All authors
Claude Skills by Tekkiiiii
github.com/Tekkiiiii258 skills2 installs63 views
- Product CritiqueSenior product manager who critiques product strategies, feature specs, roadmaps, user flows, pricing, and packaging decisions — acting as a rigorous product reviewer. Produces a structured critique report with severity ratings (Critical/High/Medium/Low) across 7 dimensions: problem clarity, user fit, solution viability, go-to-market logic, competitive positioning, success metrics, and technical feasibility. Use when the user says 'review product', 'critique this roadmap', 'product review', '...Votes: 0GitHub stars: 3
- Project Expansion ScoutConfigure and run the Project Expansion Scout — an autonomous strategic growth agent that scans active projects for expansion opportunities, consults the BOD for configurable feasibility approval (default >80%), and adds approved expansion phases to PROJECT.md. Trigger when you want to set up, configure, invoke, or manage the expansion scout loop. Scenarios: when you want to be more intentional about growth than reactive firefighting, when a project has stalled with no next phase in sight, wh...Votes: 0GitHub stars: 3
- Project StatusMaintain machine-readable project status snapshots for instant context at the start of any session, eliminating the need to re-derive project state from package.json, Cargo.toml, or git history. A lightweight PROJECT.md convention in every project root: YAML frontmatter for machine parsing (status, phase, version, last_session, tech_stack, blockers, focus) plus a brief prose section for human context. Triggered: automatically at session start (read PROJECT.md first, then work), when starting ...Votes: 0GitHub stars: 3
- Promt EngineeringWrite, optimize, and debug LLM prompts — system prompts, task prompts, and prompt templates. Trigger when: the user wants to write or improve a system prompt; asks 'how do I prompt Claude/GPT/Gemini to [X]'; a prompt keeps giving bad or inconsistent outputs; wants to build a prompt template; asks about few-shot, chain-of-thought, or role-based prompting; wants to reduce hallucinations or improve AI output quality; or asks to evaluate or critique a prompt. Key capabilities: role assignment, ou...Votes: 0GitHub stars: 3
- ProofreaderProofread any text in English or Vietnamese (or mixed) - check for typos, grammar errors, tone mark errors, clarity issues, and logical flow problems, while understanding the content's context, tone, and intended audience. Calibrates standards to document type so a CV bullet's deliberate parallelism is preserved while a blog post is checked for flow. Use whenever the user shares writing and asks to proofread, check, review writing, fix errors, or pastes a block of text expecting feedback. Eve...Votes: 0GitHub stars: 3
- Provider ActionsImplement Terraform Provider actions using the Plugin Framework. Use when developing imperative operations that execute at lifecycle events (before/after create, update, destroy).Votes: 0GitHub stars: 3
- Provider ResourcesImplement Terraform Provider resources and data sources using the Plugin Framework. Use when developing CRUD operations, schema design, state management, and acceptance testing for provider resources.Votes: 0GitHub stars: 3
- Provider Test PatternsTerraform provider acceptance test patterns using terraform-plugin-testing with the Plugin Framework. Covers test structure, TestCase/TestStep fields, ConfigStateChecks with custom statecheck.StateCheck implementations, plan checks, CompareValue for cross-step assertions, config helpers, import testing with ImportStateKind, sweepers, and scenario patterns (basic, update, disappears, validation, regression), and ephemeral resource testing with the echoprovider package. Use when writing, review...Votes: 0GitHub stars: 3
- 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 "test but don't fix". For the full test-fix-verify loop, use /qa instead. Proactively suggest when the user wants a bug report without any code changes. (gstack) Voice triggers (speech-to-text aliases): "bug report", "just check for bugs".Votes: 0GitHub stars: 3
