plugin-builder

Use when hardening, converting, auditing, or pre-release checking a Codex plugin package by verifying manifest paths, bundled skills, hooks, MCP/app config, validation gates, and release blockers.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Failed to scan

The risk profile of this skill

Quality

Content

85%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 hardening skill body: terse, action-oriented, with a clearly sequenced validate-then-patch-then-rerun workflow and proper one-level-deep references into a real bundle. The main weakness is minor duplication of the validation command and output example across sections.

Suggestions

De-duplicate the validation command (it appears in both the Workflow inspection block and the Validation section) by keeping it once and cross-referencing.

Consolidate the Outputs YAML and the Examples output-summary YAML so the canonical return shape appears once, with the example patch_diff shown only as the delta.

Replace the abstract step 4 ('Patch the smallest source surface that fixes...') with a concrete pointer to the per-defect remediation steps in references/workflow.md so the action is executable from the body alone.

Dimension	Reasoning	Score
Conciseness	The body is lean and sectioned with no padding explaining concepts Claude already knows, but the validation command and the output YAML each recur in two sections (Workflow+Validation, Outputs+Examples), creating minor redundancy that could be trimmed.	4 / 5
Actionability	Provides executable commands (jq manifest projection, find for bundled surfaces, the validate script) and concrete input/fix JSON plus output YAML, but steps like 'Patch the smallest source surface' and the `<plugin>` placeholder leave small gaps versus fully copy-paste-ready guidance.	4 / 5
Workflow Clarity	The five-step workflow is explicitly sequenced with a validate-before-change checkpoint (step 3) and a rerun-gate feedback loop (step 5), plus a 'Fail fast' rule — clear validation and error-recovery for a hardening/patching operation.	5 / 5
Progressive Disclosure	Overview body links one-level-deep to real bundle files via a 'Read when' matrix and a References section; the detailed procedure and contract docs are correctly pushed to references/workflow.md and the runtime/contract references, keeping the surface navigable.	5 / 5
	Total	18 / 20 Passed

Description

92%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, concrete description that clearly pairs a 'Use when' trigger with a comprehensive enumeration of the verification surfaces it owns. It is third-person/imperative in voice and tightly scoped to Codex plugin hardening with minimal conflict risk.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('hardening, converting, auditing, or pre-release checking') and enumerates specific verification targets ('manifest paths, bundled skills, hooks, MCP/app config, validation gates, and release blockers'), giving comprehensive coverage rather than a single generic action.	5 / 5
Completeness	Explicitly answers both 'what' (verifying manifest paths, bundled skills, hooks, MCP/app config, validation gates, release blockers) and 'when' via a concrete 'Use when...' clause with multiple trigger phrases.	5 / 5
Trigger Term Quality	'hardening, converting, auditing, pre-release checking' and 'Codex plugin package' are natural terms a user would say, but it leans on domain jargon ('manifest paths', 'MCP/app config') and omits common synonyms or file extensions a less technical user might use.	4 / 5
Distinctiveness Conflict Risk	Scoped to 'Codex plugin package' release/hardening — a clear niche with distinct triggers (hardening, converting, auditing, pre-release checking) that are unlikely to fire for unrelated skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: jscraik/Agent-Skills
Path: Plugins/plugin-factory/skills/code_quality_review/plugin-builder/SKILL.md
Commit: 2f91362

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.