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
Quality
76%
Does it follow best practices?
Impact
100%
1.47xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/plugin-creator/skills/agent-plugin-ecosystem/SKILL.mdQuality
Discovery
72%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 description effectively identifies a specialized niche with good trigger terms covering multiple platforms and technical concepts. However, it lacks an explicit 'Use when...' clause and describes what the skill contains rather than what actions Claude will perform with it. The passive framing ('Auto-loaded into agents') weakens the actionability.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when writing or editing SKILL.md files, plugin.json manifests, or building cross-platform agent plugins.'
Reframe from describing contents to describing actions, e.g., 'Guides creation of portable skill files and plugin manifests across Claude Code, Cursor, and agentskills.io platforms.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (AI agent plugin systems) and lists some actions like 'Describes plugin.json schemas, SKILL.md portability constraints, cross-vendor differences, and self-update instructions' but these are more about what it contains than concrete actions Claude would perform. | 2 / 3 |
Completeness | The 'what' is reasonably covered (ecosystem awareness, schema descriptions, portability constraints), but there's no explicit 'Use when...' clause. The phrase 'Auto-loaded into agents writing skills, agents, or plugin manifests' implies when but doesn't provide explicit trigger guidance. | 2 / 3 |
Trigger Term Quality | Good coverage of natural terms: 'Claude Code', 'Cursor', 'agentskills.io', 'AAIF', 'skills', 'agents', 'plugin manifests', 'plugin.json', 'SKILL.md' are all terms users would naturally use when working in this domain. | 3 / 3 |
Distinctiveness Conflict Risk | Very clear niche targeting AI agent plugin ecosystems with specific platform names (Claude Code, Cursor, agentskills.io, AAIF). Unlikely to conflict with other skills due to the specialized domain and explicit platform references. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
79%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality reference skill that efficiently documents cross-platform plugin ecosystem differences. Its strengths are precise, actionable specifications with concrete examples and clear platform distinctions. Minor weaknesses include the monolithic structure (OpenCode section could be separate) and the self-update protocol lacking explicit validation steps for verifying ecosystem changes.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, presenting only ecosystem-specific facts Claude wouldn't inherently know. No unnecessary explanations of basic concepts; every section delivers actionable platform-specific information. | 3 / 3 |
Actionability | Provides concrete, copy-paste ready examples including exact manifest paths, YAML/JSON snippets for MCP configuration, and specific validation commands. The allowed-tools delimiter difference is precisely documented with examples. | 3 / 3 |
Workflow Clarity | The mermaid flowchart provides good decision guidance, but the self-update protocol lacks explicit validation steps. For a reference skill rather than a procedural one, the workflow is adequate but could benefit from clearer verification checkpoints when updating ecosystem facts. | 2 / 3 |
Progressive Disclosure | Content is well-organized with clear sections, but it's a monolithic file with no references to external detailed documentation. The OpenCode extensions section is quite detailed and could be split out. External URLs are provided but as sources, not as 'see X for more details' navigation. | 2 / 3 |
Total | 10 / 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.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- Jamie-BitFlight/claude_skills
- Commit
5667e97
- 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.