Progressive-disclosure instructions an agent loads on demand. Cheap until invoked, which is why the per-session figure on each card is usually two digits.
Review an ADR the user has written in docs/adr/. Use when the user says an ADR is ready for review or asks for feedback on a decision record. Never use this to write or rewrite an ADR for them.
An AI coach for entrepreneurs working through product ideas, business questions, and personal growth. It uses structured conversations about customers, problems, experiments, products, and possible futures.
A search tool for carbon emission factors, which are values used to estimate emissions from activities or materials. It queries the Carbonstop CCDB database and returns structured results.
Create a PR on an OSAC component repo (including the osac mono-repo, which may need per-component validation for multiple touched components in one pass) using the fork-based workflow. Runs repo-specific validation (build, test, lint), pushes to the developer's push remote, and opens a PR against the upstream repo…
Create or check concise reviewer-visible PR context and practical proof when an authorized workflow publishes an update or prepares it for merge. Lead with what broke and how it is fixed, use actual product screenshots for static UI changes and recordings for motion or manual interaction, keep technical diagrams as…
An interactive setup skill that turns an empty Claude Code folder into an OpenClaw-style personal assistant. It asks about the assistant's identity, tone, communication channels, permissions, and memory, then creates the related instruction and memory files.
Find B2B prospects, research and score leads, generate personalized outreach drafts, create macOS Mail.app drafts, and open lead sources for manual verification — via the local Codex-native Lead Hunter CLI. Every outreach action stops at a human-reviewed draft; nothing is ever sent or posted automatically.
Use only when the user explicitly asks for kimippt, /kimippt, Kimi PPT, Kimi slides, or generation through kimi.com/slides. Operates the user's logged-in main Chrome only through a main-Chrome control tool exposed in the current session, uploads the source document, generates and downloads the PPTX, then delivers it.…
Query local Claude Code, Codex CLI, OpenCode, Kimi Code CLI, Cursor Agent CLI, and Pi session history through the corral CLI — list recent sessions, search by topic, read a session's conversation, export a shareable transcript with tool calls and thinking, or build a handoff context package to continue interrupted…
Detect, triage, and fix performance problems across Windows native C/C++ (clang-cl/MSVC; VTune, AMD uProf, ETW/WPA), WSL Linux, native Linux (perf/flamegraphs/GCC/Clang), and CUDA/NVIDIA environments (nvidia-smi, nvcc, Nsight Systems, Nsight Compute). Invoke when the user asks to optimize or debug performance, review…
SvelteKit frontend patterns for Tauri desktop apps. Use when writing Svelte components, pages, layouts, load functions, or routing in a Tauri project. Triggers on .svelte files, +page, +layout, +server, load function, SvelteKit, adapter, SSR, prerender. Complements the tauri-v2 skill (Rust backend); this skill owns…
Audits a mobile app codebase — Expo/React Native (managed or bare) or native iOS/Android, standalone or inside a Turborepo/monorepo — and reports whether it would pass Apple App Review and Google Play review. Use this skill whenever the user: asks if their app will pass, fail, or get rejected by Apple or Google…
GTM brain for solo founders launching products. Pulse reads the user's brief (identity, voice, hard rules) AND the configured workspace (README, /doc/, recent commits, source) to know the product as well as the user does. The page drives a three-step pipeline — Gather local (script), Gather web (agent + Fetch tools)…
Always active — coordinates with other Claude Code agents via intercom MCP. Automatically checks for messages, announces presence, and communicates to avoid conflicts. Triggers on ANY task start and periodically during work.
Build a 3D tower-defense game (creeps walk a lane, you place towers on a grid to stop them) on the Ship Shit engine, matching the FPS's neon-arena look. Use when adding a TD mode/game with an RTS-style angled or orthographic camera (NOT pointer-lock), raycast click-to-place on a grid, gold/build economy, waypoint…
Write back findings, updates, observations, or new content to a project's Confluence surface. Use this skill whenever someone wants to: update a project doc, write back findings from a session, add questions or blockers to a project, record a decision, capture meeting notes, append research, create a new doc in the…
Reference for writing and editing skills well — the vocabulary and principles that make a skill predictable. Use whenever authoring, editing, or reviewing a SKILL.md, or deciding a skill's trigger description, invocation mode, or file structure.
★not rated 3 1mo agoA51 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: