Agent skills you can check before you install
Public SKILL.md skills from GitHub repositories with 50+ stars and from the vendors themselves, scanned and scored. Install any of them with one command in Claude Code, Cursor, Codex, GitHub Copilot or Gemini CLI.
48,622 skills from 2,355 repositories · updated 7 hours ago
48,622 skills
- work-with-prcode-yeongyu/oh-my-openagentFull PR lifecycle in a fresh task-owned git worktree: implement via the ulw-loop skill with mandatory evidence-bound manual QA → reviewer-readable English PR → verification loop (CI + Cubic, where Cubic is skipped only when its quota is exhausted) → merge by default → worktree cleanup. Decomposes one task into the smallest atomic, independently-mergeable PRs and builds the independent ones concurrently via one worktree per PR driven by parallel subagents or a team. Unbounded loop: any failing gate sends you back to fix-and-re-QA inside that PR's worktree. Use whenever implementation work needs to land as a PR. Triggers: 'create a PR', 'implement and PR', 'work on this and make a PR', 'implement issue', 'land this as a PR', 'split into atomic PRs', 'parallel PRs', 'work-with-pr', 'PR workflow', 'implement end to end', even when user just says 'implement X' if the context implies PR delivery.TestingNo warnings★ 70.6K↓ —Also in 1 other repo
- docs-reviewforyourhealth111-pixel/Vibe-SkillsReview documentation changes for compliance with the Metabase writing style guide. Use when reviewing pull requests, files, or diffs containing documentation markdown files.EngineeringNo warnings★ 3.8K↓ —
- exa-local-dev-loopjeremylongshore/tons-of-skills-marketplaceBuild and test an Exa adapter locally using schema fixtures, recorded content-free envelopes, and an explicit opt-in live lane. Use when operating or reviewing this Exa boundary. Trigger with "Exa local dev loop", "review Exa local dev loop", or "fix Exa local dev loop".TestingNo warnings★ 2.9K↓ —
- pr-gardeningpaperclipai/paperclipDiscover the pull requests this Paperclip instance opened (never community contributions), report what each is for and how confident we are that it is merge-ready, and automatically drive the non-ready ones back to green with /prepare-paperclip-pr — without ever merging.OtherNo warnings★ 109.7K↓ —
- theboardroomdavepoon/buildwithclaudeConvene an AI executive board of directors (CEO, CFO, COO, CLO, CISO sub-agent personas) to vet a business idea, product concept, new service offering, M&A target, or operational initiative — and deliver an integrated board memo with a Go/No-Go recommendation. Use this skill whenever the user wants an idea vetted, stress-tested, or reviewed from multiple executive perspectives; asks to "present this to the board," "run this by the boardroom," "vet this idea," "poke holes in this plan," or "prep me for a board meeting"; or shares a business plan, pitch, proposal, or initiative document and asks for structured executive feedback. Also trigger when the user asks for a Go/No-Go decision, risk review across finance/legal/security/operations, or preparation for presenting an initiative to real leadership.SecurityNo warnings★ 3.7K↓ —
- recalldavepoon/buildwithclaudeSearch Origin's local memory by query. Targeted lookup, not orientation. Invoked as `/recall <query>`. Use when the user asks "do you remember", "what do you know about", "look up".ProductivityNo warnings★ 3.7K↓ —
- neon-realtimeneondatabase/agent-skillsNeon Realtime makes any SQL query live. Build realtime, reactive apps and agents on Lakebase Postgres with live SQL queries and reactivity primitives. Use when app UI or agent state must update live from database rows (dashboards, feeds, collaboration, multi-user or multi-device sync), for optimistic mutations, or to replace polling or other realtime sync systems. Triggers include "live query", "subscribe", "sync engine", "useLiveQuery", "TanStack DB", "optimistic updates", "@neon/realtime". For push that doesn't come from database rows (presence, typing, LLM streams), use neon-functions.OfficialDataNo warnings★ 108↓ —Also in 1 other repo
- i4h-workflow-dataset-mimicNVIDIA/skillsExpand workflow HDF5 demonstrations with action jitter, optionally scoped to node segments. Use for synthetic variants; do not use to collect data, alter state directly, or generate new images.ProductivityNo warnings★ 3.8K↓ —
