Loading…
Showing 8611–8640 of 10191 skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| wtf.healthxiduzo/wtfThis skill should be used when a developer or lead wants a project status overview — what is blocked, stale, unverified, or waiting on a next step — for example "project health check", "what's blocking the release", "standup summary", or "what's left in this epic". Scans all open WTF issues — Traces plus legacy Tasks — and produces a triage-ready health report with actionable next steps. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| wtf.hotfixxiduzo/wtfThis skill should be used when something is broken in production and needs an immediate fix that bypasses the normal Epic→Feature→Trace planning flow — for example "production is down", "hotfix needed", "critical bug in prod", "emergency fix for | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| wtf.implement-tracexiduzo/wtfThis skill should be used when a developer is ready to implement, resume, or continue a GitHub Trace issue — for example "implement trace | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| wtf.loopxiduzo/wtfThis skill should be used when a developer wants to autonomously execute all Traces under a fully-specified Epic or Feature — for example "go", "start building", "implement everything", "run the loop", "execute the feature", "build it all", "kick it off". Requires that the Epic/Feature/Trace tree is fully written before starting. Chains implement → verify → PR → re-aim for every Trace — spine-first within each Feature, parallel across Features — with targeted human-in-the-loop gates for contradictions, ambiguities, and every change to a Trace Plan's scenario set. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| wtf.pr-reviewxiduzo/wtfThis skill should be used when a developer or tech lead wants to review a pull request for correctness, spec adherence, and code quality — for example "review PR | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| wtf.retroxiduzo/wtfThis skill should be used when a team wants to close out a completed Epic or sprint, capture what was planned vs. what shipped, learn from deviations, and formally mark the Epic done — for example "run a retro on this epic", "close out the epic", "what deviated from the plan", "retrospective for epic | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| wtf.setupxiduzo/wtfThis skill should be used when a user wants to set up WTF in a repository or check that the environment is ready for it — for example "set up wtf", "is wtf ready", "install wtf templates", or "a new dev joined, set them up". Verifies the GitHub CLI and its auth, installs the required gh extensions and the issue and PR templates, configures issue classification, planning, feature scope, and delivery mode, and registers the hooks. Run once per repo when onboarding, or when a contributor joins the project. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| wtf.spikexiduzo/wtfThis skill should be used when a developer or tech lead needs to investigate a technical unknown before committing to an approach — for example "run a spike on X", "I need to research this before writing the epic", "we don't know how to approach this yet", "investigate if we can use X for Y", "time-box this exploration", "what's the right architecture for this?", or "should we use A or B?". Produces a findings document and a concrete recommendation that feeds directly into write-epic or write-trace. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| wtf.write-epicxiduzo/wtfThis skill should be used when a user wants to create, draft, or plan a GitHub Epic issue — for example "write an epic", "I want to define a new initiative", "scope out this strategic project", "turn this idea into an epic", "plan work that spans multiple features", or "start from a bounded context". Also use when the user asks to define domain outcomes, capture a large initiative before breaking it into features, or describe work in terms of business goals rather than implementation details. