kamushadenes
132 verified skills139 total stars
mempalace-help
Show MemPalace help — available commands, usage tips, and getting started guidance.
data-ai2
mempalace
MemPalace — mine projects and conversations into a searchable memory palace. Use when asked about mempalace, memory palace, mining memories, searching memories, or palace setup.
tools2
web-ui-designer
Design and implement web UIs with a design-system-first approach. Use when building dashboards, admin panels, landing pages, or any web frontend. Covers design tokens, dark/light themes, responsive layouts, chart/data visualization, component architecture, and progressive enhancement. Works with any server-rendered stack (Go/Templ, Python/Jinja, Ruby/ERB, Node/EJS) or client-rendered framework (React, Vue, Svelte). Also use when redesigning existing UIs or adding new pages/views to an existing web app.
tools2
mempalace-status
Show MemPalace status — room counts, storage usage, and palace health.
data-ai2
mempalace-init
Initialize a new MemPalace — guided setup for your AI memory palace with ChromaDB backend.
development2
mempalace-search
Search your MemPalace — semantic search across all mined memories, projects, and conversations.
tools2
mempalace-mine
Mine a project or conversation into your MemPalace — extract and store memories for later retrieval.
tools2
gsd-new-workspace
Create an isolated workspace with repo copies and independent .planning/
tools1
gsd-remove-workspace
Remove a GSD workspace and clean up worktrees
tools1
gsd-remove-phase
Remove a future phase from roadmap and renumber subsequent phases
tools1
gsd-integration
Get Shit Done framework integration. Use when deciding between /gsd commands and direct execution for development tasks.
development1
caveman-commit
Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes /caveman-commit. Auto-triggers when staging changes.
development1
caveman-help
Quick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /caveman-help, "caveman help", "what caveman commands", "how do I use caveman".
tools1
caveman-review
Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", "/review", or invokes /caveman-review. Auto-triggers when reviewing pull requests.
development1
deep-review
Comprehensive code review using 9 specialized reviewer agents. Use when the user asks for a deep review, thorough code review, or comprehensive analysis. For faster review, suggest codex-review instead.
development1
docs
Generate or update comprehensive project documentation beyond README. Use for API reference, architecture decision records (ADRs), developer guides, contributing guides, configuration reference, deployment guides, migration guides, runbooks, changelogs, and release notes. Supports repo (docs/) or GitHub Wiki destinations. Always updates README.md via the `readme` skill as a final step. Triggers on "write docs", "document the API", "create a developer guide", "add an ADR", "write a runbook", "generate changelog", "docs wiki", or any documentation task that is NOT a README.
development1
feedback-loop
Update CLAUDE.md or rules when patterns of errors emerge
databases1
fix-pr
Fix PR review feedback and code scanning alerts. Use when the user asks to fix PR comments, address review feedback, resolve PR issues, or fix SAST alerts.
development1
github-actions-pro
GitHub Actions workflow management specialist. Use for gh run commands, workflow monitoring, log analysis, re-running jobs, and CI/CD debugging.
development1
playwriter
Control the user own Chrome browser via Playwriter extension with Playwright code snippets in a stateful local js sandbox via playwriter cli. Use this over other Playwright MCPs to automate the browser — it connects to the user's existing Chrome instead of launching a new one. Use this for JS-heavy websites (Instagram, Twitter, cookie/login walls, lazy-loaded UIs) instead of webfetch/curl. Run `playwriter skill` command to read the complete up to date skill
tools1
proxmox-admin
Proxmox VE administrator for container and VM management. Use for pct/qm commands, cluster operations, storage, and backups.
data-ai1
python-pro
Senior Python developer for Python 3.11+. Use for type-safe, async, production-ready code.
development1
readme
Generate or update comprehensive README.md files for any project. Use when the user says "write readme", "create readme", "update readme", or asks for help with README.md specifically. Produces thorough README covering setup, architecture, and deployment. Docs/wiki-aware — automatically includes a Documentation section linking to docs/ or GitHub Wiki when they exist. For broader project documentation (API reference, developer guides, runbooks, ADRs, changelogs), use the `docs` skill instead.
development1
rust-engineer
Senior Rust engineer for systems programming. Use for ownership, async Rust, and zero-cost abstractions.
development1
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
tools1
sql-pro
Senior SQL developer for query optimization and complex patterns. Use for PostgreSQL, MySQL, SQL Server.
development1
steampipe
Query cloud infrastructure and APIs using SQL with Steampipe. Use when querying AWS, GCP, Azure, or other cloud resources via SQL; checking compliance and security posture; finding misconfigurations or untagged resources; analyzing IAM policies, S3 buckets, EC2 instances, or any cloud resources; or when user mentions steampipe, cloud queries, or infrastructure analysis.
development1
terraform-engineer
Senior Terraform engineer for IaC. Use for module development, state management, and multi-cloud deployments.
development1
verification-loops
Verify changes work before completing. Use browser testing, test suites, and manual checks.
testing1
gsd-list-workspaces
List active GSD workspaces and their status
tools1
caveman-review
Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", "/review", or invokes /caveman-review. Auto-triggers when reviewing pull requests.
