CtrlK
BlogDocsLog inGet started
Tessl Logo

plugin-factory-router

Route plugin-factory requests to the right lane. Use when plugin creation, building, installation, review, or routing is broad, mixed, or under-specified.

60

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./Plugins/plugin-factory/skills/plugin-factory-router/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%Weight 40%Scale 1-3

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

A well-structured, read-only routing skill with concrete deliverables and a real validation command, but it is held back by repetitive prohibitions, a routing decision procedure that is only partially specified in-body, and several bundle-external references that cannot be verified.

Suggestions

Consolidate the repeated 'do not install/execute/fetch plugin code' rule into a single Execution Boundaries statement and remove the duplicates from Constraints, Gotchas, and Anti-Patterns to tighten token use.

Add an explicit numbered routing sequence (gather inputs -> apply First-Principles Gate -> select one lane -> return deliverables -> validate) so the workflow is sequenced with checkpoints rather than implied by topic sections.

Either include the referenced Infrastructure/references/* files in the bundle or rewrite those citations to point at bundle-local files, so every referenced path is verifiable.

DimensionReasoningScore

Conciseness

The body is mostly lean but repeats the same prohibitions across Execution Boundaries, Constraints, Gotchas, and Anti-Patterns (e.g. 'Do not install, execute, or fetch plugin code' appears ~4 times), which is tightening-worthy padding; it does not reach the lean 'every token earns its place' anchor at 3.

2 / 3

Actionability

Deliverables and the exact validation command are concrete, but the core routing decision procedure is delegated to workflow.md (which only lists lanes without selection criteria) and much of the body prescribes what not to do rather than a positive, executable routing procedure.

2 / 3

Workflow Clarity

Inputs, deliverables, and a fail-fast validation gate are present, but the routing process is organized by topic rather than as a numbered sequence with explicit checkpoints; the sequence is implied rather than laid out, matching the 'steps listed but gaps' anchor.

2 / 3

Progressive Disclosure

Local references (workflow.md, current-codex-plugin-runtime.md) are real, clearly signaled, and one level deep with 'Read when' triggers, but four referenced paths point to Infrastructure/references/* that are not present in the bundle, leaving those links unverifiable and slightly weakening the structure.

2 / 3

Total

8

/

12

Passed

Description

90%Weight 40%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.

A concise, third-person description with an explicit Use-when trigger and good natural keyword coverage for a well-scoped routing niche. Its only weakness is that the headline action ('route') is abstract rather than a concrete capability, which slightly limits specificity.

DimensionReasoningScore

Specificity

Names the domain ('plugin-factory') and enumerates concrete sub-tasks ('plugin creation, building, installation, review, or routing'), but the primary verb 'Route ... to the right lane' is a meta-action rather than a concrete capability, so it stops short of the multiple-specific-actions anchor at 3.

2 / 3

Completeness

Explicitly answers both 'what' ('Route plugin-factory requests to the right lane') and 'when' with an explicit 'Use when ...' clause, matching the anchor for clearly answering both.

3 / 3

Trigger Term Quality

Includes natural terms users would say ('plugin creation, building, installation, review, or routing') alongside the trigger condition 'broad, mixed, or under-specified', giving good coverage of the ways such requests are phrased.

3 / 3

Distinctiveness Conflict Risk

Targets a clear niche (ambiguous plugin-factory requests) with a distinct 'broad, mixed, or under-specified' trigger unlikely to fire for focused plugin-creator or plugin-installer skills.

3 / 3

Total

11

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

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.