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| wtf.write-featurexiduzo/wtfThis skill should be used when a user wants to create a GitHub Feature issue, break down an Epic into user-facing capabilities, write user stories in domain language, or capture what a domain actor can do — for example "create a feature", "write a feature for this epic", "add a feature to an epic", "break this epic into features", "write user stories for this feature", or "describe what this actor can do". Use this skill to write a single Feature. Use `wtf.epic-to-features` to generate the full set of Features for an Epic at once. Supports two planning modes — `guided` (step-by-step questions) and `flow` (derive, one consolidated review) — passed as an argument or read from `.wtf/config.json`. Not applicable to Traces, Epics, or bug reports. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| wtf.write-tracexiduzo/wtfThis skill should be used when a user wants to create a single Trace issue under a Feature — for example "create a trace", "write a trace for this feature", "add a trace to feature | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| pwa-shellgagandeepgill/puzzle-gameHow this arcade ships as an installable PWA: the service worker's cache strategy and version bump, the deliberate no-skipWaiting decision and the update prompt that completes it, what is safe to precache and what is not, and the stale-build trap that makes a fix look like it did not work. Use when touching public/sw.js, the manifest, offline behaviour, caching, or when a change you just built is not showing up in the browser. | Stars: 0 | Updated | Claude CodeCodex | Verified | Install |
| react-performancegagandeepgill/puzzle-gameReact and Next.js performance optimization patterns adapted from Vercel Engineering's React Best Practices (https://github.com/vercel-labs/agent-skills). Organizes 70+ rules across 8 priority categories — waterfalls, bundle size, server-side, client fetching, re-render, rendering, JS micro-perf, advanced. Use when writing, reviewing, or refactoring React/Next.js code for performance. | Stars: 0 | Updated | Claude CodeCodex | Verified | Install |
| bnbchain-erc8004-agentkbarbel640-del/skillsRegister and update yourself as an agent (ERC8004) on BNB Chain (BSC Testnet). Use this skill to give the agent an on-chain identity without needing BNB for gas (sponsored via MegaFuel Paymaster). Supports registering a new agent, getting agent info, and updating agent metadata/endpoints. | Stars: 1 | Updated | Claude CodeCodex | Verified | Install |
| skill-porterkbarbel640-del/skillsConverts Claude Code skills to Gemini CLI extensions and vice versa. Use when the user wants to make a skill cross-platform compatible, port a skill between platforms, or create a universal extension that works on both Claude Code and Gemini CLI. | Stars: 1 | Updated | Claude CodeCodex | Verified | Install |
| clawarenakbarbel640-del/skillsAI Agent Prediction Arena - Predict Kalshi market outcomes, compete for accuracy | Stars: 1 | Updated | Claude CodeCodex | Verified | Install |
| odwSuraj1235/open-dynamic-workflowsDynamic multi-agent workflows — plan first, then orchestrate parallel agents with adversarial verification via the local odw daemon. Use when the user asks for a "workflow", says "ultracode", or hands you a task spanning many files/items that benefits from parallel agents. | Stars: 50 | Updated | Claude CodeCodex | Verified | Install |
| odwSuraj1235/open-dynamic-workflowsDynamic multi-agent workflows — plan first, then orchestrate parallel agents with adversarial verification via the local odw daemon. Use when the user asks for a "workflow", says "ultracode", or hands you a task spanning many files/items that benefits from parallel agents. | Stars: 50 | Updated | Claude CodeCodex | Verified | Install |
