By pandysp
Identify and verify unverified claims in the agent's own responses before presenting them as conclusions.
A collection of Claude Code plugins.
# Add the marketplace
/plugin marketplace add pandysp/claude-plugins
# Install a plugin
/plugin install <plugin-name>@pandysp
| Plugin | Category | Description |
|---|---|---|
| align | Workflow | Surface what the agent thinks the task is before producing any artifact |
| explore | Workflow | Map the terrain before designing — locate, trace, pattern, constrain |
| clarify | Workflow | Resolve underspecified decisions with targeted questions before designing |
| design-options | Workflow | Generate multiple strong design options with tradeoff profiles, anchored on the ideal |
| pre-mortem | Workflow | Identify how a plan or design could fail before committing |
| second-opinion | Workflow | Spawn 1-3 independent reviewers from other models for critical perspectives |
| steel-man-own-position | Workflow | Restate the strongest version of a prior position before flipping under pushback |
| spec | Workflow | Write the implementation spec that drives execution after design is chosen |
| verify-claims | Workflow | Identify and verify unverified claims before presenting them as conclusions |
| verify-result | Workflow | Black-box verification of any agent output — code, documents, presentations, configs |
| silent-failures | Workflow | Audit error handling for silent failures, inadequate feedback, and inappropriate fallbacks |
| preflight | Workflow | Honest self-assessment of completeness, correctness, quality, and loose ends before shipping |
| handoff | Workflow | Write a durable handoff — PR descriptions, summaries, memos, or memory notes |
| reflect | Workflow | Capture durable lessons from a session before they fade |
| understudy | Workflow | Write code, comments, tests, and commits that read as if the project's own maintainer wrote them |
| worktrunk-hook | Tooling | Route Claude Code's auto-created git worktrees through worktrunk so sessions inherit project hooks |
ruby scripts/validate.rb
CI runs the same validation on pull requests and pushes to main.
MIT
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub pandysp/claude-plugins --plugin verify-claimsUltra-compressed communication mode. Cuts 65% of output tokens (measured) while keeping full technical accuracy by speaking like a caveman.
Frontend design skill for UI/UX implementation
Memory compression system for Claude Code - persist context across sessions
Marketing skills for AI agents — conversion optimization, copywriting, SEO, paid ads, ad creative, and growth
Generate multiple strong design options with explicit tradeoff profiles, anchored against at least two ideal target architectures.
Multi-lens quality audit for docs, code, and other artifacts. 13 quality adjectives as audit lenses with per-domain translation sheets, a workflow-backed finder/verifier pipeline, and lens-yield reporting.
Black-box verification of any agent output — code, documents, presentations, reports, configs. Examine from the consumer's perspective and show evidence.
Surface what I think we're doing before acting on it — produces a structured manifest exposing every silent commitment so the user can correct course before any artifact is produced.
Get 1-3 independent second opinions from fresh Claude reviewers to strengthen your reasoning before presenting to the user.
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.