and a single composite action ("Implements new RobustMQ MQTT connector integrations end-to-end"), but does not enumerate multiple distinct concrete actions; the listed connector types function as triggers rather than separate capabilities.

3 / 5

Completeness

Explicitly answers both what ("Implements new RobustMQ MQTT connector integrations end-to-end using project conventions") and when ("Use when the user asks to add, implement, or support a new connector type...") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive natural trigger terms including synonym verbs ("add, implement, or support") and a broad list of named connector types (webhook, opentsdb, clickhouse, influxdb, cassandra, mqtt bridge) users would naturally say.

5 / 5

Distinctiveness Conflict Risk

Clear niche tied to a specific project and named connector types with minimal conflict risk; the "protocol-compatible targets" catch-all introduces minor overlap with generic integration skills.

4 / 5

Total

17

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
robustmq/robustmq
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.