CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

75

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

The risk profile of this skill

SKILL.md
Quality
Evals
Security

Quality

Content

85%Scale 1-3

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

This is a well-structured skill with strong actionability and workflow clarity. It provides concrete commands, clear validation checkpoints with feedback loops, and good progressive disclosure to reference files. The main weakness is minor verbosity—a few sections (Philosophy, Anti-Patterns) could be tightened or removed, and there's slight redundancy between the workflow and validation sections.

DimensionReasoningScore

Conciseness

The skill is mostly efficient and avoids explaining basic concepts, but includes some sections that could be tightened—e.g., the 'Philosophy' section is a single bullet that adds little value, and the 'Anti-Patterns' section has only one item. Some repetition exists between the workflow steps and the validation section. Overall reasonably lean but not maximally tight.

2 / 3

Actionability

Provides concrete, executable bash and jq commands for inspection and validation, specific JSON examples showing input defects and fixes, and a structured YAML output format. The workflow steps are specific enough to act on, and the example input/output pair demonstrates exactly what a fix looks like.

3 / 3

Workflow Clarity

The 5-step workflow is clearly sequenced with explicit validation checkpoints: run validation before changing files (step 3), patch minimally (step 4), rerun the gate and report evidence (step 5). There's a clear feedback loop (validate → fix → revalidate) and a fail-fast directive. The failure mode section adds explicit stop conditions and blocker reporting.

3 / 3

Progressive Disclosure

The skill provides a compact overview with clear, well-signaled one-level-deep references to workflow.md, current-codex-plugin-runtime.md, and other reference files. Each reference includes a 'Read when' condition explaining when to consult it. Content is appropriately split between the main skill and reference files.

3 / 3

Total

11

/

12

Passed

Description

100%Scale 1-3

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

This is a strong description that clearly defines a narrow, specific domain (Codex plugin package verification) with explicit trigger conditions and concrete actions. It uses third person voice appropriately and includes a well-structured 'Use when...' clause with multiple natural trigger scenarios. The only minor concern is that the description is somewhat dense with technical terms, but these are precisely the terms users in this domain would use.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions: hardening, converting, auditing, pre-release checking, verifying manifest paths, bundled skills, hooks, MCP/app config, validation gates, and release blockers.

3 / 3

Completeness

Explicitly answers both what (verifying manifest paths, bundled skills, hooks, MCP/app config, validation gates, release blockers) and when ('Use when hardening, converting, auditing, or pre-release checking a Codex plugin package').

3 / 3

Trigger Term Quality

Includes strong natural trigger terms users would say: 'hardening', 'auditing', 'pre-release checking', 'Codex plugin', 'manifest', 'hooks', 'MCP', 'validation gates', 'release blockers'. These are domain-specific but exactly what a user working with Codex plugins would naturally mention.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive with a clear niche around Codex plugin packages specifically. The combination of 'Codex plugin', 'manifest paths', 'bundled skills', 'hooks', 'MCP/app config', and 'release blockers' creates a very specific domain unlikely to conflict with other skills.

3 / 3

Total

12

/

12

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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
jscraik/Agent-Skills
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.