- landing-optimizeraaron-he-zhu/aaron-marketing-skillsUse when the user asks to "optimize our landing page for influencer traffic", "fix our promo-code landing page", or "improve conversion from a creator campaign"; produces a message-match audit, page-structure and social-proof recommendations, a promo-code/CTA conversion plan, and an A/B test roadmap. Not for measuring campaign results after launch — use performance-analyzer. 落地页优化/达人流量转化提升TestingNo warnings★ 3K↓ —
- trailmark-summarytrailofbits/skillsRuns a Trailmark summary analysis on a codebase. Returns auto-detected languages, entry point count, and dependency list. Use when vivisect or galvanize needs a quick structural overview. Triggers: trailmark summary, code summary, structural overview.ProductivityNo warnings★ 7.9K↓ —
- reproduce-regressiontrailofbits/skillsUse when deploying before/after systems and building a live-system PoC for a regression candidate.DevOpsNo warnings★ 7.9K↓ —
- apify-rate-limitsjeremylongshore/tons-of-skills-marketplaceHandle Apify API rate limits with proper backoff and request queuing. Use when hitting 429 errors, optimizing API request throughput, or implementing rate-aware client wrappers. Trigger with "apify rate limit", "apify throttling", "apify 429", "apify retry", "apify backoff", "too many requests apify".EngineeringNo warnings★ 2.9K↓ —
- yt-researchjeremylongshore/tons-of-skills-marketplaceAnalyze competitor YouTube coverage and video opportunities using sourced observations with explicit sampling limits. Use when researching channels or a niche before ideation. Trigger with "research channels" or "competitive video research".ScienceNo warnings★ 2.9K↓ —
- fuzzing-obstaclestrailofbits/skillsPatches past the barriers that stop a fuzzer making progress — checksum and hash verification, magic-value validation, time-based seeds, and other non-deterministic global state. Covers locating the blocking check, neutering it behind a fuzzing build flag, and avoiding the false positives a patch can introduce. Use when a fuzzer is stuck at validation, when coverage shows large regions behind a checksum, or when valid inputs are impractical to generate.OtherNo warnings★ 7.9K↓ —
- physicsnemo-shard-tensorNVIDIA/skillsOfficial NVIDIA-authored guidance for PhysicsNeMo ShardTensor domain parallelism — integrate domain parallelism into training/inference scripts (new or existing) with DDP or FSDP2, write and register shard patches to enable new layers/ops, and bootstrap multi-GPU correctness tests. Use when working with ShardTensor, scatter_tensor, domain parallelism, sequence/spatial sharding, ring attention, DeviceMesh + DDP/FSDP2 hybrid parallelism, or physicsnemo.domain_parallel. Do NOT use for generic PyTorch DDP/FSDP setup without domain parallelism, picking a PhysicsNeMo model or example (use physicsnemo-discover), or non-distributed training questions.TestingNo warnings★ 3.8K↓ —
- doca-fireflyNVIDIA/skillsUse this skill when the user is operating the DOCA Firefly Service container on BlueField — picking the four PTP configuration axes (role / profile / domain / interface), wiring the BlueField PHC + host follower + consumer workload pairing, deciding whether PTP-grade time is even needed (vs. chrony / NTP), or debugging a Firefly deployment where PTP isn't syncing or the host clock isn't following. Trigger even when the user does not explicitly mention "DOCA Firefly" or "PTP" — typical implicit phrasings include "container green but PTP never advances past LISTENING", "Firefly says synced but the host clock still drifts", "sync acquired but offset is tens of microseconds", "my Rivermax SMPTE workload needs PTP", or "is chrony good enough". Refuse and route elsewhere for installing DOCA, host-side chrony / ptp4l config bodies, PTP topology / boundary-clock design, building DOCA apps that read the disciplined PHC, or other DOCA services (DMS, Flow-Inspector, HBN) — those belong to other skills.DevOpsNo warnings★ 3.8K↓ —
- sepia-writeNanako0129/sepiaUse when a user explicitly requests Sepia write to create new prose.WritingNo warnings★ 3.6K↓ —
- adjudicate-regressiontrailofbits/skillsUse when deciding whether source and live reproduction evidence establish a new regression or an exclusion.OtherNo warnings★ 7.9K↓ —
