CtrlK
BlogDocsLog inGet started
Tessl Logo

plugin-review

Read when reviewing a plugin PR or auditing an existing plugin script (server/plugins/*/script.py or equivalent). Covers the one check not already mechanically enforced by test_plugin_conventions.py - plugin scripts embedding their own raw SQL instead of an existing/new model method - plus a worked real-PR example.

71

Quality

86%

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

86%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 lean, highly actionable reviewer checklist that pairs a concrete review flow with a worked real-PR example and exact fixes, well-structured for a short single-purpose skill. The only soft spot is a couple of justifiable-but-verbose digressions that could be tightened without losing meaning.

DimensionReasoningScore

Conciseness

Dense and information-rich, assuming codebase familiarity and quoting CLAUDE.md rather than re-explaining layering; the GraphQL digression and the exception-list rationale are mildly verbose but purposeful (they stop a reviewer from giving wrong advice), so it sits at efficient-with-minor-trimming rather than the fully lean anchor 5.

4 / 5

Actionability

Provides a concrete numbered review flow with specific file paths and file:line references, and a worked real-PR example with exact fixes ('DeviceInstance().getByMac(mac) is not None', delete raw SQL; add 'DeviceInstance.getAllByName(name)') that are copy-paste-ready and cover the common cases.

5 / 5

Workflow Clarity

The 'Review flow for a raw SQL query in a plugin' gives a clear, sequenced four-step checklist whose steps are themselves validation checks; because this is a read-only review (not a destructive or batch operation) the validation cap does not apply, and the worked example reinforces the sequence, leaving only minor explicit-checkpoint gaps short of anchor 5.

4 / 5

Progressive Disclosure

Under 50 lines with no need for external references (no bundle files exist), and organized into clear sections (Scope, The check this skill adds, Review flow, Worked example); per the rubric's simple-skill guidance this qualifies for a 5 on well-organized sections alone.

5 / 5

Total

18

/

20

Passed

Description

87%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 highly specific, well-targeted description that clearly states both what the skill does and when to use it, with concrete trigger phrasing and strong distinctiveness from sibling skills. The only minor weakness is trigger-term breadth — a couple of natural synonyms would round it out.

DimensionReasoningScore

Specificity

Names several concrete actions ('reviewing a plugin PR', 'auditing an existing plugin script', detecting raw SQL embedding, a worked real-PR example) with full coverage of its narrow scope; falls just short of anchor 5 only because the skill's scope is a single check rather than a broad multi-action domain.

4 / 5

Completeness

Explicitly answers both 'what' (the raw-SQL-vs-model-method check plus a worked real-PR example) and 'when' ('Read when reviewing a plugin PR or auditing an existing plugin script') with concrete trigger phrases, matching the anchor 5 example.

5 / 5

Trigger Term Quality

The 'Read when reviewing a plugin PR or auditing an existing plugin script' clause supplies natural phrases a user would actually say; coverage is good but lacks synonyms or variations that would push it to anchor 5, and clearly exceeds the thin keyword sets of anchor 3.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (plugin-script raw-SQL review) and explicitly distinguishes itself from the author-facing [[plugin-development]] skill and the mechanically-enforced test_plugin_conventions.py checks, giving minimal conflict risk.

5 / 5

Total

18

/

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
netalertx/NetAlertX
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.