From decision-evaluation-framework
Orchestrator — analyze a decision through multiple frameworks in parallel. Reads a decision file, fans out to N framework subagents simultaneously (one per selected framework), each produces a structured analysis fragment, then synthesis aggregates the results. Use this when the user wants a multi-lens evaluation of a major decision rather than running individual frameworks.
npx claudepluginhub danielrosehill/claude-code-plugins --plugin decision-evaluation-frameworkThis skill uses the workspace's default tool permissions.
The main entry point. Runs a portfolio of decision frameworks in parallel against a single decision and produces structured per-framework outputs plus a synthesis.
Provides UI/UX resources: 50+ styles, color palettes, font pairings, guidelines, charts for web/mobile across React, Next.js, Vue, Svelte, Tailwind, React Native, Flutter. Aids planning, building, reviewing interfaces.
Fetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.
Analyzes multiple pages for keyword overlap, SEO cannibalization risks, and content duplication. Suggests differentiation, consolidation, and resolution strategies when reviewing similar content.
Share bugs, ideas, or general feedback.
The main entry point. Runs a portfolio of decision frameworks in parallel against a single decision and produces structured per-framework outputs plus a synthesis.
DATA_ROOT="${CLAUDE_USER_DATA:-${XDG_DATA_HOME:-$HOME/.local/share}/claude-plugins}/decision-evaluation-framework"
CONFIG="$DATA_ROOT/config.json"
If the config doesn't exist, tell the user to run /decision:onboard first.
The user invokes this with:
/decision:new-decision first to scaffold a file, then proceed).Optional flags / arguments:
--bundle=<name> — use a named bundle from config.--frameworks=cost-benefit,pre-mortem,... — explicit framework list.default_frameworks from config.Load the decision file. Confirm it has the expected sections (Context, Options, Constraints, Stakeholders, etc.). If it's incomplete, offer to complete it interactively before continuing.
Resolve framework list. Bundle name → list, explicit list, or default. Validate every name corresponds to a file in the plugin's frameworks/ directory.
Create the analysis workspace at <output_root>/<YYYY-MM-DD>-<slug>/:
<slug>/
decision.md # copy of the input decision
fragments/ # per-framework outputs land here
synthesis.md # written by /decision:synthesize
analysis.pdf # written by /decision:render-pdf
Fan out IN PARALLEL. Launch N subagents in a single message with N Task tool calls (subagent_type: general-purpose). Each subagent receives:
Apply the <framework-name> framework to the following decision.
Decision file: <absolute path to decision.md>
Framework guide: <absolute path to frameworks/<framework-name>.md>
Read the decision fully. Read the framework guide fully. Apply the framework
exactly as the guide specifies. Write your analysis to:
<absolute path to fragments/<framework-name>.md>
Use the output structure the guide prescribes. Conclude with a 0-100 score
per the guide's scoring instruction. Do not invent additional frameworks.
The parallel fan-out is mandatory — sequential execution is much slower and produces less independent perspectives.
Wait for all subagents to finish. Verify each fragment file was written. Re-run any that failed.
Synthesize. Invoke /decision:synthesize <slug-folder> to produce the cross-framework synthesis (or run that skill's logic inline).
Offer to render — ask the user if they want a PDF (/decision:render-pdf) and/or upload to Drive (/decision:export).
Report the workspace path and the synthesis verdict.
/decision:new-decision.--frameworks with an unknown name, list available frameworks and ask.