Loading...
Loading...
Found 6,530 Skills
Three modes. Session mode (default): extracts generalizable lessons from RESEARCH.md and git history at session end; lessons that imply a new or significantly changed skill are handed off to skill-creator. Personalize mode: searches the skills registry via `npx skills find`, reads the target skill(s), checks compatibility and scope overlap against installed skills, interviews the user to understand what they want and what to skip, then creates or improves skills using skill-creator. Registry mode: curates `skillpacks/skill_dictionary.yaml` and `skillpacks/presets/*.yaml` by assessing external packs, judging necessity/compatibility, and recommending subsets. Create mode: designs a brand- new skill from scratch using skill-creator. Never edits SKILL.md directly — all changes go through skill-creator's draft→test→iterate loop, human merges. Trigger phrases: "end session", "extract lessons", "personalize my skills", "integrate this skill", "update skillpack", "find a skill for", "create a skill", "improve skill", "refresh the skillpack registry", "assess this skill pack", "update skill_dictionary.yaml", "update index.yaml".
Run an autonomous Humanize-governed SGLang SOTA performance loop for one LLM model: first perform the fixed fair SGLang/vLLM/TensorRT-LLM deployment search and benchmark, then start one RLCR loop that repeatedly decides the gap, profiles the current bottleneck, runs layer/kernel pipeline analysis, patches SGLang code, optionally uses ncu-report-skill for kernel evidence, and revalidates until SGLang matches or beats the best observed framework under the same workload and SLA.
Track, categorize, and prioritize technical debt across the codebase. Scans for debt indicators, maintains a debt register, and recommends repayment scheduling.
Grassroots-first campaign design for anyone being outspent — startups vs. incumbents, NGOs vs. corporate comms, movements vs. state-backed machines, solo brands vs. big-budget competitors. Ideates awareness, launch, fundraising, mobilization, community-build, counter-narrative, referral, founder-story, and coalition campaigns. Triggers on "campaign plan", "marketing strategy", "ad budget", "should I advertise", "paid vs organic", "launch plan", "grassroots", "low budget marketing", "NGO campaign", "outspent", "competitor has bigger budget", "how do I compete without money". Also trigger on any spend asymmetry, collapsing organic reach, rising CPAs, or a trust/credibility problem — even without the word "campaign". Nudge activation when the user debates buying ads, boosting posts, or hiring influencers; they are likely about to burn money on a channel that will not persuade.
Auditing Google Cloud Platform IAM permissions to identify overly permissive bindings, primitive role usage, service account key proliferation, and cross-project access risks using gcloud CLI, Policy Analyzer, and IAM Recommender.
The meta skill. Turn any raw feature into a properly-skilled, tested, resolvable unit of agent capability. Cross-modal eval is the recommended Phase 3 quality gate: 3 frontier models from different providers critique the output, you iterate to quality, THEN write tests that lock in the proven-good behavior.
Discover, explore, and learn about MCP (Model Context Protocol) servers from a curated list of 6000+ implementations across 30+ categories
Complete FFmpeg + OpenCV + Python integration guide for video processing pipelines. PROACTIVELY activate for: (1) FFmpeg to OpenCV frame handoff, (2) cv2.VideoCapture vs ffmpeg subprocess, (3) BGR/RGB color format conversion gotchas, (4) Frame dimension order img[y,x] vs img[x,y], (5) ffmpegcv GPU-accelerated video I/O, (6) VidGear multi-threaded streaming, (7) Decord batch video loading for ML, (8) PyAV frame-level processing, (9) Audio stream preservation with video filters, (10) Memory-efficient frame generators, (11) OpenCV + FFmpeg + Modal parallel processing, (12) Pipe frames between FFmpeg and OpenCV. Provides: Color format conversion patterns, coordinate system gotchas, library selection guide, memory management, subprocess pipe patterns, GPU-accelerated alternatives to cv2.VideoCapture. Ensures: Correct integration between FFmpeg and OpenCV without color/coordinate bugs. See also: ffmpeg-python-integration-reference for type-safe parameter mappings.
The orchestrator and entry point for the engineering skills suite. Use this skill whenever the task involves doing engineering work to a high bar — reviewing code or a design, designing a new system or component, debugging a hard problem or running an incident, implementing a substantive change, writing documentation, or sanity-checking an approach. Use it when the user phrases things casually ("rip into this", "be brutal", "is this approach right", "what am I missing", "what would you change", "look at this") or formally ("review this PR", "audit this design"). Use it proactively for any non-trivial engineering work, before declaring something done. The skill triages the work, dispatches to the right specialty skill(s), enforces verification, and produces an evidence-backed result. The goal is to ensure no AI shortcut, sycophantic agreement, or stylistic distraction gets in the way of work that holds up to senior-engineer scrutiny.
Run an ordered sequence of pm-skills against one input via the pm-workflow-orchestrator sub-agent, pausing for go/no-go and stopping on a failed or empty step. Dispatches natively on Claude Code with the pm-skills plugin (invokes @agent-pm-skills:pm-workflow-orchestrator, which delegates each step through the Skill tool); on non-Claude clients (Codex CLI, Cursor, Windsurf, Copilot, Gemini CLI) reads agents/pm-workflow-orchestrator.md and walks the loop inline after a tool-capability pre-flight. Explicit invocation only; never fires proactively. EXPERIMENTAL on all non-Claude clients and on the native path until smoke-tested; run --dry-run first.
QA-test a website or web app and return a 1-5 quality score (5 = flawless, 1 = broken) with evidence. Use when the user wants to test, QA, evaluate, score, or "check how good" a site, page, flow, or app — including a local dev server (e.g. "qa test localhost:5173", "does the checkout work?", "rate this landing page"). Drives a real Browser Use cloud browser, tunneling localhost automatically.
Translates an image (or a set of image references — screenshots, mockups, Figma URLs, live websites) into two mirrored design-system artifacts: `docs/design.md` (YAML tokens + prose, following Google's open [design.md](https://github.com/google-labs-code/design.md) format, for the coding agent) and `docs/design.html` (a self-contained, token-driven style guide rendering every token and component live, for the human to read). Reads the imagery, asks targeted clarifying questions, derives the design tokens (colors, typography, spacing, rounded, components), and writes both files. Fully standalone — requires no other document or skill. Use when the founder says "create a design system", "design from image", "translate image to design", "create design.md", "image to design system", "extract design tokens", or shares an image with no other clear intent.