All authors
Claude Skills by Tekkiiiii
github.com/Tekkiiiii258 skills2 installs63 views
- Supabase DeployDeploy to Supabase — link a Supabase project, push database migrations safely, deploy edge functions with secrets, configure storage buckets and policies, validate everything is live. Supabase is primarily a backend-as-a-service (database, auth, serverless functions, storage) — static sites and frontend apps belong on Vercel or Netlify, not here. Trigger when: the user says "/supabase-deploy", "deploy to supabase", "push supabase migrations", or "supabase db push"; the user asks to link, init...Votes: 0GitHub stars: 3
- Supabase Postgres Best PracticesComprehensive performance optimization guide for Postgres, maintained by Supabase. Contains rules across 8 categories, prioritized by impact to guide automated query optimization and schema design.Votes: 0GitHub stars: 3
- Supabase SqlWrite, design, optimize, and debug SQL specifically for Supabase's PostgreSQL engine. Covers schema design, queries, Row Level Security (RLS) policies, migrations, query optimization, and Supabase-specific patterns (Auth triggers, Storage path tables, Realtime publications). Trigger when: the user asks to write or edit a SQL query; design a new table or modify an existing schema; optimize a slow query or fix a missing index; write or debug RLS policies; work with Supabase Auth, Storage, or Re...Votes: 0GitHub stars: 3
- Superpowers AutoplanUse when asked to "autoplan", "run the review pipeline", "full review", "review my plan", "check everything", "multi-review", or when you want to run CEO, design, and engineering reviews sequentially and surface taste decisions at a final gate. Orchestrates plan-ceo-review, plan-design-review, and plan-eng-review in sequence with a final approval gate.Votes: 0GitHub stars: 3
- Superpowers Brainstorming'Use before writing any code, scaffolding, or taking implementation actionVotes: 0GitHub stars: 3
- Superpowers CanaryPost-deploy canary monitoring. Watches the live app for console errors, performance regressions, and page failures. Takes periodic screenshots, compares against pre-deploy baselines, and alerts on anomalies. Use when: "monitor deploy", "canary", "post-deploy check", "watch production", "verify deploy".Votes: 0GitHub stars: 3
- Superpowers CodexOpenAI Codex CLI wrapper — three modes. Review: independent diff review with pass/fail gate. Challenge: adversarial mode that tries to break your code. Consult: ask Codex anything with session continuity. Use when asked to "get a second opinion", "run codex", "cross-model review", or "adversarial test".Votes: 0GitHub stars: 3
- Superpowers CsoUse when asked to "run a security audit", "security review", "check for vulnerabilities", "OWASP review", "threat model", "secrets audit", or when starting a new project with sensitive data. Chief Security Officer — 15-phase security audit covering attack surface, secrets archaeology, dependency supply chain, CI/CD, LLM security, skill supply chain, OWASP Top 10, and STRIDE threat modeling.Votes: 0GitHub stars: 3
- Superpowers Design ReviewDesign audit tool that crawls a live site, screenshots every page, runs a 10-category checklist (including AI slop detection), and iteratively fixes issues with atomic commits. For reviewing plans before implementation, use /superpowers-plan-design-review instead. Use when asked to "audit this site", "design review", "check the UI", or "visual QA".Votes: 0GitHub stars: 3
- Superpowers Dispatching Parallel Agents'Use when multiple independent problems exist and sequential investigationVotes: 0GitHub stars: 3
- Superpowers Document ReleasePost-ship documentation update. Reads all project docs, cross-references the diff, updates README/ARCHITECTURE/CONTRIBUTING/CLAUDE.md, polishes CHANGELOG voice, cleans up TODOS, and optionally bumps VERSION. Use after /superpowers-finishing-a-development-branch completes or after a significant PR lands.Votes: 0GitHub stars: 3
- Superpowers Executing Plans'Use when executing a written implementation plan in the current sessionVotes: 0GitHub stars: 3
- Superpowers Finishing A Development Branch'Use when all tasks in a plan are complete — run the full ship pipelineVotes: 0GitHub stars: 3
- Superpowers GuardUse when the user wants maximum safety — "guard mode", "full safety", "lock it down", "protect this", "maximum safety", "prod safety", "production guard". Combines destructive command warnings and directory-scoped edit restrictions. Use for prod work, live systems, or when you want to prevent accidental modifications outside a scope.Votes: 0GitHub stars: 3
- Superpowers Land And DeployUse when asked to "land and deploy", "merge and ship", "deploy this PR", "merge to production", "ship to prod", or after /ship creates a PR. Picks up after /ship — verifies CI, merges PR, waits for deploy, runs canary checks, and produces a deploy report.Votes: 0GitHub stars: 3
