CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-plugin-ecosystem

Ecosystem awareness for AI agent plugin systems — Claude Code, Cursor, agentskills.io standard, AAIF. Auto-loaded into agents writing skills, agents, or plugin manifests so output targets the correct schema and platform. Describes plugin.json schemas, SKILL.md portability constraints, cross-vendor differences, and self-update instructions when ecosystem changes occur.

84

1.47x

Quality

76%

Does it follow best practices?

Impact

100%

1.47x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/plugin-creator/skills/agent-plugin-ecosystem/SKILL.md
SKILL.md
Quality
Evals
Security

Evaluation results

100%

45%

Set Up a Claude Code Plugin Bundle for a Dev Team

Claude Code plugin manifest authoring

Criteria
Without context
With context

Manifest location

0%

100%

Kebab-case name

100%

100%

Agents as array of paths

50%

100%

Paths start with ./

0%

100%

Agents field completeness

100%

100%

Skills registered

100%

100%

Validation command in README

100%

100%

Comma-delimited allowed-tools

50%

100%

Without context: $0.5408 · 2m 19s · 26 turns · 31 in / 8,325 out tokens

With context: $0.6681 · 2m 23s · 34 turns · 285 in / 8,824 out tokens

100%

36%

Create a Portable SQL Query Helper Skill

Cross-vendor SKILL.md portability

Criteria
Without context
With context

Space-delimited allowed-tools

0%

100%

No user-invocable field

100%

100%

No model field

100%

100%

No argument-hint field

100%

100%

No agent field

100%

100%

No hooks field

100%

100%

Uses only portable fields

100%

100%

Notes mention delimiter choice

0%

100%

Notes mention avoided fields

40%

100%

Without context: $0.5205 · 2m 30s · 22 turns · 1,091 in / 7,325 out tokens

With context: $0.3585 · 1m 37s · 17 turns · 271 in / 5,231 out tokens

100%

13%

Set Up an OpenCode Skill with Database MCP Access

OpenCode MCP skill configuration

Criteria
Without context
With context

Inline mcp: frontmatter

100%

100%

Correct npx command

70%

100%

sidecar skill has no mcp frontmatter

100%

100%

mcp.json sidecar structure

100%

100%

mcp.json precedence documented

100%

100%

Server start timing

100%

100%

Idle timeout documented

100%

100%

Session end teardown

100%

100%

Pool key structure

23%

100%

Without context: $1.5458 · 4m 57s · 47 turns · 116 in / 8,802 out tokens

With context: $0.4579 · 1m 33s · 23 turns · 457 in / 5,818 out tokens

Repository
Jamie-BitFlight/claude_skills
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

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.