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

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

100%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a well-structured, token-efficient overview with executable commands, an explicit validation feedback loop, and clear one-level-deep reference navigation. It scores well across all dimensions, with only minor reference-hygiene issues (orphaned bundle files and external Infrastructure links that do not resolve in this bundle).

Suggestions

Link the orphaned reference files present in references/ (hooks-contract.md, hooks.template.json, terminology-map.md) from the body, or remove them if unused, so the bundle surface matches the documented References list.

Resolve or qualify the Infrastructure/references/*.md links (openai-style-plugin-design-contract, first-principles-factory-gate, software-literature-*) which do not exist in this bundle, to avoid dead navigation paths.

Dimension	Reasoning	Score
Conciseness	The body is lean: short sections, a compact 5-step workflow, and real command/code fences with no explanatory padding about what plugins, hooks, or MCP are, so every token earns its place and it assumes Claude's competence.	3 / 3
Actionability	It gives concrete, copy-paste-ready commands (jq manifest query, find for bundled surfaces, the validation script) and a worked input-defect/fix example, matching the level-3 anchor of fully executable guidance with specific examples.	3 / 3
Workflow Clarity	The 5-step sequence includes an explicit pre-change validation checkpoint, a fail-fast directive, and a rerun-the-gate feedback loop (validate -> patch -> rerun) with pass/fail/blocked reporting, satisfying the level-3 anchor for clear sequencing with validation steps.	3 / 3
Progressive Disclosure	The SKILL.md is a compact overview that defers detail to one-level-deep, clearly signaled references via a 'Read when' navigation block, and the cited in-bundle references/*.md\|yaml\|json files all resolve; it is not a monolithic wall of text or deeply nested.	3 / 3
	Total	12 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, trigger-rich, and complete, clearly scoping the skill to Codex plugin hardening/conversion/auditing with an explicit 'Use when' clause and a concrete enumeration of what it verifies. It avoids fluff and uses neutral imperative voice.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions ("hardening, converting, auditing, or pre-release checking") and concrete verification targets ("manifest paths, bundled skills, hooks, MCP/app config, validation gates, and release blockers"), matching the level-3 anchor of multiple specific concrete actions; it is not merely naming a domain with some actions.	3 / 3
Completeness	It explicitly answers both what (the verifying-clause enumeration of manifest/skills/hooks/MCP/gates/blockers) and when (the explicit "Use when..." trigger), satisfying the level-3 anchor for both what and when with explicit triggers.	3 / 3
Trigger Term Quality	The "Use when hardening, converting, auditing, or pre-release checking a Codex plugin package" clause uses natural verbs a plugin author would actually say ("harden/audit/convert my plugin"), giving good coverage of trigger phrasing rather than abstract jargon.	3 / 3
Distinctiveness Conflict Risk	It is scoped tightly to "a Codex plugin package" with distinct hardening/auditing/converting triggers, a clear niche unlikely to fire for unrelated skills rather than a generic capability description.	3 / 3
	Total	12 / 12 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
Commit: 5a6027f

Reviewed: 5 days 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.