| odwSuraj1235/open-dynamic-workflowsDynamic multi-agent workflows — plan first, then orchestrate parallel agents with adversarial verification via the local odw daemon. Use when the user asks for a "workflow", says "ultracode", or hands you a task spanning many files/items that benefits from parallel agents. | Stars: 50 | Updated | Claude CodeCodex | Verified | Install |
| probe-astral-descriptionagent-ecosystem/agent-skill-implementationBenchmark skill whose description stays under the spec's 1024-character limit when counted in Unicode code points but runs past it when counted in UTF-16 code units or UTF-8 bytes. Use when asked to probe description length units. The head marker MAGPIE-OBSIDIAN-1240 sits near the start and a tail marker sits at the very end; between them is deliberate emoji padding. 🐦🪨🧪📏🔤🧭🌐📐📦🧱🔎🧮📚🪶🧵🪵🔬🧩🗺🪙🐦🪨🧪📏🔤🧭🌐📐📦🧱🔎🧮📚🪶🧵🪵🔬🧩🗺🪙🐦🪨🧪📏🔤🧭🌐📐📦🧱 🔎🧮📚🪶🧵🪵🔬🧩🗺🪙🐦🪨🧪📏🔤🧭🌐📐📦🧱🔎🧮📚🪶🧵🪵🔬🧩🗺🪙🐦🪨🧪📏🔤🧭🌐📐📦🧱🔎🧮📚🪶🧵🪵🔬🧩🗺🪙 🐦🪨🧪📏🔤🧭🌐📐📦🧱🔎🧮📚🪶🧵🪵🔬🧩🗺🪙🐦🪨🧪📏🔤🧭🌐📐📦🧱🔎🧮📚🪶🧵🪵🔬🧩🗺🪙🐦🪨🧪📏🔤🧭🌐📐📦🧱 🔎🧮📚🪶🧵🪵🔬🧩🗺🪙🐦🪨🧪📏🔤🧭🌐📐📦🧱🔎🧮📚🪶🧵🪵🔬🧩🗺🪙🐦🪨🧪📏🔤🧭🌐📐📦🧱🔎🧮📚🪶🧵🪵🔬🧩🗺🪙 🐦🪨🧪📏🔤🧭🌐📐📦🧱🔎🧮📚🪶🧵🪵🔬🧩🗺🪙🐦🪨🧪📏🔤🧭🌐📐📦🧱🔎🧮📚🪶🧵🪵🔬🧩🗺🪙🐦🪨🧪📏🔤🧭🌐📐📦🧱 🔎🧮📚🪶🧵🪵🔬🧩🗺🪙🐦🪨🧪📏🔤🧭🌐📐📦🧱🔎🧮📚🪶🧵🪵🔬🧩🗺🪙🐦🪨🧪📏🔤🧭🌐📐📦🧱🔎🧮📚🪶🧵🪵🔬🧩🗺🪙 🐦🪨🧪📏🔤🧭🌐📐📦🧱🔎🧮📚🪶🧵🪵🔬🧩🗺🪙🐦🪨🧪📏🔤🧭🌐📐📦🧱🔎🧮📚🪶🧵🪵🔬🧩🗺🪙🐦🪨🧪📏🔤🧭🌐📐📦🧱 🔎🧮📚🪶🧵🪵🔬🧩🗺🪙🐦🪨🧪📏🔤🧭🌐📐📦🧱🔎🧮📚🪶🧵🪵🔬🧩🗺🪙🐦🪨🧪📏🔤🧭🌐📐📦🧱🔎🧮📚🪶🧵🪵🔬🧩🗺🪙 🐦🪨🧪📏🔤🧭🌐📐📦🧱🔎🧮📚🪶🧵🪵🔬🧩🗺🪙🐦🪨🧪📏🔤🧭🌐📐📦🧱🔎🧮📚🪶🧵🪵🔬🧩🗺🪙🐦🪨🧪📏🔤🧭🌐📐📦🧱 The tail marker is LINNET-MALACHITE-2420 | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| probe-long-compatibilityagent-ecosystem/agent-skill-implementationBenchmark skill whose compatibility field runs past the spec's 500-character limit. Use when asked to probe oversize compatibility handling. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| checksum-skillhellogxp/skill-runtime-intelligenceDeterministically validates the bundled fixture payload and returns its token. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| checksum-skillhellogxp/skill-runtime-intelligenceDeterministically validates the bundled fixture payload and returns its token. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| home-assistantjackson2w/claude-code-skillsThis skill should be used when configuring, troubleshooting, or extending a Home Assistant OS (HAOS) instance — installing add-ons/apps, editing configuration.yaml, setting up Tailscale/remote access, or troubleshooting onboarding, the Supervisor, or backups, or building automations/scripts/helpers/template switches/webhooks through HA's REST and websocket APIs. Trigger phrases include "Home Assistant add-on", "Home Assistant apps", "configuration.yaml", "HAOS", "Home Assistant Tailscale", "Supervisor", "HACS", "home assistant api", "create automation via api", "/api/config/automation/config", "input_boolean/create", "timer/create", "home assistant websocket", "template switch config flow", "webhook local_only", "ios shortcut webhook", "template value should be a string", "pause for 1 hour then revert". | Stars: 1 | Updated | Claude CodeCodex | Unverified | Install |
| ollama-macos-headlessjackson2w/claude-code-skillsThis skill should be used when running Ollama headless on a Mac as an always-on service, when Ollama returns HTTP 403 to requests arriving through a reverse proxy or Tailscale Serve, when deciding whether to enable macOS auto-login for a headless box, when choosing a model size for an 8GB Apple Silicon machine, or when a Caddy reverse proxy returns HTTP 200 with an empty body. Trigger phrases include "ollama headless mac", "ollama 403 proxy", "ollama Host header", "OLLAMA_ORIGINS not working", "brew services doesn't start until login", "LaunchDaemon vs LaunchAgent", "mac mini always on service", "ollama tailscale serve", "8GB unified memory model size", "caddy 200 empty body", "caddy site matcher Host". | Stars: 1 | Updated | Claude CodeCodex | Unverified | Install |
| pause-handoff-emailjackson2w/claude-code-skillsThis skill should be used whenever a working session pauses rather than completes — when Will says "good pause point", "let's pause here", "I'll pick this up later", "that's enough for today", "wrapping up", "done for now", or hands work back while something is still mid-flight. It defines the pause-handoff email sent to Will covering unverified claims, owed work, phrases to resume each thread, and steps only he can run. Also applies when he asks to "email me the flags", "send me what's outstanding", "what do I need to do", or "how do I pick this up later". | Stars: 1 | Updated | Claude CodeCodex | Unverified | Install |
