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.
49,395 skills from 2,375 repositories · updated 25 minutes ago
49,393 skills
- pulumi-upgrade-providerpulumi/agent-skillsAutomate Pulumi provider repo upgrades with the `upgrade-provider` tool. Use when upgrading a pulumi provider repository to a new upstream version, running `upgrade-provider`, and addressing its common failure modes like patch conflicts or missing module mappings.OfficialOtherNo warnings★ 78↓ —
- hex-debug-bundlejeremylongshore/tons-of-skills-marketplaceCollect Hex debug evidence for support tickets and troubleshooting. Use when encountering persistent issues, preparing support tickets, or collecting diagnostic information for Hex problems. Trigger with phrases like "hex debug", "hex support bundle", "collect hex logs", "hex diagnostic".EngineeringNo warnings★ 2.9K↓ —
- doca-telemetry-utilsNVIDIA/skillsdoca_telemetry_utils command line on a host with DOCA: discover the diagnostic-counter schema, translate counter names to binary Data IDs and back, and check per-device counter support before committing a DOCA Telemetry exporter config. Use this skill when telemetry counters vanish between the exporter and the collector: "my exporter ships but the collector sees nothing", "this metric silently drops downstream", "which counters does this BlueField expose", "translate this 0x... back to a counter name", "what do node / pcie_index / depth mean here", or "is this counter supported on this device", even without naming the tool. Route exporter or collector code to doca-telemetry-exporter / doca-telemetry, DTS deployment to doca-dts, and DOCA install or repair to doca-setup.DevOpsNo warnings★ 3.8K↓ —
- adobe-load-scalejeremylongshore/tons-of-skills-marketplaceDerive a safe Adobe workload envelope from synthetic load, queue/backpressure behavior, current service constraints, spend, and output correctness. Use when the task requires adobe capacity and load envelope. Trigger with "load test Adobe", "scale Firefly jobs", or "Adobe capacity plan".TestingNo warnings★ 2.9K↓ —
- codejeremylongshore/tons-of-skills-marketplaceUse BEFORE generating, refactoring, reviewing, or debugging code. Trigger phrases include "write a function/script/class for X", "review this code/diff/PR", "refactor this", "debug this error", "is this implementation correct", "what's wrong with this code", "improve this code", "translate from X to Y", or any prompt with a code block the user wants you to act on. Also fires when planning architectural changes, picking algorithms or data structures, or evaluating dependency upgrades. Calls the code MCP tool to retrieve an engineering scaffold (failure pattern, procedure, correct-pattern example, verification step) before generating. Catches hallucinated APIs, lost edge cases, premature algorithm commitment, silent contract violations, refactors that change behavior masked by passing tests. Do NOT trigger for pure code reading with no action requested, simple syntax questions, file system operations, running existing tests, or confirming an existing pattern is fine.EngineeringNo warnings★ 2.9K↓ —
- cohere-hello-worldjeremylongshore/tons-of-skills-marketplaceRun bounded Cohere v2 Chat, Embed, or Rerank requests with current model discovery and explicit validation. Use when proving a new Cohere setup. Trigger with "Cohere hello world", "Cohere quickstart", or "test Cohere API".TestingNo warnings★ 2.9K↓ —
- clerk-rate-limitsjeremylongshore/tons-of-skills-marketplaceUnderstand and manage Clerk rate limits and quotas. Use when hitting rate limits, optimizing API usage, or planning for high-traffic scenarios. Trigger with phrases like "clerk rate limit", "clerk quota", "clerk API limits", "clerk throttling".PlanningNo warnings★ 2.9K↓ —
- i4h-workflow-train-rlNVIDIA/skillsUse when training, evaluating, or exporting Workflow policies with online RSL-RL or RLinf, including RL checkpoint and Workflow handoff.ProductivityNo warnings★ 3.8K↓ —
- attio-sdk-patternsjeremylongshore/tons-of-skills-marketplaceBuild a typed Attio REST client with tenant-aware tokens, endpoint-specific pagination, structured errors, bounded retries, and contract tests while distinguishing it from the Attio App SDK. Use when creating or refactoring Attio integration code. Trigger with "Attio SDK", "Attio client wrapper", or "typed Attio API".TestingNo warnings★ 2.9K↓ —
- package-searchdavepoon/buildwithclaudeSearch for packages and assess security risk before adding as dependenciesSecurityNo warnings★ 3.7K↓ —
- gsd:ai-integration-phasedavepoon/buildwithclaudeGenerate AI design contract (AI-SPEC.md) for phases that involve building AI systems — framework selection, implementation guidance from official docs, and evaluation strategyDesignNo warnings★ 3.7K↓ —
- anima-rate-limitsjeremylongshore/tons-of-skills-marketplaceImplement rate limiting for Anima API code generation requests. Use when batching component generation, handling rate limit errors, or optimizing API throughput for large design systems. Trigger with: "anima rate limit", "anima throttling", "anima batch generation".DesignNo warnings★ 2.9K↓ —
- kavel-image-studiodavepoon/buildwithclaudeTurn a photo into a specific AI look (new hairstyle, collectible figurine, royal pet portrait, wedding photo, 90s yearbook, sticker, HD restore) or a photo into a dance video, using Kavel (www.kavel.ai). Use when the user wants to restyle/transform a photo, asks "how do I make an AI X from my photo", or wants a photorealistic image edit that keeps the same face. Gives the right tool, a model-tuned prompt, and the generate link.MediaNo warnings★ 3.7K↓ —