- QaSystematically QA test a web application and fix bugs found. Runs QA testing, then iteratively fixes bugs in source code, committing each fix atomically and re-verifying. Use when asked to "qa", "QA", "test this site", "find bugs", "test and fix", or "fix what's broken". Proactively suggest when the user says a feature is ready for testing or asks "does this work?". Three tiers: Quick (critical/high only), Standard (+ medium), Exhaustive (+ cosmetic). Produces before/after health scores, fix ...Votes: 0GitHub stars: 3
- Quality Loop RouterSystem-wide quality enforcement for creative task pipelines. Determines Mode A (internal — full cc-loop) or Mode B (external platform — single critique pass + fix plan + approval gate). Invoked as the final step of any creative pipeline.Votes: 0GitHub stars: 3
- Railway DeployDeploy to Railway — link a project, set environment variables, trigger builds, fetch logs, generate a production URL, and validate health checks. Trigger when the user says 'deploy to railway', 'railway deploy', 'railway env vars', 'railway link', or 'railway production'. Key capabilities: detects Railway CLI and project config, authenticates and links via `railway init` or `railway link`, pushes env vars with `--dry-run` preview before applying, supports git-triggered auto-deploy and direct ...Votes: 0GitHub stars: 3
- RecallQuick single-project context check. Reads next-session.md directly (no subagent) and outputs a 6-field briefing. For multi-project resume, use /pd-resume instead. Invoke as /recall [slug] or when user says 'resume session', 'pick up where we left off'. SSOT for project paths is ~/.claude/memory/medium-term.md.Votes: 0GitHub stars: 3
- Receiving Code ReviewUse when receiving code review feedback \u2014 respond with technical rigor using a 6-step pattern: read without reacting, understand by restating, verify against actual codebase reality, evaluate technical soundness, respond with acknowledgment or reasoned pushback, and implement one item at a time with per-item testing. Purpose: Ensure every review suggestion is correct before implementing \u2014 avoid following orders from reviewers who lack full context, and avoid implementing what was re...Votes: 0GitHub stars: 3
- Refactor ModuleTransform monolithic Terraform configurations into reusable, maintainable modules following HashiCorp's module design principles and community best practices.Votes: 0GitHub stars: 3
- Remotion To HyperframesTranslate an existing Remotion (React-based) video composition into a HyperFrames HTML composition. Use ONLY when the user explicitly asks to port, convert, migrate, translate, or rewrite a Remotion composition as HyperFrames — for example "port my Remotion project to HyperFrames", "convert this Remotion code to HyperFrames", "migrate from Remotion", "translate this Remotion comp", or "rewrite this as HyperFrames HTML". Do NOT use when (a) the user is authoring a NEW HyperFrames composition, ...Votes: 0GitHub stars: 3
- Requesting Code ReviewUse before merging, after completing a major feature, or when stuck — dispatch structured code review to catch issues before they compound. Two-pass review (Critical then Informational), Fix-First protocol, adversarial review that scales by diff size.Votes: 0GitHub stars: 3
- Reservation BookingBuild a complete reservation/booking system — slot management, calendar UI, booking CRUD, confirmation emails, and Stripe/Paymob deposit payments. Triggers when user asks to build a booking site, reservation system, appointment scheduler, appointment booking, slot booking, booking dashboard, or booking page with calendar.Votes: 0GitHub stars: 3
- Respawn SelfPD context-aware self-respawn. Invoked by a PD agent when context window reaches 80% threshold. Saves current state, writes a continuation manifest with all in-flight work and next actions, then stops. The parent session (or user) spawns a fresh PD with the manifest. Enforces max 3 respawns per project per 24h. Invoke when context ≥ 80% during a PD session. Also used proactively at phase transitions when context > 70% and a major task boundary is clean.Votes: 0GitHub stars: 3
- Restaurant PosBuild a Restaurant Point of Sale (POS) system — menu CRUD, table management, floor plan, order flow, Kitchen Display System (KDS), tip tracking, and multi-outlet support. Triggers when user asks to build a restaurant POS, restaurant management, menu management, restaurant ordering, kitchen display, or table management.Votes: 0GitHub stars: 3
- Resume BodResume the BOD/Agency Council kickoff workflow in a new chat session — restores context from memory, summarizes prior state, and reassembles the full 12-person council in two waves. Trigger when the user invokes /resume-bod, /bod-resume, 'resume the board', 'continue council workflow', or 'pick up where BOD left off'. Also for: checking whether a prior team still exists before creating a new one (reuses existing if intact), assembling a focused sub-council (engineering, GTM, or marketing only...Votes: 0GitHub stars: 3
- RetroWeekly engineering retrospective. Analyzes commit history, work patterns, and code quality metrics with persistent history and trend tracking. Team-aware: breaks down per-person contributions with praise and growth areas. Use when asked to "weekly retro", "what did we ship", or "engineering retrospective". Proactively suggest at the end of a work week or sprint. (gstack)Votes: 0GitHub stars: 3
- ReviewPre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues. Use when asked to "review this PR", "code review", "pre-landing review", or "check my diff". Proactively suggest when the user is about to merge or land code changes. (gstack)Votes: 0GitHub stars: 3
- Room Manager DigestGenerate 12-hour activity digests for all department heads. Reads rolling.md feeds from each dept room, summarizes team activity from the last 12h, and sends a concise digest via SendMessage to each dept head. Run standalone every 12h or alongside the main RoomManager cycle. Idempotent — only sends when there are new entries. When to trigger: on a 12h cron schedule as a standalone job; merged into the main RoomManager cycle on its 12h digest check; manually via /room-manager-digest when a dep...Votes: 0GitHub stars: 3
- Room ManagerPoll all agency chat rooms for new messages, route escalations, handle NEXUS handoffs, fan out PD statuses to department rooms, update shared context, throttle member notifications, and generate 12-hour digests for dept heads. Run as a background subagent on cron. Trigger with /room-manager or when new room activity is suspected. When to trigger: every 10 minutes as a background loop; when a user suspects new room activity; after a handoff file appears in a room handoffs/ dir; when an ESCALAT...Votes: 0GitHub stars: 3
- Run Acceptance TestsGuide for running acceptance tests for a Terraform provider. Use this when asked to run an acceptance test or to run a test with the prefix `TestAcc`.Votes: 0GitHub stars: 3
- Sandbox SdkBuild sandboxed applications for secure code execution. Load when building AI code execution, code interpreters, CI/CD systems, interactive dev environments, or executing untrusted code. Covers Sandbox SDK lifecycle, commands, files, code interpreter, and preview URLs. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.Votes: 0GitHub stars: 3
- Sanity Best PracticesSanity development best practices for schema design, GROQ queries, TypeGen, Visual Editing, images, Portable Text, Studio structure, localization, migrations, Sanity Functions, Blueprints, and framework integrations such as Next.js, Nuxt, Astro, Remix, SvelteKit, Angular, Hydrogen, and the App SDK. Use this skill whenever working with Sanity schemas, defineType or defineField, GROQ or defineQuery, content modeling, Presentation or preview setups, Sanity-powered frontend integrations, Sanity F...Votes: 0GitHub stars: 3
- Save StateFreezes the current session — writes all session-end files, resets the turn counter, outputs a single confirmation. Fully autonomous, no user interaction. Invoke as /save-state [slug], /save-state (auto-detects from cwd), or /save-state all. When to trigger: at the end of every working session before closing; before switching to a different project; when mid-flight work needs to be preserved for the next session; after any significant milestone or decision; and whenever the user says "save st...Votes: 0GitHub stars: 3
- ScrapePull data from a web page. First call on a new intent prototypes the flow via $B primitives and returns JSON. Subsequent calls on a matching intent route to a codified browser-skill and return in ~200ms. Read-only — for mutating flows (form fills, clicks, submissions), use /automate. Use when asked to "scrape", "get data from", "pull", "extract from", or "what's on" a page. (gstack)Votes: 0GitHub stars: 3
