Agent Plugins Marketplace
← All plugins

eval-skill-catalog

v0.0.1

Eval-only fixture plugin. Provides synthetic SKILL.md stand-ins for names that skill-routing eval scenarios (evals/scenarios/skill_routing.yaml, overlay_work_requires_overlay_skill.yaml) reference but core does not itself ship: a placeholder overlay's workspace/legal-entity skill, its project dev skill, the generic language bibles, and the review skill named without a leading slash. Registered by teatree.eval.api_runner ONLY for a scenario that declares EvalSpec.available_skills, so the isolated eval clean room has a real, discoverable Skill-tool catalog entry for each. Not a real overlay, not shipped skill content, not installed for real use.

Claude Code8 Skills

1 GitHub starsUpdated 1 hour ago

Directory evidence

Runtimes
Claude Code
Parsed components
8 skill or MCP entries
Source updated
Sep 25, 2026
Manifest status
Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install eval-skill-catalog for Claude Code

Installs for the current user
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install eval-skill-catalog@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually
git clone https://github.com/souliane/teatree

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is evals/fixtures/skill_catalog/.

Plugin files

evals/fixtures/skill_catalog/
├── .claude-plugin/plugin.json
├── skills/ac-django/SKILL.md
├── skills/ac-python/SKILL.md
├── skills/architecture-design/SKILL.md
├── skills/backend-dev/SKILL.md
├── skills/frontend-dev/SKILL.md
├── skills/review/SKILL.md
├── skills/t3-widget/SKILL.md
└── skills/widget-le/SKILL.md

Included Skills8

ac-djangoskills/ac-django/SKILL.md

EVAL FIXTURE. Stand-in for the generic Django companion bible layered underneath a project's own backend dev skill for Django work. Placeholder only — see evals/scenarios/skill_routing.yaml (overlay_django_coding_loads_companion_bible).

ac-pythonskills/ac-python/SKILL.md

EVAL FIXTURE. Stand-in for the generic Python companion bible layered underneath a project's own backend dev skill for plain-Python (non-Django) work. Placeholder only — see evals/scenarios/skill_routing.yaml (overlay_python_coding_generalizes_to_python_bible).

architecture-designskills/architecture-design/SKILL.md

EVAL FIXTURE. Stand-in for the architecture/planning companion skill a planning scenario must self-load before drafting any plan. Placeholder only — see evals/scenarios/skill_routing.yaml.

backend-devskills/backend-dev/SKILL.md

EVAL FIXTURE. Stand-in for a hypothetical overlay's project dev skill (backend/Django flavour) — the standing companion skill loaded alongside the coding/reviewing phase skill for its backend repos. Placeholder only — see evals/scenarios/skill_routing.yaml.

frontend-devskills/frontend-dev/SKILL.md

EVAL FIXTURE. Stand-in for a hypothetical overlay's project dev skill (frontend flavour) — the standing companion skill loaded alongside the coding/reviewing phase skill for its frontend repos. Placeholder only — see evals/scenarios/skill_routing.yaml.

reviewskills/review/SKILL.md

EVAL FIXTURE. Stand-in for the code-review skill named without a leading slash by a scenario that must DERIVE it applies here rather than pattern-match a literal '/t3:review' in the prompt. Placeholder only — see evals/scenarios/skill_routing.yaml.

t3-widgetskills/t3-widget/SKILL.md

EVAL FIXTURE. Stand-in for a hypothetical overlay's multi-repo workspace playbook skill: worktree/run/test/review wiring for its repos. Placeholder only — see evals/scenarios/skill_routing.yaml and overlay_work_requires_overlay_skill.yaml.

widget-leskills/widget-le/SKILL.md

EVAL FIXTURE. Stand-in for a hypothetical overlay's legal-entity review skill, part of the declared reviewer skill set for its legal-entity repos. Placeholder only — see evals/scenarios/skill_routing.yaml.

Plugin manifests1

evals/fixtures/skill_catalog/.claude-plugin/plugin.json
{
  "name": "eval-skill-catalog",
  "version": "0.0.1",
  "description": "Eval-only fixture plugin. Provides synthetic SKILL.md stand-ins for names that skill-routing eval scenarios (evals/scenarios/skill_routing.yaml, overlay_work_requires_overlay_skill.yaml) reference but core does not itself ship: a placeholder overlay's workspace/legal-entity skill, its project dev skill, the generic language bibles, and the review skill named without a leading slash. Registered by teatree.eval.api_runner ONLY for a scenario that declares EvalSpec.available_skills, so the isolated eval clean room has a real, discoverable Skill-tool catalog entry for each. Not a real overlay, not shipped skill content, not installed for real use."
}

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[eval-skill-catalog on Agent Plugins Marketplace](https://pluginsmp.com/plugins/eval-skill-catalog)