Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By workersio
Benchmark Claude Code agent skills against baselines via isolated eval sessions, layered grading with deterministic checks and LLM-as-judge, behavioral analysis, and USE/DON'T USE reports to quantify performance improvements and decide on adoption.
npx claudepluginhub workersio/specA collection of Claude Code plugins by workers.io.
Converts Claude Code conversations into reusable agents. The plugin analyzes your session -- the original task, every correction you made, tool calls, and the final output -- and distills it into an agent file saved to .claude/agents/. Agents are invocable with @agent-name in any future conversation and shared through version control. No server, no API, no accounts.
Writes Kani bounded model checker proofs for Solana and Rust programs. Includes reference docs covering proof patterns, invariant design, coverage workflows, Kani features, and Anchor verification.
Structured Solana smart contract security audits across 25 vulnerability types. Includes reference docs for each vulnerability, a cheatsheet, audit checklist, and exploit case studies.
Verify, check, transform, and repair Lean 4 proofs using the Axiom (Axle) API and CLI.
Benchmark any agent skill to measure whether it actually improves performance. Runs isolated eval sessions with and without the skill, grades outputs via layered grading (deterministic checks + LLM-as-judge), analyzes behavioral signals, and generates a comparison report with a USE / DON'T USE verdict.
npx skills add workersio/spec
This installs all plugins from the repository. Individual plugins can be selected during installation.
plugins/
save/ # Convert sessions into reusable agents
.claude-plugin/plugin.json
skills/save/SKILL.md
kani-proof/ # Kani bounded model checker proofs
.claude-plugin/plugin.json
skills/kani-proof/SKILL.md
skills/kani-proof/references/
solana-audit/ # Solana smart contract audits
.claude-plugin/plugin.json
skills/solana-audit/SKILL.md
skills/solana-audit/references/
axiom/ # Lean 4 proof verification via Axiom
.claude-plugin/plugin.json
skills/axiom/SKILL.md
skill-benchmark/ # Benchmark any agent skill
.claude-plugin/plugin.json
skills/skill-benchmark/SKILL.md
skills/skill-benchmark/scripts/
skills/skill-benchmark/agents/
skills/skill-benchmark/references/
Each plugin lives under plugins/ with its own .claude-plugin/plugin.json manifest and skills/ directory. The root .claude-plugin/marketplace.json catalogs all plugins for marketplace discovery.
MIT
Share bugs, ideas, or general feedback.
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Benchmark, evaluate, and optimize skills to ensure reliable performance across all LLMs
Evaluate Agent Skill design quality against official specifications and best practices. Use when reviewing, auditing, or improving SKILL.md files and skill packages.
Create and validate production-grade agent skills with 100-point marketplace grading
Professional skill and subagent creation with dual-mode workflow: 12-step fast mode and 15-step full mode with behavioral pressure testing and TDD integration.
Self-evolving skill engine for Claude Code. Creates, scores, repairs, and hardens skills autonomously through recursive improvement cycles.
Open collection of AI agent skills — reusable, framework-agnostic SKILL.md packages
Testing workflow skill for high-value test discovery, strategy, implementation, review, and suite health diagnostics.
Verify, check, transform, and repair Lean 4 proofs using the Axiom (Axle) API and CLI
Write Kani bounded model checker proofs for Solana and Rust programs
Convert Claude Code sessions into reusable agents
Structured Solana smart contract security audits
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