- research-to-deployjeremylongshore/tons-of-skills-marketplaceResearch current infrastructure documentation, generate reviewable deployment configurations and runbooks, and execute scoped deployments when authorized. Use when planning a cloud deployment or creating Terraform, container or Kubernetes configurations. Trigger with "research and deploy", "create Terraform" or "generate infrastructure configs".DevOpsNo warnings★ 2.9K↓ —
- alchemy-cost-tuningjeremylongshore/tons-of-skills-marketplaceGovern Alchemy compute usage and spend with current account evidence, workload attribution, budgets, and reversible optimizations. Use when forecasting or reducing Alchemy cost. Trigger with "Alchemy cost", "Alchemy compute units", or "reduce Alchemy spend".OtherNo warnings★ 2.9K↓ —
- share-of-voice-trackeraaron-he-zhu/aaron-marketing-skillsUse when the user asks to "track our share of voice", "what share of the conversation do we own vs competitors", or "trend our SOV this quarter"; computes SOV% = brand mentions ÷ (brand + competitor panel mentions) per platform per period on a LOCKED competitor panel — a panel switch invalidates the trend (restart the series and log the break; the ECHO O3 rule) — plus a sentiment-weighted SOV variant (sentiment labeled Estimated unless human-coded) and a Wikipedia-pageviews attention-share alternative; built from keyless listening connectors, gdelt.py news echo, and user exports — public counts only, closed platforms are never scraped. Not for backlink or offsite SEO signals — use offsite-signal-analyzer. 声量份额/竞品声量对比/提及份额/注意力份额BrowserNo warnings★ 3.1K↓ —
- hermes-tweetdavepoon/buildwithclaudeUse Hermes Tweet when a Claude Code workflow needs a source-aware handoff to Hermes Agent for X/Twitter research, account context, monitoring, or approval-gated actions through the native Hermes Agent plugin.ScienceNo warnings★ 3.7K↓ —
- category-narrative-mapperaaron-he-zhu/aaron-marketing-skillsUse when the user asks to "map the category narrative", "tear down how competitors tell their story", or "find the language conventions in our market"; produces a category narrative map — the dominant stories and points of view in the category, its language conventions and framing clichés, and a per-competitor narrative teardown (arc, claimed onlyness, proof pattern) plus how each rival's messaging has shifted over time (scraped copy vs archived copy). Not for the positioning canvas itself — use positioning-mapper; not for the beachhead's beliefs and objections — use audience-belief-mapper; not for SERP keyword targeting — use keyword-research; not for claim adjudication — use offer-claims-registry. 品类叙事/竞争叙事拆解/语言惯例/叙事演变BrowserNo warnings★ 3.1K↓ —
- adobe-observabilityjeremylongshore/tons-of-skills-marketplaceInstrument Adobe integrations with redacted structured logs, request/job/activation correlation, service-level indicators, alerts, and evidence retention. Use when the task requires adobe content-safe observability. Trigger with "monitor Adobe API", "Adobe observability", or "App Builder logs".DevOpsNo warnings★ 2.9K↓ —
- abridge-rate-limitsjeremylongshore/tons-of-skills-marketplaceAnalyze and control capacity, queueing, and backpressure for a tenant-specific Abridge integration without inventing public limits or headers. Use when handling concurrency or throttling requirements. Trigger with "plan Abridge capacity".PlanningNo warnings★ 2.9K↓ —
- groq-rate-limitsjeremylongshore/tons-of-skills-marketplaceImplement Groq rate limit handling with backoff, queuing, and header parsing. Use when handling rate limit errors, implementing retry logic, or optimizing API request throughput for Groq. Trigger with phrases like "groq rate limit", "groq throttling", "groq 429", "groq retry", "groq backoff".EngineeringNo warnings★ 2.9K↓ —
- reviewdavepoon/buildwithclaudePower-user audit of Origin's pending surfaces. Most users want `/brief` for revisions. That handles the daily flow. Use `/review` only for explicit deep-walk audits after bulk imports, or when you want to walk the full queue rather than the top 3 shown in /brief. Invoked as `/review captures` or `/review revisions`.EngineeringNo warnings★ 3.7K↓ —
- wiki-synthesizeAr9av/obsidian-wikiFind recurring concept combinations across the wiki that lack an explicit synthesis page, then create cross-cutting synthesis pages. Use for knowledge synthesis after the vault has accumulated enough material.OtherNo warnings★ 3.7K↓ —
- drill-statusdavepoon/buildwithclaudeShow drill-me learning progress — topics studied, cards due for review, weakest concepts, and what to study next. Use when the user asks what's due, how their learning is going, or for their drill-me status.EngineeringNo warnings★ 3.7K↓ —
tao-train-mask-auto-label
NVIDIA/skills
OtherUpdated 18 hours ago
From the author
MAL (Mask Auto-Label) for weakly-supervised segmentation. Produces segmentation masks from minimal annotations (point or box annotations) using a ViT-MAE backbone. Use when training, evaluating, or running inference for a TAO MAL model. Trigger phrases include "train MAL", "Mask Auto-Label", "weakly-supervised segmentation", "box-prompted segmentation", "minimal-annotation mask prediction".
Install
npx skills add NVIDIA/skills --skill tao-train-mask-auto-label -a claude-code
Installs to .claude/skills/tao-train-mask-auto-label/ · 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 (14)
- BENCHMARK.md
- SKILL.md
- config/skillspector-baseline.yaml
- evals/evals.json
- references/skill_info.yaml
- references/spec_template_evaluate.yaml
- references/spec_template_inference.yaml
- references/spec_template_train.yaml
- schemas/evaluate.schema.json
- schemas/inference.schema.json
- schemas/manifest.json
- schemas/train.schema.json
- +2 more