By ddunnock
Run deep tests, static analyses, security audits, and code reviews on Claude skills. Initialize sessions with skill paths or SKILL.md files, execute full pipelines capturing runtime I/O and API traces, resume interrupted runs, regenerate HTML reports, and get scored reviews of scripts, prompts, and security findings.
npx claudepluginhub ddunnock/claude-plugins --plugin skill-testerStatic analysis only — run inventory, deterministic scan, prompt lint, security audit, code review, and report (no test execution)
Initialize a skill-tester session — collect target skill, mode, sensitivity, test prompts, and report location
Regenerate HTML report from existing session data
Resume an interrupted skill-tester session from the last completed phase
Execute full analysis — all phases (2-9) including inventory, scan, prompt lint, test execution, security audit, code review, session trace, and report
Display session state — skill path, mode, session dir, phase completion, and next action
Runtime capture only — run inventory, test execution, session trace, and report (no security/code/prompt review)
Assesses skill script quality, anti-pattern compliance, documentation, idempotency, and dependency hygiene. Produces a scored code_review.json with per-script ratings and top recommendations.
Performs deep qualitative analysis of SKILL.md and agent instruction quality, using prompt_lint.json findings as grounding. Evaluates instruction clarity, goal alignment, ambiguity, and prompt engineering best practices.
Analyzes deterministic scan findings and raw scripts to produce a grounded security report with severity ratings and actionable fix recommendations.
Create and manage Claude Code skills, plugins, subagents, and hooks. Use when building new skills, validating existing skills, testing skills empirically, creating plugins, converting projects to plugins, creating hooks, or managing plugin automation. Includes /skills-toolkit:skill-composer, /skills-toolkit:skill-refiner, /skills-toolkit:skill-tester, /skills-toolkit:plugin-creator, /skills-toolkit:subagent-creator, /skills-toolkit:hook-creator, and /skills-toolkit:ask-user-question skills.
建立新技能、修改和改進現有技能、衡量技能效能。用於從零開始建立技能、編輯或優化現有技能、執行評估測試、基準測試效能分析、或優化技能描述以提升觸發準確度
Self-evolving skill engine for Claude Code. Creates, scores, repairs, and hardens skills autonomously through recursive improvement cycles.
Analyze and optimize your Agent Skills (SKILL.md) using session data and research-backed static checks. Works with Claude Code, Codex, and any Agent Skills-compatible agent.
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
Battle-tested Claude Code plugin for engineering teams — 53 agents, 203 skills, 69 legacy command shims, production-ready hooks, and selective install workflows evolved through continuous real-world use
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, and rules evolved over 10+ months of intensive daily use
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claim