- doca-bare-metal-deploymentNVIDIA/skillsRunning a DOCA-linked binary directly on the hardware, with no container or kubelet: on host x86 with a BlueField NIC over PCIe, or bare-metal on BlueField Arm. Use this skill for launching and supervising it (direct, tmux, systemd), and when it "exits 1 right after launch", "systemd keeps restarting it", reports "no matching device on the BF", or the BlueField itself is unhealthy: "bfb-install exited 0 but DPU is dead", "ping 192.168.100.2 works but ssh fails", "host PFs aren't showing netdevs". Refuse service containers under kubelet (doca-container-deployment). Covers PCI/NUMA/CPU/IRQ binding, co-tenant isolation (cgroup-v2/netns/numactl), a seven-layer error taxonomy, platform lifecycle (BFB install, RShim/TMFIFO, host PF rebind, post-BFB recovery) and a six-state BlueField lifecycle classifier. Destructive firmware burn / mlxconfig set requires explicit confirmation via doca-hardware-safety; library APIs, env prep, and build use other skills.DevOpsNo warnings★ 3.8K↓ —
- g-assist-mcp-skillNVIDIA/skillsUse this skill to check or change this machine's NVIDIA display and GPU settings, such as resolution, refresh rate, V-Sync, G-SYNC, brightness, color, and GPU performance.OtherNo warnings★ 3.8K↓ —
- plain-englishjeremylongshore/tons-of-skills-marketplaceExplain supplied contract clauses in clear language while preserving conditions, exceptions and source locators. Use when a non-lawyer wants to understand an agreement. Trigger with "explain this contract", "plain-english" or "translate this contract to plain English".LegalNo warnings★ 2.9K↓ —
- impeccableUpdatedpbakaus/impeccableUse when the user wants to design, redesign, shape, critique, audit, polish, simplify, harden, animate, or otherwise improve a frontend interface: websites, landing pages, dashboards, product UI, components, forms, settings, onboarding, empty states, and native iOS or Android screens. Handles UX review, hierarchy, layout, typography, color, motion, UX copy, accessibility, responsive behavior, edge cases, and capturing or documenting design systems (DESIGN.md, tokens). Also for making bland UI bolder, loud UI quieter, or ambitious visual effects. Not for backend-only or non-UI tasks.DesignNo warnings★ 98.9K↓ —
- golang-spf13-cobrasamber/cc-skills-golangGolang CLI command tree library using spf13/cobra — cobra.Command, RunE vs Run, PersistentPreRunE hook chain, Args validators (NoArgs, ExactArgs, MatchAll, custom), persistent vs local flags, command groups, ValidArgsFunction, RegisterFlagCompletionFunc, ShellCompDirective, usage/help template customization, man-page and markdown doc generation, and testing with SetArgs/SetOut/SetErr. Apply when using or adopting spf13/cobra, or when the codebase imports `github.com/spf13/cobra`. For configuration layering alongside cobra, see the `samber/cc-skills-golang@golang-spf13-viper` skill. For general CLI architecture (project layout, exit codes, signal handling, I/O patterns), see `samber/cc-skills-golang@golang-cli`.TestingNo warnings★ 3.7K↓ —
- tao-finetune-clipNVIDIA/skillsCLIP vision-language model for image-text retrieval, zero-shot classification, embedding extraction, ONNX export, and TensorRT deployment. Use when fine-tuning or training CLIP, running zero-shot classification, computing image embeddings, or deploying CLIP to ONNX/TensorRT. This is a single-action model skill; do not use it for an iterative weak-attribute improvement loop that keeps retraining and evaluating until progress stops, which belongs to tao-run-deft-pas.DevOpsNo warnings★ 3.8K↓ —
tao-finetune-clip
NVIDIA/skills
DevOpsUpdated 2 days ago
From the author
CLIP vision-language model for image-text retrieval, zero-shot classification, embedding extraction, ONNX export, and TensorRT deployment. Use when fine-tuning or training CLIP, running zero-shot classification, computing image embeddings, or deploying CLIP to ONNX/TensorRT. This is a single-action model skill; do not use it for an iterative weak-attribute improvement loop that keeps retraining and evaluating until progress stops, which belongs to tao-run-deft-pas.
Install
npx skills add NVIDIA/skills --skill tao-finetune-clip -a claude-code
Installs to .claude/skills/tao-finetune-clip/ · Each command fetches the skill straight from GitHub with the open skills CLI.
Download .zip
Byte-identical to the scanned commit, with the repository’s licence and a SOURCE.txt.
What it can touch
Instructions onlyNo network use seenLicence: APACHE-2.0
Safety checks on SKILL.md
No warnings.
Why 90
Security100
Provenance83
Maintenance100
Licence100
Adoption57
Files (23)
- BENCHMARK.md
- SKILL.md
- config/skillspector-baseline.yaml
- evals/evals.json
- references/clip-peft.md
- references/error-patterns.md
- references/pas-metrics.md
- references/skill_info.yaml
- references/spec-param-inference.md
- references/spec_template.yaml
- references/spec_template_deploy.yaml
- references/spec_template_evaluate.yaml
- +11 more