CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

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

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 skill body with concrete file paths, explicit validation steps, and useful checklists and pitfalls. The main gaps are the absence of any copy-paste code examples, no explicit fix-and-revalidate feedback loop in the workflow, and minor duplication between the File Matrix and the step-by-step sections.

Suggestions

Add a feedback loop to the validation step (e.g., 'If cargo check fails, fix the reported errors and re-run before proceeding') to strengthen error recovery.

Include a short copy-paste skeleton (config struct with derive attributes, or a FromStr match arm) so the exact code shape is not left to inference.

Deduplicate the File Matrix (it restates paths from steps 1-8) or reframe it as a single cross-reference checklist to trim tokens.

DimensionReasoningScore

Conciseness

The body is efficient and assumes competence (no Rust/CI basics explained, just file paths, checklists, and rules), but the 'File Matrix' section repeats the file paths already given in steps 1-8 and the completion template repeats the verify command. This matches 'Efficient; minor instances of over-explanation that could be trimmed' rather than the lean level 5.

4 / 5

Actionability

Concrete guidance throughout: exact file paths, named struct methods ('as_str()', 'FromStr', 'send_batch()'), a runnable 'cargo check -p metadata-struct -p connector -p admin-server' command, and a completion template. Falls short of level 5 because it offers no copy-paste Rust examples (e.g., a skeleton config struct or a FromStr arm), leaving the exact code shapes to be inferred from existing connectors.

4 / 5

Workflow Clarity

The 8-step sequence is clearly ordered with an explicit 'Validation and Checks' section ('Run after edits', confirm no missing match arms, confirm docs contents) plus a File Matrix checklist and Common Pitfalls. Not level 5 because there is no explicit error-recovery feedback loop (e.g., 'if cargo check fails, fix and re-run'), though validation steps themselves are present, placing it above level 3.

4 / 5

Progressive Disclosure

No bundle files exist and all content is inline, but the body is well-organized with clear section headers, a fast path, and focused subsections, so navigation is easy. It sits at 'Good structure; most content is appropriately placed; minor organization gaps' rather than 5, since self-contained sections like 'Failure Strategy Semantics' and the docs listing could plausibly live in a one-level-deep reference file for a ~220-line skill.

4 / 5

Total

16

/

20

Passed

Description

82%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 what/when structure and a rich list of natural trigger terms anchored to a specific project niche. The only weakness is that the 'what' stays at the summary level rather than naming the concrete sub-actions of an end-to-end connector delivery.

Suggestions

Enumerate 2-3 concrete deliverables in the 'what' clause (e.g., 'metadata structs, connector runtime, registration wiring, admin API parsing, and docs') to lift specificity.

Add a few more natural trigger synonyms such as 'sink', 'destination', or standalone 'bridge' to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

The description names the domain ('RobustMQ MQTT connector integrations') and one concrete action ('Implements... end-to-end using project conventions'), but does not enumerate the constituent actions (metadata struct, runtime, registration, admin API, docs). This matches the anchor 'Names domain and 1-2 concrete actions, but not comprehensive', not the level above which requires several specific actions.

3 / 5

Completeness

It 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 such as...') with concrete trigger phrases, matching the anchor-5 example pattern exactly. Level 4 would require a less explicit 'when' clause, which is not the case here.

5 / 5

Trigger Term Quality

'add, implement, or support' plus concrete connector names (webhook, opentsdb, clickhouse, influxdb, cassandra, mqtt bridge) gives good natural-term coverage, but a few common phrasings users might say ('sink', 'destination', standalone 'bridge/integration') are missing. Not level 5, which demands comprehensive synonym coverage; clearly above level 3's partial coverage.

4 / 5

Distinctiveness Conflict Risk

The description occupies a clear niche (RobustMQ MQTT connectors) with named target systems and connector-specific triggers, making it unlikely to fire for unrelated skills. It matches 'Clear niche with distinct triggers; minimal conflict risk'.

5 / 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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

robustmq/robustmq

Path

.claude/skills/connector-delivery/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.