- Superpowers Office HoursUse when the user wants to explore a product idea, validate a concept, get clarity on what to build, or get unstuck on a product decision. YC-style product framing — six forcing questions that expose demand reality before any code is written. No implementation. Produces a design doc. Use when asked "office hours", "product framing", "think about this idea", "is this a good idea", "validate my concept", "what should I build", "help me clarify this".Votes: 0GitHub stars: 3
- Superpowers Plan Ceo ReviewUse when asked to "think bigger", "expand scope", "strategy review", "rethink this", "is this ambitious enough", "CEO review", or "founder review". CEO/founder-mode review of an implementation plan — finds the 10-star product, challenges premises, expands scope. Requires a plan file as input.Votes: 0GitHub stars: 3
- Superpowers Plan Design ReviewDesigner's eye plan review. Rates each design dimension 0-10, explains what would make it a 10, then fixes the plan to get there. Works in plan mode. For live site visual audits, use /superpowers-design-review. Use when asked to "review the design plan", "design critique", or "check the UX before building". Proactively suggest when the user has a plan with UI/UX components.Votes: 0GitHub stars: 3
- Superpowers Plan Eng ReviewEngineering plan review. Lock in the execution plan — architecture, data flow, diagrams, edge cases, test coverage, performance. Walks through issues interactively with opinionated recommendations. Use when asked to "review the architecture", "engineering review", or "lock in the plan". Proactively suggest when the user has a plan or design doc and is about to start coding.Votes: 0GitHub stars: 3
- Superpowers Qa OnlyReport-only QA testing. Systematically tests a web application and produces a structured report with health score, screenshots, and repro steps — but never fixes anything. Use when asked to "just report bugs", "qa report only", or "run QA without making changes".Votes: 0GitHub stars: 3
- Superpowers RetroUse when asked to "weekly retro", "what did we ship", "engineering retrospective", "sprint summary", "ship report", or proactively at the end of a work week or sprint. Analyzes commit history, work patterns, and code quality metrics with persistent history and trend tracking.Votes: 0GitHub stars: 3
- Superpowers Subagent Driven DevelopmentUse when executing a written plan with independent tasks dispatched to fresh subagents in parallel waves. Organizes tasks into dependency-ordered waves — independent tasks first, dependent tasks after — then dispatches each task to a fresh subagent with complete context, exact file paths, and verification steps. Two-stage review gates execution: spec compliance check before code quality check. Also for: executing multi-wave feature branches; running parallel independent tasks while preserving...Votes: 0GitHub stars: 3
- Superpowers Systematic DebuggingUse when encountering any bug, test failure, crash, or technical issue — find root cause before any fix attempt. Systematic five-phase debugging: (1) root cause investigation, (2) scope lock, (3) pattern analysis, (4) hypothesis testing, (5) implementation and verification. Enforces the iron law: NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST. Also for: intermittent failures, integration breakdowns, performance regressions, and state corruption issues where symptoms mask the underlying cause.Votes: 0GitHub stars: 3
- Superpowers Test Driven DevelopmentUse when writing any new code, fixing bugs, or changing behavior — enforces the RED-GREEN-REFACTOR cycle. Write the failing test first, watch it fail for the right reason, write the minimal code to pass it, then refactor. The iron law: no production code without a failing test first. Also for: regression-proofing existing code, driving design via tests, and ensuring bug fixes are captured as test cases. Skipping TDD even once is rationalization — always invoke when code will be written.Votes: 0GitHub stars: 3
- Superpowers UnbundleScope reduction mode — identify what can be cut from a plan or PR without losing core value. The opposite of plan-ceo-review's expansion mode. Use when asked to 'reduce scope', 'unbundle', 'trim the fat', or 'cut this down'. Runs a 7-step process: identify the ONE thing that must ship, inventory all scope items, categorize into Tier 1 through Tier 4, propose cuts one at a time, challenge secondary items, validate core still works, and document the cuts. Also for: pre-PR scope negotiation, spr...Votes: 0GitHub stars: 3
- Superpowers Using Git WorktreesUse after design approval and before starting implementation — creates an isolated Git worktree with verified clean test baseline so new work cannot affect main. Selects directory (.worktrees/ preferred, worktrees/ alternative), verifies Git-ignore safety for project-local paths, auto-detects project setup from package.json/Cargo.toml/go.mod, and runs baseline tests to confirm the worktree is production-clean. Also for: parallel feature work without branch juggling; enabling subagent worktree...Votes: 0GitHub stars: 3
