Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
npx claudepluginhub xobotyi/cc-foundry --plugin ai-helpersClaude Code extensibility and configuration reference: plugins, hooks, skills, subagents, MCP servers, output styles, memory, settings, and model configuration. Invoke whenever Claude Code itself is the subject — questions, configuration, building extensions, debugging, or understanding internals.
Design Claude Code output styles: persona, tone, and behavioral rules that replace the default system prompt. Invoke whenever task involves any interaction with output styles — creating, editing, evaluating, or changing how Claude communicates.
Prompt design techniques for LLMs: structure, examples, reasoning patterns, and optimization. Invoke whenever task involves any interaction with AI instructions — crafting, debugging, improving, or evaluating prompts for skills, agents, output styles, or system configurations.
Design and iterate Claude Code skills: SKILL.md structure, description formulas, content architecture, and quality evaluation. Invoke whenever task involves any interaction with Claude Code skills — creating, reviewing, evaluating, debugging, or improving skills.
Claude Code subagent lifecycle: creation, configuration, evaluation, and troubleshooting. Invoke whenever task involves any interaction with Claude Code subagents — designing, debugging, iterating, or deciding when to delegate work to isolated agent contexts.
Share bugs, ideas, or general feedback.
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 claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Software engineering discipline: output styles, coding fundamentals, and universal development practices
Skill and agent authoring tools: generate, audit, and improve Claude Code skills, commands, and agents
Skills for creating new agent skills for Claude Code and VS Code Copilot
Ultimate Claude Code skill creator. Design, scaffold, build, review, evolve, and publish production-grade AI agent skills following the Agent Skills open standard and 3-layer architecture.
Curate auto-memory, promote learnings to CLAUDE.md and rules, extract proven patterns into reusable skills.
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Infrastructure management discipline: Ansible automation, container orchestration, Proxmox virtualization, Unraid NAS, and network architecture
Open-source contribution discipline: issue writing, pull request creation, and contribution etiquette
PHP language discipline: conventions, modern idioms, type system, OOP, and testing
Git commit workflow: atomic commits, validation, conventions
Python language discipline: conventions, modern idioms, type system, packaging, testing, and LSP-powered code intelligence
Plugins that make Claude Code better at its job.
Claude Code is powerful out of the box, but it has gaps. It forgets skills mid-session. Commits are messy. Building AI artifacts is trial-and-error. Code ships without validation. These plugins fix that.
Add the marketplace, then install any plugin:
/plugin marketplace add xobotyi/cc-foundry
/plugin install <plugin-name>
Claude skips skills and forgets about them mid-session. This plugin injects a Skill Enforcement Framework via lifecycle hooks that forces Claude to evaluate which skills apply at every checkpoint: user prompt, after reading files, after editing, and after loading skills. Skills are treated as non-atomic — phase shifts (coding to testing) trigger re-evaluation of unread references from already-loaded skills.
/plugin install skill-enforcer
Messy commits — mixed changes, vague messages, wrong order. The /commit command enforces an 8-step pipeline: identify
logical units in the diff, plan commit order (style to refactor to fix to feature), run quality gates, self-review,
stage selectively, validate messages against conventions, commit, and verify. Each message runs through automated
validation before execution.
/plugin install git-commit
Planning is either too shallow or too detailed. This plugin provides a four-stage pipeline that produces artifacts consumable by both humans and agents: design documents (problem analysis and recommendation), technical designs (component mapping and sequencing), task decomposition (actionable hierarchies with acceptance criteria), and task creation (issue tracker items). Each stage builds on the previous with explicit approval gates.
/plugin install the-blueprint
Claude writes code before understanding what exists — guessing APIs, skipping tests, multiplying abstractions. This
plugin provides a coding skill that enforces a discovery-first workflow (Discover, Plan, Implement, Verify) and a
software-engineer output style with LSP-first navigation and engineering judgment. Runs before language-specific
skills as a prerequisite.
/plugin install the-coder
Code quality is checked manually or not at all. This plugin provides a two-level validation pipeline:
quality-validation checks that deliverables match the original request before completion, and
code-quality-evaluation orchestrates 8 specialized review agents (naming, complexity, comments, tests, error handling,
security, observability, documentation) that evaluate code in parallel. All agents are read-only — they report, you
decide.
/plugin install the-crucible
No visibility into context window usage, cost, or model. This plugin installs a 3-row status line to your user-level Claude configuration showing output style, model, session cost, context window remaining, cache hit rate, and current working directory. Color urgency increases as context approaches limits. Auto-syncs on every session start and survives agent directory changes.
/plugin install the-statusline
Agentic workflow mechanics — the foundational skills that make working with Claude Code effective across sessions and
teams. The claude-md skill applies prompt engineering principles to CLAUDE.md files: what belongs where, writing
instructions Claude actually follows, diagnosing why rules get ignored (buried, vague, stale, contradictory), and
systematic improvement. The handoff skill produces structured transfer documents when work crosses context boundaries
— session restarts, teammate delegation, async resumption — preserving decisions, constraints, and remaining work in
500-2000 tokens while dropping noise.
/plugin install the-workflow
Creating prompts, skills, agents, and output styles is guesswork without structured guidance. This plugin provides
skills encoding best practices for each artifact type: prompt-engineering (foundation), skill-engineering,
subagent-engineering, output-style-engineering, and claude-code-sdk (reference). All skills build on
prompt-engineering fundamentals. Includes an ai-engineer output style for collaborative artifact work.
/plugin install ai-helpers
Go has strong idioms that differ from other languages — premature abstraction, incorrect error handling, interface
misuse, and concurrency bugs are common pitfalls. This plugin provides a golang skill covering conventions, error
handling, interfaces, concurrency, testing, and project structure, plus a templ skill for type-safe HTML templating
with component composition, attribute handling, and JS integration.
/plugin install golang