| skill-boilerplatecolomet/skill-boilerplateOne-time setup wizard that generates a personalized skill-creator. Use when the user has just installed this boilerplate and wants to configure it, says 'set up the skill creator', 'configure the boilerplate', 'let's set this up', 'I want to start making skills', or asks how to get started with this repo. Runs once, asks eleven questions about naming conventions, versioning, layout and scope, plus one for what to call the result, then writes a ready-to-use skill-creating skill. Do NOT use this to create an individual skill -- that is what the generated tool does afterwards. | Stars: 0 | Updated | Claude CodeCodex | Verified | Install |
| showoffAll-The-Vibes/ShowOffTurn the current project, a GitHub PR URL, a URL-backed app, or a supplied evidence path into a short polished project showcase video (25 s default, 10-90 s accepted) with a poster image, a written plan, a composition brief, and ready-to-paste share copy. Use when the user says "showoff this project", "make a demo video", "create a showcase reel", "showcase what I built", "turn this PR into a video", "make a shareable clip of my work", "make a highlight reel", "create a product demo", or "record what this app does". Inspects the source, plans a grounded narrative, composes a HyperFrames video, bakes the strongest settled frame as the poster, and writes share copy. ShowOff never automatically publishes or uploads the finished artifacts. It may contact supplied PR/app hosts, Claude Code, HyperFrames update sources, and explicitly approved Media OS providers. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| statusline-setupOXI-717/ai-native-toolkitUse when user asks to set up, configure, or troubleshoot the Claude Code statusline. Triggers: "setup statusline", "fix statusline", "statusline not working", "show usage limits", "context percentage". NOT for general status questions. | Stars: 9 | Updated | Claude CodeCodex | Unverified | Install |
| vibe-plmluckiday/vibe-hardwareThe integration / product-lifecycle layer ABOVE vibe-firmware · vibe-pcb · vibe-cad: turn a small embedded product into a single PRODUCT MANIFEST plus the INTERFACE CONTRACTS the three domains must agree on, keep them in sync across a revision, and gate a release/fab on all three being green at once. Use when STARTING a new product (scaffold the firmware/pcb/cad dirs + manifest), CHANGING something that crosses a domain boundary (a pin move, a board-outline change, a shared fit number), CUTTING a revision, or wiring up a fab/release. Key facts this skill encodes: the product is one `product.yaml` — identity + per-domain status + the interface contracts — and it is the single source of truth (the architecture's "fit numbers + net map" box made concrete); there are exactly three contracts — `pinmap.yaml` (pcb -> firmware), `board.step` (pcb -> cad, a GENERATED artifact), `constraints.yaml` (cad <-> pcb, the shared fit numbers) — direction is producer -> consumer; `revision` (vYYYY-MM-DD) bumps on ANY cross-domain change so all three move together; the release gate is cross-domain (pcb ERC/DRC 0/0/0 + belly, cad 0 mm^3 fit, firmware hardware-tested) and must be green at ONE revision before fab. Critically, vibe-plm is self-contained: its scripts read the contract FILES and never import/call another skill's code — cross-skill coupling is DATA (the manifest + the contracts) and PROSE hand-offs, never a runtime dependency. Validate with `scripts/plm_check.py` (manifest sanity + interface-drift gate). Worked reference: `examples/pager-buddy/product.yaml`. Siblings: vibe-firmware/pcb/cad. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |