Create and manage Claude Code plugins with proper structure, manifests, and marketplace integration. Use when creating plugins for a marketplace, adding plugin components (commands, agents, hooks), bumping plugin versions, or working with plugin.json/marketplace.json manifests.
Install with Tessl CLI
npx tessl i github:softaworks/agent-toolkit --skill plugin-forgeOverall
score
93%
Does it follow best practices?
Validation for skill structure
Discovery
100%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 is a well-crafted skill description that excels across all dimensions. It provides specific actions, includes natural trigger terms users would actually use, explicitly states both what the skill does and when to use it, and occupies a clear niche that won't conflict with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Create and manage Claude Code plugins', 'adding plugin components (commands, agents, hooks)', 'bumping plugin versions', 'working with plugin.json/marketplace.json manifests'. | 3 / 3 |
Completeness | Clearly answers both what ('Create and manage Claude Code plugins with proper structure, manifests, and marketplace integration') and when ('Use when creating plugins for a marketplace, adding plugin components...'). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'plugins', 'marketplace', 'commands', 'agents', 'hooks', 'plugin versions', 'plugin.json', 'marketplace.json', 'manifests'. Good coverage of domain-specific terms. | 3 / 3 |
Distinctiveness Conflict Risk | Very specific niche targeting Claude Code plugins with distinct triggers like 'plugin.json', 'marketplace.json', 'plugin components'. Unlikely to conflict with general coding or documentation skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
87%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, actionable skill that efficiently covers plugin creation and management. The content is appropriately concise with executable examples and good progressive disclosure through reference tables. The main weakness is the lack of explicit validation steps in workflows, particularly for manifest updates and plugin installation verification.
Suggestions
Add validation checkpoint after step 3 (Register in Marketplace): e.g., 'Validate JSON: python -m json.tool marketplace.json'
Include verification step in local testing workflow: 'Verify installation: /plugin list should show plugin-name@marketplace-name'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Content is lean and efficient, using tables and code blocks without unnecessary explanation. Assumes Claude understands plugin concepts, versioning, and directory structures without over-explaining. | 3 / 3 |
Actionability | Provides fully executable bash commands, complete JSON examples, and specific file paths. The create_plugin.py and bump_version.py commands are copy-paste ready with all required flags documented. | 3 / 3 |
Workflow Clarity | Development workflow has clear numbered steps, but lacks validation checkpoints. No verification step after creating structure, no validation after updating manifests, and the testing workflow doesn't include a 'verify installation succeeded' step. | 2 / 3 |
Progressive Disclosure | Excellent structure with quick start at top, detailed workflows in middle, and clear references table at bottom pointing to one-level-deep documentation files. Navigation is well-signaled with tables for components, references, and scripts. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
87%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 14 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata' field is not a dictionary | Warning |
license_field | 'license' field is missing | Warning |
Total | 14 / 16 Passed | |
Table of Contents
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.