Library documentation via Context7. Use for API references, code examples, framework docs.
Update project documentation based on recent changes. Use when user says "update docs", "document", "add documentation", "update readme", "write docs", or wants to improve…
Fix ALL issues via parallel agents with zero tolerance quality enforcement. Use when user says "fix", "fix issues", "fix errors", "fix all", "fix bugs", "fix lint", "fix tests",…
Dialectic thinking for code and architecture decisions — spawn thesis
Implement the next ready task. Use when starting a development session
Turn a requirement or idea into an EPIC with vertical-slice TASKs. Use
Conducts a deep, multi-round interview to clarify ambiguous requirements and produces a structured specification document.
Create a single TASK or REQ file from a template. Use for one-off artifact
Inter-agent messaging via ccgram swarm. Use when communicating with
Improve test design and coverage, including TDD/red-green-refactor guidance.
Audit AI coding-agent configuration against current features and local
Validate and deploy Kubernetes, Terraform, Helm, Kustomize, GitHub Actions,
Extract durable learnings from a session and propose project customizations
Writes git commit messages using conventional commits format with gitmoji. Use when creating git commits, preparing commit messages, or when the user asks to commit changes.
Report spec progress. Use when checking overall project state, viewing
Review Claude Code configuration for context efficiency, signal density,
Code review covering security, quality, tests, implementation, documentation,
Mark a task complete with evidence. Use when finishing a task, discovering
Token-optimized structural code search using tree-sitter AST parsing. Use instead of reading full files when you need to understand code structure, find functions, or explore a…
Multi-cloud security assessment and penetration testing capabilities. Execute Prowler/ScoutSuite assessments, analyze IAM policies, identify cloud misconfigurations, test…
Monitor a Claude Code team in tmux, auto-approve prompts, and report
Analyze AI coding agent usage, cost, efficiency, and burn rate — Claude
Web research via Pi web providers. Use for technical comparisons, recent
Explore public GitHub repositories in Pi using GitHub CLI, local clones,
Cloud CLI patterns for GCP and AWS. Use when running bq queries, gcloud
Prefer modern CLI tools — rg, fd, bat, eza, sd, dust, procs — over grep,
Idiomatic TypeScript development. Use when writing TypeScript code, Node.js
Batch refactoring via MorphLLM edit_file. Use for "refactor across files",
Simple web development with HTML, CSS, JS, and HTMX. Auto-activates when
Idiomatic Python 3.12+ development. Use when writing Python code, CLI
Idiomatic Go 1.25+ development. Use when writing Go code, designing APIs,
Intelligent codebase search and zoom-out mapping via WarpGrep. Use when
Review and score AI agent/skill instructions for quality across 8 dimensions:
Infrastructure patterns for Kubernetes, Terraform, Helm, Kustomize, and
Spec-driven development orientation and quick reference. Use when starting
Query project history, past decisions, and known gotchas from claude-mem