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.

57

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

50%

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

The body is well-structured with a validation feedback loop, but it is held back by a duplicated line and, more seriously, by referencing six reference files that do not exist in the bundle, which breaks the workflow pointer and progressive disclosure. Most dimensions land at 2 as a result.

Suggestions

Ship the missing references/ bundle files (workflow.md, factory-governance-spine.md, contract.yaml, evals.yaml, task-profile.json, plugin-json-spec.md) so the cited detail and scaffold procedure actually resolve.

Remove the duplicated "Apply the context-disposition policy..." line to stop wasting tokens.

Inline a minimal sequenced scaffold step list in SKILL.md so the core workflow is actionable even before the reader opens references/workflow.md.

DimensionReasoningScore

Conciseness

The body is mostly lean and sectioned without over-explaining basics, but the context-disposition policy line is duplicated verbatim ("Apply the context-disposition policy..." appears twice) and a few paragraphs could be tightened, matching the score-2 anchor of mostly efficient but with unnecessary content.

2 / 3

Actionability

Concrete executable guidance exists in the Validation section (specific quick_validate.py and validate_skill_authoring_family.sh commands) and Required Behavior rules, but the core scaffold procedure is deferred to references/workflow.md which is not present in the bundle, leaving the main instruction incomplete.

2 / 3

Workflow Clarity

A validation checkpoint and feedback loop are present ("Fail fast: stop at first failed gate and report blocker text") plus a Failure mode section, but the actual multi-step scaffold sequence lives only in the missing references/workflow.md, so the sequence is present only by reference with the detail absent.

2 / 3

Progressive Disclosure

The body is well organized as an overview with a clearly signaled "Read when:" navigation block pointing one level deep, but all six references/* files it cites (workflow.md, factory-governance-spine.md, contract.yaml, evals.yaml, task-profile.json, plugin-json-spec.md) are absent from the bundle, so the disclosure is broken rather than delivering detail.

2 / 3

Total

8

/

12

Passed

Description

85%

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 specific, third-person description with an explicit Use-when trigger and a clear niche, so completeness and distinctiveness are strong. Trigger-term quality is the weakest dimension because the phrasing is jargon-heavy and lacks plain user-language variations.

Suggestions

Add plain-language trigger terms a user would naturally say (e.g. "create a plugin", "package a skill as a plugin", "move a skill into a plugin") alongside the technical ones.

Consider trimming domain jargon like "traceability or evidence contracts" in the opening sentence so the capability reads more naturally.

DimensionReasoningScore

Specificity

Lists multiple concrete actions such as "Scaffold Codex plugin packages with deterministic manifests, marketplace metadata, and traceability or evidence contracts", matching the score-3 anchor for listing several specific concrete actions.

3 / 3

Completeness

It explicitly answers what (scaffold plugin packages with manifests/metadata/contracts) and when (an explicit "Use when..." clause), satisfying the score-3 anchor for both an explicit what and an explicit when.

3 / 3

Trigger Term Quality

The "Use when creating plugin roots or adopting existing skills into plugin ownership" clause gives some relevant keywords, but the description leans on technical jargon ("deterministic manifests", "traceability or evidence contracts") and omits plainer variations a user might say (e.g. "create a plugin", "package a skill").

2 / 3

Distinctiveness Conflict Risk

The niche is sharply defined (Codex plugin scaffolding / skill adoption) with distinct triggers unlikely to fire for unrelated skills, matching the score-3 clear-niche anchor.

3 / 3

Total

11

/

12

Passed

Validation

81%

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

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

relative_links

Relative link issues: 3 missing, 1 suspicious

Warning

referenced_paths_exist

Referenced path issues: 10 missing

Warning

Total

13

/

16

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.