All nine kinds in one list: what an agent loads, what it runs, what it
reads and what bundles the rest. 412,887 of
them, each with its token cost per session, a security scan with the
line that triggered it, and whether it is the original or one of the
copies.
Write or change Home Assistant YAML — automations, scripts, scenes, templates, integrations, packages, helpers. Covers checking current integration documentation before writing, the mandatory HA YAML style guide, reading and querying YAML with yq, safe writes through writeconfigsafe, validation, backups, and whether a…
Use when you need to see and operate an Android screen through an OCR/vision model plus ADB. Optimized commander workflow: one model plan, batch ADB execution, minimal round-trips, verify at milestones.
Complete guide for building accessible, high-UX forms in modern stacks (React/Next.js, Tailwind, Zod). Includes specific patterns for clickable areas, range sliders, output-inspired design, and WCAG compliance.
Generate and interpret security-research diffs between Windows versions or patch levels using this repo's WinDiff CLI and databases. Use when comparing Windows builds or binaries such as ntoskrnl.exe, ntdll.dll, win32k.sys, ci.dll, or cng.sys to find changed syscalls, symbols, types, mitigation flags, callbacks…
Adversarially pressure-test a draft or pending U.S. utility patent against technically credible, commercially plausible design-arounds that preserve its value proposition while avoiding the current proposed claims. Use fresh competitor subagents, then have the outer agent decide whether each workaround remains inside…
Standalone Phase 6 of SAP UI testing. Rediscovers the configured test folder, program, approved cases, and primary system from disk; validates upstream inputs; then writes one tests/ /test-scripts/TC-XXX.spec.ts per case using @sap-testing/runtime. Use when the user asks to write, generate, or convert Playwright…
Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments. Triggers Greptile review, fixes all actionable comments, pushes/re-shelves, re-triggers review, and repeats. Use when the user wants to fully optimize a…
Full-funnel App Store Optimization from Claude Code — keyword research, 50-locale metadata, localized screenshots, worldwide pricing, in-app localization, and a verified submission checklist. Bring your own App Store Connect key.
★not rated 394▲
+31 1mo agoA
tokens not measured
originalMIT
Generate clinical trial protocols for medical devices or drugs. This skill should be used when users say "Create a clinical trial protocol", "Generate protocol for [device/drug]", "Help me design a clinical study", "Research similar trials for [intervention]", or when developing FDA submission documentation for…
A set of Claude Code slash commands for the cloudwego/abcoder project. The commands create structured coding-task documents, design implementation plans, and check those plans against the codebase.
Anti-detection browser automation for AI agents. Use when the user needs stealth web browsing, undetectable scraping, fingerprint spoofing, proxy rotation, or privacy-focused browser automation. Triggers include "stealth scrape", "anti-detection", "bypass fingerprinting", "camofox", "camoufox", "undetectable browser"…
Manages Google NotebookLM notebooks via the nlm CLI. Use for creating notebooks, listing and syncing sources, uploading files/URLs/text, chatting with sources, generating reports/audio/video/slides, running research, managing labels, editing notebook metadata (title/emoji/description/cover), and managing notebook…
Skills that keep development open to the person running it, who does not read code: plain-language session reports, followable operator instructions, decisions framed as questions with a recommendation, an attack on a decision while it can still be changed, what-to-do-next orchestration, verification of work done in…
★not rated 398▲
+84
changed todayA
tokens not measured
originalMIT
Import existing project documentation into a block-level PlanWeave Plan Package and validate it through the PlanWeave CLI. Use when importing PRDs, roadmaps, issue sets, architecture notes, or another strong source plan.
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: