CtrlK
BlogDocsLog inGet started
Tessl Logo

plugin-creator

Scaffold Codex plugin packages with deterministic manifests, marketplace metadata, and traceability or evidence contracts for non-trivial adoption. Use when creating plugin roots or adopting existing skills into plugin ownership.

46

Quality

48%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./Plugins/plugin-factory/fixtures/budget-archive/2026-04-21/deferred-store/skills/scaffolding_templates/plugin-creator/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

37%

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

This skill has reasonable structure and clear boundaries/constraints for plugin scaffolding, but it defers nearly all actionable workflow content to external references that aren't available in the bundle. The duplicated context-disposition paragraph and overlapping anti-pattern/gotcha sections reduce conciseness. The skill would benefit significantly from inlining at least a minimal step-by-step workflow with validation checkpoints rather than fully delegating to references/workflow.md.

Suggestions

Inline a minimal numbered workflow (5-7 steps) showing the core scaffold process with validation checkpoints, even if the full procedure lives in references/workflow.md. This would address the workflow_clarity gap.

Remove the duplicated 'Apply the context-disposition policy' paragraph and consolidate overlapping content between Anti-Patterns, Gotchas, and Constraints sections.

Add a concrete example of the expected plugin.json manifest structure (even a minimal one) to make the skill actionable without requiring reference file access.

Provide brief descriptions for each reference file in the References section so Claude knows when to consult each one without guessing.

DimensionReasoningScore

Conciseness

The skill has some unnecessary repetition (the context-disposition policy paragraph is duplicated verbatim) and includes sections like 'Remember' and 'Core Philosophy' that add little actionable value. The 'Gotchas' and 'Anti-Patterns' sections overlap somewhat. However, it's not egregiously verbose and mostly stays focused on plugin-specific guidance Claude wouldn't inherently know.

2 / 3

Actionability

The skill provides concrete examples of user requests, validation commands, and output field names, but the actual scaffold procedure is deferred entirely to 'references/workflow.md' which is not provided. The main body lacks executable code or step-by-step instructions for creating the plugin structure (e.g., what goes in plugin.json, directory layout). The validation bash commands are concrete and copy-paste ready, but the core task is abstract.

2 / 3

Workflow Clarity

The workflow section simply says 'Use the detailed scaffold procedure in references/workflow.md' without providing any inline steps. Since the bundle files are not provided, there is no visible workflow. For a skill involving file creation, moves, and manifest validation, the absence of any sequenced steps with validation checkpoints in the main body is a significant gap. The 'fail fast' note is good but insufficient without the actual workflow.

1 / 3

Progressive Disclosure

The skill references multiple external files (workflow.md, factory-governance-spine.md, contract.yaml, etc.) with clear 'Read when' signaling, which is good structure. However, since no bundle files are provided, we cannot verify these references exist. The main body defers too much core content to references, leaving the SKILL.md itself somewhat hollow. The references section at the bottom is a flat list without descriptions for most items.

2 / 3

Total

7

/

12

Passed

Description

59%

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 has good structural completeness with an explicit 'Use when...' clause and occupies a clearly distinct niche. However, it suffers from heavy jargon and buzzword-laden language ('deterministic manifests', 'evidence contracts for non-trivial adoption') that obscures what the skill actually does and makes it unlikely to match natural user queries. The trigger terms are too technical for practical skill selection.

Suggestions

Replace jargon like 'deterministic manifests' and 'evidence contracts for non-trivial adoption' with plain-language descriptions of what these actually produce (e.g., 'generate plugin configuration files, package metadata, and compliance documentation').

Add natural trigger terms users would actually say, such as 'create plugin', 'new Codex plugin', 'plugin setup', 'plugin boilerplate', or 'plugin template'.

DimensionReasoningScore

Specificity

It names a domain (Codex plugin packages) and some actions (scaffold, create manifests, marketplace metadata, traceability contracts), but the language is heavy on jargon ('deterministic manifests', 'evidence contracts for non-trivial adoption') rather than concrete, understandable actions. It's not as vague as a 1, but the actions are obscured by buzzwords.

2 / 3

Completeness

It does explicitly answer both 'what' (scaffold Codex plugin packages with manifests, metadata, and contracts) and 'when' ('Use when creating plugin roots or adopting existing skills into plugin ownership'). The 'Use when...' clause is present and explicit.

3 / 3

Trigger Term Quality

The terms used ('deterministic manifests', 'traceability or evidence contracts', 'non-trivial adoption', 'plugin roots') are highly technical jargon that users would almost never naturally say. Common terms like 'plugin', 'scaffold', and 'package' are present but buried among obscure terminology.

1 / 3

Distinctiveness Conflict Risk

The description is highly specific to 'Codex plugin packages' with a very narrow niche. It is unlikely to conflict with other skills due to its specialized domain and unique terminology.

3 / 3

Total

9

/

12

Passed

Validation

90%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

10

/

11

Passed

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.