- Security CritiqueSenior application security engineer who audits code for vulnerabilities, misconfigurations, and architectural security gaps — acting as a rigorous security reviewer. Produces a structured critique report with severity ratings (Critical/High/Medium/Low) aligned to OWASP Top 10 and MITRE ATT&CK. Covers: authentication/authorization flaws, injection vectors, data exposure, secrets management, dependency vulnerabilities, CI/CD security, and compliance implications. Use when the user says 'securi...Votes: 0GitHub stars: 3
- SecurityApply security best practices to code, architecture, and workflows. Trigger whenever the user mentions authentication, authorization, API keys, secrets, encryption, vulnerabilities, OWASP, SQL injection, XSS, CSRF, data exposure, penetration testing, security review, or asks "is this secure?". Also trigger proactively when reviewing code that handles user data, passwords, tokens, or network requests. When to trigger: during any code review pass when the diff touches auth, payments, user input...Votes: 0GitHub stars: 3
- SeedTyped project incubator — guided ideation through graduation into buildable projectsVotes: 0GitHub stars: 3
- Self HealingAutomatically diagnose and fix broken workflows, failing scripts, errors, and bugs without giving up. Trigger when a script fails, a workflow breaks, there's an error message, code isn't working as expected, or the user says "it's broken", "this isn't working", "I'm getting an error", "fix this", or pastes a stack trace. Also trigger proactively when Claude encounters an error mid-task. When to trigger: any time a bash command exits non-zero; when a build step fails (npm install, pip, cargo, ...Votes: 0GitHub stars: 3
- Seo Aeo Best PracticesSEO, GEO, and AEO best practices knowledge base — 9 on-demand reference files covering technical SEO (metadata, sitemaps, CWV, hreflang, AI crawlers), structured data (JSON-LD templates for Article/FAQ/HowTo/Organization/Product/Breadcrumb/Person/Event), E-E-A-T principles (Quality Rater signals + implementation), AEO (featured snippets, PAA, voice search, knowledge panels, extraction zones), GEO (AI citation optimization, entity authority, platform-specific for ChatGPT/Perplexity/Claude/Gemi...Votes: 0GitHub stars: 3
- Setup Browser CookiesImport cookies from your real Chromium browser into the headless browse session. Opens an interactive picker UI where you select which cookie domains to import. Use before QA testing authenticated pages. Use when asked to "import cookies", "login to the site", or "authenticate the browser". (gstack)Votes: 0GitHub stars: 3
- Setup DeployConfigure deployment settings for /land-and-deploy. Detects your deploy platform (Fly.io, Render, Vercel, Netlify, Heroku, GitHub Actions, custom), production URL, health check endpoints, and deploy status commands. Writes the configuration to CLAUDE.md so all future deploys are automatic. Use when: "setup deploy", "configure deployment", "set up land-and-deploy", "how do I deploy with gstack", "add deploy config".Votes: 0GitHub stars: 3
- Setup GbrainSet up gbrain for this coding agent: install the CLI, initialize a local PGLite or Supabase brain, register MCP, capture per-remote trust policy. One command from zero to "gbrain is running, and this agent can call it." Use when: "setup gbrain", "connect gbrain", "start gbrain", "install gbrain", "configure gbrain for this machine". (gstack)Votes: 0GitHub stars: 3
- Shadcn UiYou are a frontend engineer specialized in building applications with shadcn/ui—a collection of beautifully designed, accessible, and customizable components built with Radix UI or Base UI and Tailwind CSS. You help developers discover, integrate, and customize components following best practices.Votes: 0GitHub stars: 3
- ShipShip workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, create PR. Use when asked to "ship", "deploy", "push to main", "create a PR", "merge and push", or "get it deployed". Proactively invoke this skill (do NOT push/PR directly) when the user says code is ready, asks about deploying, wants to push code up, or asks to create a PR. (gstack)Votes: 0GitHub stars: 3