development1
golang-pro
Senior Go developer for concurrent, cloud-native systems. Use for Go 1.21+ with goroutines, channels, gRPC, and performance optimization.
development1
spec-miner
Reverse-engineer specifications from undocumented code. Use for legacy systems or creating documentation from implementations.
development1
gsd-add-phase
Add phase to end of current milestone in roadmap
tools1
gsd-add-backlog
Add an idea to the backlog parking lot (999.x numbering)
tools1
gsd-analyze-dependencies
Analyze phase dependencies and suggest Depends on entries for ROADMAP.md
testing1
gsd-code-review-fix
Auto-fix issues found by code review in REVIEW.md. Spawns fixer agent, commits each fix atomically, produces REVIEW-FIX.md summary.
development1
gsd-manager
Interactive command center for managing multiple phases from one terminal
tools1
gsd-next
Automatically advance to the next logical step in the GSD workflow
tools1
gsd-plant-seed
Capture a forward-looking idea with trigger conditions — surfaces automatically at the right milestone
tools1
gsd-set-profile
Switch model profile for GSD agents (quality/balanced/budget/inherit)
testing1
commit-push-pr
Commit, push, and open a PR. Use when the user asks to create a pull request, open a PR, or push and create PR.
tools1
caveman-help
Quick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /caveman-help, "caveman help", "what caveman commands", "how do I use caveman".
tools1
qa-fix
Pick a bug from .omc/qa-bugs.md, fix it via the OMC executor, and verify the fix with Playwright. Use when the user wants to fix QA bugs from a previous audit. Optionally specify a bug number to fix a specific bug.
testing1
new-lxc
Create a new NixOS LXC container on Proxmox with impermanence, configured for specified services. Provide services and description in your instructions. Also supports migration mode when called from the migrate-lxc skill.
testing1
commit
Create a git commit. Use when the user asks to commit changes, save work, or create a commit.
tools1
migrate-lxc
Migrate a non-NixOS LXC container to NixOS with impermanence, handling configuration extraction, secrets via agenix, data migration, and cross-host IP reference resolution. Provide origin SSH, target SSH (or "new"), service type, and description.
data-ai1
caveman-commit
Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes /caveman-commit. Auto-triggers when staging changes.
development1
gsd-ui-review
Retroactive 6-pillar visual audit of implemented frontend code
development1
gsd-scan
Rapid codebase assessment — lightweight alternative to /gsd-map-codebase
development1
gsd-reapply-patches
Reapply local modifications after a GSD update
tools1
gsd-plan-milestone-gaps
Create phases to close all gaps identified by milestone audit
testing1
gsd-note
Zero-friction idea capture. Append, list, or promote notes to todos.
tools1
gsd-insert-phase
Insert urgent work as decimal phase (e.g., 72.1) between existing phases
testing1
gsd-do
Route freeform text to the right GSD command automatically
tools1
gsd-add-todo
Capture idea or task as todo from current conversation context
tools1
typescript-pro
Senior TypeScript specialist for type-safe full-stack apps. Use for advanced generics, discriminated unions, and strict mode.
development1
compress
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman:compress <filepath> or "compress memory file"
development1
gsd-new-milestone
Start a new milestone cycle — update PROJECT.md and route to requirements
tools1
gsd-debug
Systematic debugging with persistent state across context resets
development1
gsd-docs-update
Generate or update project documentation verified against the codebase
development1
gsd-autonomous
Run all remaining phases autonomously — discuss→plan→execute per phase
data-ai1
gsd-audit-uat
Cross-phase audit of all outstanding UAT and verification items
testing1
gsd-progress
Check progress, advance workflow, or dispatch freeform intent — the unified GSD situational command
testing1
gsd-secure-phase
Retroactively verify threat mitigations for a completed phase
testing1
gsd-ui-phase
Generate UI design contract (UI-SPEC.md) for frontend phases
development1
gsd-ultraplan-phase
[BETA] Offload plan phase to Claude Code's ultraplan cloud; review in browser and import back.
development1
gsd-update
Update GSD to latest version with changelog display
testing1
gsd-undo
Safe git revert. Roll back phase or plan commits using the phase manifest with dependency checks.
testing1
gsd-validate-phase
Retroactively audit and fill Nyquist validation gaps for a completed phase
testing1
gsd-new-project
Initialize a new project with deep context gathering and PROJECT.md
tools1
gsd-ns-ideate
exploration capture | explore sketch spike spec capture
tools1
gsd-ns-review
quality gates | code review debug audit security eval ui
development1
gsd-ns-project
project lifecycle | milestones audits summary
testing1
gsd-ns-context
codebase intelligence | map graphify docs learnings
development1
gsd-profile-user
Generate developer behavioral profile and create Claude-discoverable artifacts
development1
gsd-quick
Execute a quick task with GSD guarantees (atomic commits, state tracking) but skip optional agents
data-ai1
gsd-plan-phase
Create detailed phase plan (PLAN.md) with verification loop
data-ai1
gsd-pr-branch
Create a clean PR branch by filtering out .planning/ commits — ready for code review
development1
gsd-resume-work
Resume work from previous session with full context restoration
tools1
gsd-pause-work
Create context handoff when pausing work mid-phase
tools1
gsd-ai-integration-phase
Generate an AI-SPEC.md design contract for phases that involve building AI systems.
