Menü
Integration-test sub-skill that declares a pip CLI dependency.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
Author and maintain installable skill-manager units: skills, plugins, doc-repos, and harnesses. Read this before editing any file inside a unit — SKILL.md, its frontmatter or description, skill-manager.toml, plugin.json, harness.toml, or a references/ page — not only when creating one from scratch. Use when making a directory installable by skill-manager, choosing a unit kind, scaffolding a unit, writing or reviewing unit manifests/TOML, adding CLI or MCP dependencies, wiring references, validating install/bind/instantiate round-trips, preparing optional registry metadata, or shipping an edit to an already-installed unit so it reaches $SKILL_MANAGER_HOME (commit, push, then `skill-manager sync`). Detailed schemas live in references for skills, plugins, doc-repos, harnesses, scaffolding, coordinates/distribution, dependencies, bindings/sync, and skill-script.
Search, install, bind, sync, and remove skill-manager-managed units: skills, plugins, doc-repos, and harnesses; manage skill projects, project child homes, CLI tools, and MCP tools. Use when the user asks to find, add, remove, inspect, bind, unbind, instantiate, sync, upgrade, or resolve one of those surfaces. CLI syntax is authoritative in `skill-manager --help`; project workflows live in `references/projects.md`; gateway operations are authoritative in `references/virtual-mcp-gateway.md`; agent workflow routing lives in `references/workflows.md`.
Use when developing or iterating on installed skill-manager skills and plugins through project-local worktrees and the skill-dev CLI.
Use when demonstrating a contained skill inside an example plugin.
Use when demonstrating the minimum shape of a skill-manager skill.
Work with the test-graph validation system -- scaffold a test_graph project into a user repo, add JBang/uv nodes, compose graphs in build.gradle.kts, discover/plan them, run one graph or all graphs, and aggregate reports. Use whenever the user asks to set up validation nodes, compose a validation graph, run test_graph, or extend an existing test_graph project.
| name | pip-cli-skill |
| description | Integration-test sub-skill that declares a pip CLI dependency. |
| skill-imports | [] |
Installs pycowsay through the bundled uv so the smoke graph can assert a
pip-backed binary lands in bin/cli.