- Superpowers Using SuperpowersUse when starting any conversation, task, or request — establishes how to discover and invoke superpowers skills via the Skill tool BEFORE taking any action or asking clarifying questions. Check for relevant skills first, then invoke with Skill tool, then announce and follow the skill workflow. Also for: resuming sessions, handling questions that look simple but have applicable skills, and onboarding new projects where skill discovery discipline must be established from the first message.Votes: 0GitHub stars: 3
- Superpowers Writing PlansUse when you have an approved spec or requirements for a multi-step task, before touching code. Transforms an approved design into a detailed, file-level implementation plan with one action per task step (2–5 min each), exact file paths, and complete code blocks. Saves plans to docs/superpowers/plans/YYYY-MM-DD-<feature-name>.md. Also for: breaking multi-subsystem specs into focused sub-plans, mapping file structure before task decomposition, triggering a plan-document-reviewer subagent for r...Votes: 0GitHub stars: 3
- Superpowers Writing SkillsUse when creating or modifying a skill in the skill library — applies TDD to process documentation. Core cycle: RED (run a pressure scenario WITHOUT the skill, document agent rationalizations), GREEN (write SKILL.md targeting those exact failures), REFACTOR (identify new rationalizations, add explicit counters, re-test). Also for: enforcing universal patterns (AskUserQuestion format, Completion Status protocol, Boil the Lake principle, Search Before Building), checking skill author compliance...Votes: 0GitHub stars: 3
- SvglFetch high-quality SVG logos for tech companies, frameworks, and tools from the SVGL API. Default tool for any icon or brand logo need in frontend projects. Supports icon + wordmark variants, light/dark mode, and 40 categories with 657+ logos.Votes: 0GitHub stars: 3
- SwarmParallel dispatch to all Project Directors in the agency — one-shot status, blocker, or priority check across the entire portfolio without loading PD context into the parent session. Spawns each PD in a fully isolated subagent that reads only their heartbeat file and responds in one line. Trigger when: the user says "/swarm", "/swarm-blocker", "/swarm-continue", or "/swarm-all"; you need a portfolio-wide status across all active projects at once; the user asks "what is everyone working on" or...Votes: 0GitHub stars: 3
- Sync Md JsonBidirectional sync between .json (authoritative source of truth) and .md (human-readable derivative) files — command-triggered, always writes fresh data from the source to the target. Trigger when: the user says "sync index", "sync md-json", "sync to md", or "sync to json"; a project status update needs to be committed to both formats; the user asks to "make sure index.json and index.md are in sync"; a new project was added or archived and both files need to reflect it. Key capabilities: JSON...Votes: 0GitHub stars: 3
- Task HandoffTier-A structured agent handoff protocol — no new infrastructure required, just discipline with the shared task store as the single coordination layer. When Agent A completes work that unblocks Agent B, Agent A writes outcome and next steps to the task store, creates Agent B's task, marks its own done, and moves on. Conversation context is not a handoff mechanism. Trigger when: an agent finishes a task and needs to unblock a downstream agent; you need to pass work between agents in a multi-st...Votes: 0GitHub stars: 3
- Task StoreStructured task coordination backed by a local SQLite database. The task store is the source of truth for pipeline state — not conversation context.Votes: 0GitHub stars: 3
- Tech StackAdvise on technology stack selection, architecture decisions, and tooling trade-offs — grounded in team context, scale requirements, and operational reality. Trigger when: the user asks "what tech should I use", "which framework", "should I use X or Y", "help me pick a database", "recommend a stack", or "what's best for building X?"; discussing starting a new project; comparing technologies or evaluating trade-offs; planning system architecture; reviewing an existing stack for improvements; o...Votes: 0GitHub stars: 3
- Tech WriterWrite developer docs, API references, README files, tutorials, inline comments, changelogs, ADRs, and runbooks. Trigger when writing any technical documentation. Purpose: Produces high-quality technical documentation across all common formats — from inline comments to full API references and multi-section READMEs. Follows Diátaxis principles (tutorial/how-to/reference/explanation) and prioritizes clarity and precision. When to trigger: (1) Writing "developer docs", "API reference", "README", ...Votes: 0GitHub stars: 3
