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.
48,168 skills from 2,325 repositories · updated 22 hours ago
48,168 skills
- nemo-rl-session-memoryNVIDIA/skillsManage durable working-session memory for coding agents. Use when a user asks to preserve or recover agent context across disconnects, VS Code restarts, long-running work, handoffs, or any session where important state should be written periodically under the repo's session directory. Do NOT use for: simple questions, short tasks, one-off commands, linting, or code review.ProductivityNo warnings★ 3.8K↓ —
- tao-train-ocdnetNVIDIA/skillsOCDNet for scene text detection. Detects arbitrary-oriented text regions in natural images using a differentiable binarization approach. Use when training, evaluating, exporting, pruning, quantizing, retraining, or running inference for a TAO OCDNet model. Trigger phrases include "train OCDNet", "scene text detection", "arbitrary-oriented text boxes", "differentiable binarization detector".OtherNo warnings★ 3.8K↓ —
- building-python-mcp-serverskajisho5/ffmpeg-skillBuilds robust Python MCP (Model Context Protocol) servers with FastMCP — tool design, error contracts, event-loop-safe blocking work, subprocess/CLI wrapping, single-file vs packaged distribution, global-state-free testing, and prompt-injection awareness. Use when writing an MCP server, exposing a tool or CLI to an LLM client, debugging tool registration/packaging, or testing MCP tools.EngineeringNo warnings★ 4.1K↓ —
- launch-asset-packageraaron-he-zhu/aaron-marketing-skillsUse when the user asks to "package the launch assets", "build a press kit", or "prep the store listing and go-live checklist"; produces a tier-scoped launch asset manifest with production status — a press kit spec (factsheet, description, history, features, videos, images, logo and icon, awards, contact), demo script and screenshot specs, a launch FAQ, dual-store listing metadata drafts against the official character budgets (per App Store Connect / Play Console documentation), and a technical go-live checklist manifest (robots flip, sitemap, OG tags, analytics verification — execution stays with technical-seo-checker and serp-markup-builder). Not for the message copy itself — use message-house-builder or content-writer; not for landing page UX — use landing-optimizer; not for keyword research beyond the store surfaces — use keyword-research. 发布资产打包/press kit/商店listing规格/上线检查清单DataNo warnings★ 3K↓ —
- i4h-lerobot-vizNVIDIA/skillsServe and visually inspect a converted LeRobot dataset in the browser. Use for videos and state/action timelines; do not use for raw workflow HDF5 or incomplete conversion output.BrowserNo warnings★ 3.8K↓ —
- concurrent-brancheskajisho5/ffmpeg-skillResolve conflicts and merges when several branches are open against one repo at the same time — the hotspot files every change must touch (registry manifests, a single version field, shared tool config, one aggregated test module, tracked build output), union-vs-recompute-vs-rebuild as three different correct resolutions, generated artifacts that must never be merged, non-deterministic serialization that makes every branch conflict, renumbered identifiers that git cannot show you, and why a clean auto-merge is not a passing test. Use when rebasing or merging a long-lived branch, resolving conflict markers, reviewing a merge commit, deciding what a repo should commit vs generate, or setting up a repo that will take parallel contributions.TestingNo warnings★ 4.1K↓ —
- miro-cost-tuningjeremylongshore/tons-of-skills-marketplaceDiagnose Miro API credit demand and implement repository-side traffic controls that preserve freshness, completeness, and user experience. Use when right-sizing polling or synchronization. Trigger with "reduce Miro API usage".EngineeringNo warnings★ 2.9K↓ —
- principle-prove-it-worksmichael-denyer/pstack-claudeApply after completing a task, before declaring done. Verify against the real artifact (run the feature, read the actual value, inspect the diff), not a proxy, self-report, or 'it compiles.'ProductivityNo warnings★ 3.7K↓ —
- scientific-brainstormingforyourhealth111-pixel/Vibe-SkillsOpen-ended scientific ideation partner. Use for research gaps, mechanism exploration, interdisciplinary connections, assumptions, possible research directions, and lightweight literature matrix or A+B paper-combination idea mapping. For structured testable hypotheses and validation plans, use hypothesis-generation instead.ScienceNo warnings★ 3.8K↓ —
- navan-sdk-patternsjeremylongshore/tons-of-skills-marketplaceDesign an application-owned Navan adapter pinned to the tenant's actual integration contract. Use when wrapping Booking API, Expense API, SFTP, or direct integration behavior. Trigger with "build a Navan client", "wrap Navan API", or "type Navan responses".DesignNo warnings★ 2.9K↓ —
- guarding-destructive-operationskajisho5/ffmpeg-skillAdd and review preconditions on operations that delete, overwrite, rewrite history, or resolve a caller-supplied name to a filesystem path — refusing instead of warning, placing the guard ahead of the first mutation, structural classification rather than string-prefix matching, name validation plus resolved-path containment as two independent checks, why a guard on the destructive path is invisible to the dry-run, and mutation-testing each half separately. Use when writing or reviewing a `--rebuild`/`--reset`/`--purge` command, a bulk delete, a history rewrite, an `rm -rf`-shaped step, or any code that turns an argument into a file path.TestingNo warnings★ 4.1K↓ —