development1
gsd-discuss-phase
Gather phase context through adaptive questioning before planning.
tools1
gsd-ns-manage
config workspace | workstreams thread update ship inbox
tools1
gsd-phase
CRUD for phases in ROADMAP.md — add, insert, remove, or edit phases
tools1
gsd-ns-workflow
workflow | discuss plan execute verify phase progress
testing1
gsd-ship
Create PR, run review, and prepare for merge after verification passes
tools1
gsd-execute-phase
Execute all plans in a phase with wave-based parallelization
tools1
gsd-explore
Socratic ideation and idea routing — think through ideas before committing to plans
tools1
gsd-forensics
Post-mortem investigation for failed GSD workflows — diagnoses what went wrong.
data-ai1
gsd-audit-fix
Autonomous audit-to-fix pipeline — find issues, classify, fix, test, commit
testing1
gsd-import
Ingest external plans with conflict detection against project decisions before writing anything.
testing1
gsd-map-codebase
Analyze codebase with parallel mapper agents to produce .planning/codebase/ documents
development1
gsd-graphify
Build, query, and inspect the project knowledge graph in .planning/graphs/
development1
gsd-settings
Configure GSD workflow toggles and model profile
data-ai1
caveman
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
testing1
gsd-join-discord
Join the GSD Discord community
tools1
caveman
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
testing1
gsd-code-review
Review source files changed during a phase for bugs, security issues, and code quality problems
development1
gsd-mvp-phase
Plan a phase as a vertical MVP slice — user story, SPIDR splitting, then plan-phase
tools1
gsd-health
Diagnose planning directory health and optionally repair issues
data-ai1
gsd-plan-review-convergence
Cross-AI plan convergence loop — replan with review feedback until no HIGH concerns remain.
data-ai1
gsd-extract-learnings
Extract decisions, lessons, patterns, and surprises from completed phase artifacts
testing1
gsd-capture
Capture ideas, tasks, notes, and seeds to their destination
tools1
gsd-audit-milestone
Audit milestone completion against original intent before archiving
testing1
gsd-add-tests
Generate tests for a completed phase based on UAT criteria and implementation
testing1
gsd-cleanup
Archive accumulated phase directories from completed milestones
tools1
gsd-complete-milestone
Archive completed milestone and prepare for next version
tools1
gsd-eval-review
Audit an executed AI phase's evaluation coverage and produce an EVAL-REVIEW.md remediation plan.
testing1
gsd-ingest-docs
Bootstrap or merge a .planning/ setup from existing ADRs, PRDs, SPECs, and docs in a repo.
documentation1
gsd-milestone-summary
Generate a comprehensive project summary from milestone artifacts for team onboarding and review
tools1
gsd-fast
Execute a trivial task inline — no subagents, no planning overhead
data-ai1
gsd-inbox
Triage and review open GitHub issues and PRs against project templates and contribution guidelines.
documentation1
gsd-help
Show available GSD commands and usage guide
documentation1
gsd-spec-phase
Clarify WHAT a phase delivers with ambiguity scoring; produces a SPEC.md before discuss-phase.
tools1
gsd-review
Request cross-AI peer review of phase plans from external AI CLIs
tools1
gsd-sketch
Sketch UI/design ideas with throwaway HTML mockups, or propose what to sketch next (frontier mode)
development1
gsd-spike
Spike an idea through experiential exploration, or propose what to spike next (frontier mode)
tools1
gsd-stats
Display project statistics — phases, plans, requirements, git metrics, and timeline
tools1
gsd-workstreams
Manage parallel workstreams — list, create, switch, status, progress, complete, and resume
tools1
gsd-config
Configure GSD settings — workflow toggles, advanced knobs, integrations, and model profile
data-ai1
gsd-thread
Manage persistent context threads for cross-session work
tools1
gsd-review-backlog
Review and promote backlog items to active milestone
tools1
gsd-workspace
Manage GSD workspaces — create, list, or remove isolated workspace environments
tools1
gsd-list-phase-assumptions
Surface the agent's assumptions about a phase approach before planning
data-ai1
gsd-verify-work
Validate built features through conversational UAT
testing1
gsd-intel
Query, inspect, or refresh codebase intelligence files in .planning/intel/
development1
gsd-session-report
Generate a session report with token usage estimates, work summary, and outcomes
business1
qa
QA audit of a web app using Playwright -- find all UI/UX bugs and save to .omc/qa-bugs.md so OMC workflows (`/qa-fix`, autopilot, ralph) can resume from the report. Use when the user asks for QA testing, UI bug hunting, or web app auditing. Provide the URL and optional focus areas in your instructions.
development1
code-stats
Analyze codebase statistics with tokei (line counts by language) and difft (semantic AST-aware diffs). Use for project composition, refactoring scope, codebase metrics.
development1
gsd-research-phase
Research how to implement a phase (standalone - usually use /gsd-plan-phase instead)
research1
gsd-check-todos
List pending todos and select one to work on
testing1