- Terraform Search ImportDiscover existing cloud resources using Terraform Search queries and bulk import them into Terraform management. Use when bringing unmanaged infrastructure under Terraform control, auditing cloud resources, or migrating to IaC.Votes: 0GitHub stars: 3
- Terraform StacksComprehensive guide for working with HashiCorp Terraform Stacks. Use when creating, modifying, or validating Terraform Stack configurations (.tfcomponent.hcl, .tfdeploy.hcl files), working with stack components and deployments from local modules, public registry, or private registry sources, managing multi-region or multi-environment infrastructure, or troubleshooting Terraform Stacks syntax and structure.Votes: 0GitHub stars: 3
- Terraform Style GuideGenerate Terraform HCL code following HashiCorp's official style conventions and best practices. Use when writing, reviewing, or generating Terraform configurations.Votes: 0GitHub stars: 3
- Terraform TestComprehensive guide for writing and running Terraform tests. Use when creating test files (.tftest.hcl), writing test scenarios with run blocks, validating infrastructure behavior with assertions, mocking providers and data sources, testing module outputs and resource configurations, or troubleshooting Terraform test syntax and execution.Votes: 0GitHub stars: 3
- Tinybird Best PracticesGuidance for Tinybird file formats, SQL rules, optimization patterns, and data modeling.Votes: 0GitHub stars: 3
- Translationese Cleaner ViLàm sạch văn phong tiếng Việt dịch sát từ tiếng Anh, gồm trật tự câu, danh hóa, bị động, business cliché và cụm đúng ngữ pháp nhưng không tự nhiên. Dùng khi bản dịch hoặc bản nháp mang cấu trúc Anh-Việt; không dùng để thay đổi thuật ngữ chuẩn, đơn giản hóa văn bản pháp lý, hay tự dịch nội dung chưa có bản tiếng Việt.Votes: 0GitHub stars: 3
- Ui Ux Pro MaxDesign-system-first UI/UX skill for generating professional interfaces across React, Next.js, Vue, Nuxt, Svelte, SwiftUI, Flutter, and React Native. Trigger for UI work: landing pages, dashboards, components, UX improvements, visual redesigns, and design-system requests. Balances modern copy-paste ecosystems (shadcn/ui, Magic UI-style motion patterns) with equal framework parity and accessibility-first implementation. Purpose: Generates a complete, implementation-ready design system before UI...Votes: 0GitHub stars: 3
- UnfreezeClear the freeze boundary set by /freeze, allowing edits to all directories again. Use when you want to widen edit scope without ending the session. Use when asked to "unfreeze", "unlock edits", "remove freeze", or "allow all edits". (gstack)Votes: 0GitHub stars: 3
- UnwrapReads inbox task save-state files and resumes work autonomously — briefing + spawn. Trigger when the user invokes /unwrap [task-slug], says \"unwrap task\", \"pick up inbox task\", or \"continue task\". Similar to /pd-resume but for single inbox tasks: spawns a briefing subagent, collects the briefing, then spawns a task worker that starts the next action immediately. SSOT for task paths is ~/.claude/tasks/inbox/.Votes: 0GitHub stars: 3
- Upgrade StripeGuide for upgrading Stripe API versions and SDKsVotes: 0GitHub stars: 3
- Vercel DeployDeploy to Vercel — link project, configure environment variables, trigger deploy (preview or production), fetch logs, and validate health check. Use when: "deploy to vercel", "vercel deploy", "vercel env vars", "vercel link", "vercel production", "vercel preview". Purpose: End-to-end Vercel deployment — detect existing setup, authenticate, link or create the project, sync env vars, trigger a preview or production build, pull deploy logs, and verify the deployment is live. When to trigger: (1)...Votes: 0GitHub stars: 3
- Video UseEdit any video by conversation. Transcribe, cut, color grade, generate overlay animations, burn subtitles — for talking heads, montages, tutorials, travel, interviews. No presets, no menus. Ask questions, confirm the plan, execute, iterate, persist. Production-correctness rules are hard; everything else is artistic freedom.Votes: 0GitHub stars: 3
- Vietnamese LanguageVietnamese language reference layer — loaded on demand by other skills, pipelines, and agents. 17 reference files covering: platform-specific cultural dynamics (Facebook/TikTok/Instagram/LinkedIn/Zalo/YouTube/Twitter-X/Threads), formal document conventions, press release structure, viral content patterns, educational content norms, SEO/diacritic strategy, regional dialects, Gen Z slang taxonomy, advertising cultural frameworks, and email/messaging conventions. Does NOT duplicate content-creat...Votes: 0GitHub stars: 3
- Web PerfAnalyzes web performance using Chrome DevTools MCP. Measures Core Web Vitals (LCP, INP, CLS) and supplementary metrics (FCP, TBT, Speed Index), identifies render-blocking resources, network dependency chains, layout shifts, caching issues, and accessibility gaps. Use when asked to audit, profile, debug, or optimize page load performance, Lighthouse scores, or site speed. Biases towards retrieval from current documentation over pre-trained knowledge.Votes: 0GitHub stars: 3