- ad-angle-researchdavepoon/buildwithclaudePull the ads a competitor is running right now on Meta (Facebook/Instagram) and Google, then extract the hooks, offers, CTAs and landing pages worth modelling. Use when writing ad copy, planning creative tests, choosing a landing page angle, or when the user asks "what is X advertising", "what ads does X run", "find competitor ad hooks". Reads live Ad Library and Ads Transparency data through the Tracetify MCP; falls back to a manual Ad Library walkthrough when the connector is absent.ScienceNo warnings★ 3.7K↓ —
- validate-pluginjeremylongshore/tons-of-skills-marketplaceValidate a Claude Code plugin directory against the official Anthropic spec and Intent Solutions enterprise standard. Runs structural validation (plugin.json fields, file references, permissions) and content validation (SKILL.md grading, command/agent frontmatter). Use when building a new plugin, preparing for marketplace submission, or auditing existing plugins. Trigger with "validate this plugin", "check plugin structure", "grade my plugin", "/validate-plugin".PlanningNo warnings★ 2.9K↓ —
- torchdrugforyourhealth111-pixel/Vibe-SkillsGraph-based drug discovery toolkit. Molecular property prediction (ADMET), protein modeling, knowledge graph reasoning, molecular generation, retrosynthesis, GNNs (GIN, GAT, SchNet), 40+ datasets, for PyTorch-based ML on molecules, proteins, and biomedical graphs.ScienceNo warnings★ 3.8K↓ —
- brevo-automationdavepoon/buildwithclaudeAutomate Brevo (Sendinblue) tasks via Rube MCP (Composio): manage email campaigns, create/edit templates, track senders, and monitor campaign performance. Always search tools first for current schemas.MarketingNo warnings★ 3.7K↓ —
- gsd:list-phase-assumptionsdavepoon/buildwithclaudeSurface Claude's assumptions about a phase approach before planningPlanningNo warnings★ 3.7K↓ —
- babysitmichael-denyer/pstack-claudeWatch an open PR — fix failing CI, handle the straightforward review comments, and drive it to a mergeable state. Claude Code analog of Cursor's built-in /babysit. Use after opening a PR when the user wants the agent to shepherd it without re-prompting.EngineeringNo warnings★ 3.7K↓ —
- thermosmichael-denyer/pstack-claudeLaunch both thermo-nuclear review subagents in parallel, then synthesize their findings. Use for thermos, double thermo review, or combined bug/security and code-quality branch audits.SecurityNo warnings★ 3.7K↓ —
- i4h-workflow-createNVIDIA/skillsCreate a minimal blank Workflow scaffold with a Scene containing ground and light plus an idle run mode. Use for fast new Workflow scaffolding.ProductivityNo warnings★ 3.8K↓ —
- kiro-debuggotalab/cc-sddInvestigate implementation failures using root-cause-first debugging. Use when an implementer is blocked, verification fails, or repeated remediation does not converge.EngineeringNo warnings★ 3.7K↓ —Also in 7 other repos
- neurokit2foryourhealth111-pixel/Vibe-SkillsComprehensive biosignal processing toolkit for analyzing physiological data including ECG, EEG, EDA, RSP, PPG, EMG, and EOG signals. Use this skill when processing cardiovascular signals, brain activity, electrodermal responses, respiratory patterns, muscle activity, or eye movements. Applicable for heart rate variability analysis, event-related potentials, complexity measures, autonomic nervous system assessment, psychophysiology research, and multi-modal physiological signal integration.ScienceNo warnings★ 3.8K↓ —Also in 1 other repo
- email-sequence-designeraaron-he-zhu/aaron-marketing-skillsUse when the user asks to "design a welcome flow", "set up an abandoned-cart sequence", "build a light re-engagement branch inside a lifecycle flow", or "plan a cold-outbound sequence"; produces general lifecycle automation flows (welcome, cart, browse-abandon, post-purchase, in-flow re-engagement, B2B cold outbound) with trigger, step timing, branch/exit conditions, goal, frequency governance (send caps, quiet hours, fatigue guardrail), a sunset path, and a SEND N-dimension score. Not for the closed-loop win-back / re-consent (re-permission) program on a lapsed cohort — use reactivation-specialist; not for writing each email's copy — use email-creative-builder; not for computing EQS or the N1 unsubscribe veto — use email-quality-auditor. 邮件自动化流程设计/购物车挽回/流失召回序列ProductivityNo warnings★ 3K↓ —
- garden-inboxpaperclipai/paperclipScan a Paperclip user's Mine inbox, classify reversible archive candidates, request checkbox confirmation, and archive only accepted selections. Use when asked to garden, clean up, prune, or tidy a Paperclip inbox without changing issues, branches, or workspaces.OtherNo warnings★ 109.2K↓ —
- impeccablepbakaus/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★ 97.8K↓ —
nemo-mbridge-resiliency
NVIDIA/skills
OtherUpdated 2 days ago
From the author
Resiliency features in Megatron Bridge including fault tolerance, straggler detection, in-process restart, preemption, and re-run state machine.
Install
npx skills add NVIDIA/skills --skill nemo-mbridge-resiliency -a claude-code
Installs to .claude/skills/nemo-mbridge-resiliency/ · 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 (6)
- BENCHMARK.md
- SKILL.md
- card.yaml
- evals/evals.json
- skill-card.md
- skill.oms.sig