From claude-dream-team
Adapt to and collaborate with the project you're working in — detect its tech stack, honor its CLAUDE.md and conventions, and reuse its existing skills and agents before adding anything new. Use at the START of any claude-dream-team task (devops, development, or QA), on existing repos as well as fresh ones. Shared by all three agents.
How this skill is triggered — by the user, by Claude, or both
Slash command
/claude-dream-team:project-adaptationThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
The first move for every claude-dream-team agent. Adapt to the project as it is; never impose a default stack or workflow.
The first move for every claude-dream-team agent. Adapt to the project as it is; never impose a default stack or workflow.
Read manifests and lockfiles to learn the truth of the project — don't assume:
package.json, composer.json, requirements.txt/pyproject.toml, go.mod, pom.xml/build.gradle, Gemfile, Cargo.toml.package.json "scripts").Dockerfile, docker-compose.yml, .github/workflows, cloudbuild.yaml, Terraform, app.yaml.CLAUDE.md (and AGENTS.md / .cursorrules if present) and follow it. On any conflict, the project's instructions win over this plugin's defaults..claude/skills, installed plugin skills) and agents (.claude/agents) and prefer them. Use the project's existing commands and scripts.claude-dream-team agents collaborate through the main session. When the qa-engineer routes a finding to [fullstack-developer] or [devops-engineer], that agent implements the fix within its own boundaries, then QA re-verifies. The routing protocol lives in qa-testing → references/code-review.md; the /dream-team-review command automates the loop.
Provides CDSS development patterns for drug interaction checking, dose validation, clinical scoring (NEWS2, qSOFA), and alert classification integrated into EMR workflows.
npx claudepluginhub danniel-isiah-libor/danniel-claude-plugins --plugin claude-dream-team