By glorykidd
Interview workflow toolkit: pre-screening assessment, question guide, and scored post-interview evaluation with PDF export
Generate a pre-screening assessment for a candidate from their resume and the job description. Produces a structured strengths/gaps analysis and two targeted interview questions. Use before any interview to prepare. Saves to questions/<CandidateName>_assessment.md.
Build a structured interview question guide for a candidate, grounded in their pre-screening assessment. Includes the interviewer's spoken introduction, core questions with follow-ups and listen-fors, and closing notes. Use after assess-candidate and before the interview. Saves to questions/<CandidateName>_questions.md.
Initialize the interview workspace folder structure in the current directory. Creates candidates/, questions/, evaluations/, interviews/, and job-description/ if they do not already exist, and scaffolds a dnuckolls_intro.md template if one is not present.
Evaluate a job candidate using their resume, pre-screening assessment, interview transcript, and summary. Produces a scored markdown evaluation and PDF in the evaluations/ folder. Use this whenever you need to assess candidate fit after an interview, generate an evaluation report, or score a candidate against a job description.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A public marketplace of Claude Code plugins — skills, agents, and bundles you can browse and install.
| Name | Type | Description |
|---|---|---|
| commit-message | skill | Generate conventional commit messages from staged changes |
| pr-description | skill | Generate PR descriptions from branch diff |
| debug-assistant | bundle | Root cause analysis command + autonomous debugging agent |
| interview | skill | Full interview workflow: workspace setup, pre-screening assessment, question guide, and scored evaluation with PDF export |
| security-review | bundle | Comprehensive security audit against OWASP Top 10, CWE, NIST 800-53, CIS Benchmarks, SOC 2, ISO 27001 |
Each plugin lives in plugins/<name>/ and is described by a manifest at .claude-plugin/plugin.json. The registry.json at the root is the auto-generated index consumed by Claude Code when installing plugins.
Plugin types:
| Type | Description |
|---|---|
| skill | One or more slash commands (/plugin:command) |
| agent | One or more autonomous subagents |
| bundle | Both commands and agents |
| mcp | An MCP server, optionally with commands |
The templates/hello-world directory is a copy-paste starter that demonstrates the full plugin structure — a command, an agent, a skill router, and a manifest — with inline documentation explaining each piece.
See CLAUDE.md for the full contribution guide.
Quick steps:
templates/hello-world to plugins/<your-plugin-name>/.claude-plugin/plugin.json with your name, description, and author./generate-registry.sh.claude-plugin/marketplace.jsonnpx claudepluginhub glorykidd/marketplace --plugin interviewGenerate clear, conventional commit messages from staged changes
Generate detailed pull request descriptions from branch diff
Comprehensive security audit against OWASP Top 10, CWE, NIST 800-53, CIS Benchmarks, SOC 2, ISO 27001
Interactive debugging assistant with root cause analysis and fix suggestions
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows
Unity Development Toolkit - Expert agents for scripting/refactoring/optimization, script templates, and Agent Skills for Unity C# development