- Skill CreatorCreate new skills using the Skill Seekers CLI (github.com/yusufkaraaslan/ Skill_Seekers), generating SKILL.md files from GitHub repos, documentation URLs, or a blank slate. Invoke with /skill-creator. When to trigger: when the user wants to create a new skill from scratch or from a GitHub repository; when a useful workflow should be captured as a reusable SKILL.md for future projects; when the user pastes a docs URL and asks to turn it into a skill; and when a one-off workflow has been run su...Votes: 0GitHub stars: 3
- Skill ImportImport skills from the skills library at ~/.claude/skills/ into a project's CLAUDE.md files, automatically matching skills to the correct nested folders (backend/, frontend/, database/, infra/, root). Invoke with /skill-import. When to trigger: when the user says "import skills" or "apply skills to this project"; when onboarding a new project and all relevant library skills should be wired in; when adding a new domain folder and existing skills should be applied there; and when a project adop...Votes: 0GitHub stars: 3
- Skill QualityAutomatically rate any skill's description quality and rewrite it if needed — the quality gate for the skill creation pipeline. Invoked by /skill-creator after skill installation, or directly with /skill-quality [skill-name]. When to trigger: automatically after every new skill is installed via /skill-creator; when manually auditing a skill's description quality; when a skill's description fails to attract correct usage; or when enhancing an existing skill and wanting to verify the descriptio...Votes: 0GitHub stars: 3
- Skill TrackerCheck and apply upstream updates to installed skills. Reads pending-updates.json generated by the cron checker, spawns haiku agents to evaluate each diff for quality and safety, then spawns sonnet agents to apply smart merges — preserving local customizations while pulling in genuine upstream improvements. Triggers: /skill-update, "update skills", "check skill versions", "are my skills up to date"Votes: 0GitHub stars: 3
- SkillifyCodify the most recent successful /scrape flow into a permanent browser-skill on disk. Future /scrape calls with the same intent run the codified script in ~200ms instead of re-driving the page. Walks back through the conversation, synthesizes script.ts + script.test.ts + fixture, runs the test in a temp dir, and asks before committing. Use when asked to "skillify", "codify", "save this scrape", or "make this permanent". (gstack)Votes: 0GitHub stars: 3
- Stop SlopDetect and remove AI-originated patterns from prose — filler phrases, throat-clearing openers, business jargon, passive voice, binary contrasts, dramatic fragmentation, rhetorical scaffolding, and false agency. Apply this before any text reaches a user or gets committed to a document. Trigger when: the user asks to "make this sound more natural", "fix AI-sounding prose", "rewrite this without filler", "clean up this writing", or "remove the AI tells"; any time you generate prose output (email...Votes: 0GitHub stars: 3
- Strategic DeckBuild a 25-30 slide strategic pitch / audit deck — gradient hero and divider slides, cream content slides with a vertical accent bar, ink headlines, a highlight accent for "the bet", and a five-act narrative arc (audit - marketing - market - bet - go-to-market). Use whenever the user asks to "build a strategic deck", "audit company X and recommend a bet", "make a strategic pitch deck", "rebuild this deck for [different company]", or any pitch/audit/strategy slide deliverable. Also triggers on...Votes: 0GitHub stars: 3
- Stripe Best Practices**Latest Stripe API version: 2026-02-25.clover.** Always use the latest API version and SDK unless the user specifies otherwise.Votes: 0GitHub stars: 3
- Style Guide ViKiểm tra và áp dụng nhất quán style guide tiếng Việt cho xưng hô, thuật ngữ, viết hoa, số, ngày giờ, đơn vị, heading, bullet và code. Dùng khi chuẩn hóa một hoặc nhiều tài liệu; không dùng để thay thế grammar review, áp quy tắc mặc định lên style guide riêng, hay đổi tên sản phẩm và nội dung được trích nguyên văn.Votes: 0GitHub stars: 3
- Subtitle BurnerBurned-in subtitle (open caption) workflow for short-form video. Produces karaoke-style word-highlight captions for TikTok/Reels/Shorts. Uses Whisper for transcription + ffmpeg for styled caption burn. No Docker required.Votes: 0GitHub stars: 3