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.
49,492 skills from 2,391 repositories · updated 15 hours ago
48,451 skills
- huggingface-vision-trainerhuggingface/skillsTrains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT, ResNet, ViT/DINOv3 — plus any Transformers classifier), and SAM/SAM2 segmentation using Hugging Face Transformers on Hugging Face Jobs cloud GPUs. Covers COCO-format dataset preparation, Albumentations augmentation, mAP/mAR evaluation, accuracy metrics, SAM segmentation with bbox/point prompts, DiceCE loss, hardware selection, cost estimation, Trackio monitoring, and Hub persistence. Use when users mention training object detection, image classification, SAM, SAM2, segmentation, image matting, DETR, D-FINE, RT-DETR, ViT, timm, MobileNet, ResNet, bounding box models, or fine-tuning vision models on Hugging Face Jobs.OfficialMediaNo warnings★ 11.3K↓ —
- email-campaignmohitagw15856/pm-claude-skillsWrite and sequence multi-email nurture or launch campaigns. Use when asked for an email sequence, drip campaign, onboarding emails, product launch emails, or nurture flow. Produces subject lines, preview text, full email body, and send-timing recommendations for each email in the sequence.MarketingNo warnings★ 1.5K↓ —
- hf-cloud-python-env-setuphuggingface/skillsSet up an isolated Python environment for SageMaker / AWS work, with the right Python version and current boto3. Use this skill whenever Python code will be executed for a SageMaker deployment, training job, or any AWS automation — including when about to run `pip install`, when about to invoke `boto3`, when creating or activating a virtualenv, or when the user asks to "set up the environment". Never use system Python and never `pip install` into it. Always isolate. This skill prevents the most common failure modes: wrong Python version, dependency conflicts, and stale SDKs.OfficialEngineeringNo warnings★ 11.3K↓ —
- tc-trackeralirezarezvani/claude-skillsUse when tracking technical changes as records, or handing work between AI sessions with a change record. Creates, updates and validates change records with tc_create.py, tc_update.py and tc_validator.py.OtherNo warnings★ 29.3K↓ —
- minutes-ideassilverstein/minutesSurface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.OtherNo warnings★ 1.6K↓ —Also in 1 other repo
- tddhashgraph-online/awesome-codex-pluginsUse when implementing or fixing production code with tests.TestingNo warnings★ 1.5K↓ —
- delta-briefingmohitagw15856/pm-claude-skillsMake a recurring brief report what changed since the last edition instead of restating everything. Use when a weekly or monthly report keeps repeating itself, when setting up a scheduled monitor or digest, or when asked to make a recurring update delta-aware. Produces a changes-first brief plus the state record the next run will diff against.WritingNo warnings★ 1.5K↓ —
- replay-user-flowsreticlehq/reticleTurn a user journey you just clicked through into a saved regression check that re-runs deterministically, with no model in the loop and no test code to write. Use when you have driven the same flow twice, when the user wants regression coverage without a Playwright suite, when a refactor needs proving against every existing journey, or when re-verifying by hand is costing a full drive every time.TestingNo warnings★ 1.3K↓ —
- doca-pcc-countersNVIDIA/skillsUse this skill when the user is invoking the DOCA PCC Counters tool — the `pcc_counters.sh` bash script under the DOCA tools directory — to arm and read the fixed firmware/hardware PCC (Programmable Congestion Control) diagnostic counters (CNP, RTT, WRED-drop, etc.) on a ConnectX / BlueField device via mst + the mlx5 debugfs `diag_cnt` interface. The script takes two positional args — `set | query` and an mst device path — with no `--help` or subcommands. Trigger even without "pcc_counters.sh" or "PCC counters": "how do I read the CNP / RTT / WRED-drop counters", "PCC counter stuck at zero", "the script says Bad Device", or "is congestion control dropping packets on this port?". Route elsewhere for writing a custom PCC algorithm (doca-pcc), factory firmware PCC config, DOCA install, or fleet-wide CC tuning.DesignNo warnings★ 3.9K↓ —
- minutes-graphsilverstein/minutesPolicy-safe relationship rankings, commitments, aliases, person profiles, and topic research. Always use Minutes' bounded native CLI surfaces; never build or read a durable graph cache.ScienceNo warnings★ 1.6K↓ —Also in 1 other repo
- minutes-debriefsilverstein/minutesPost-meeting debrief — analyzes what happened, compares outcomes to your prep intentions, tracks decision evolution. Use when the user says "debrief", "what just happened in that meeting", "what did we decide", "debrief that call", "post-meeting", "what changed", or right after stopping a recording.OtherNo warnings★ 1.6K↓ —Also in 1 other repo
- 00-arena-routeragentscope-ai/OpenJudgeUse when the user wants to compare or benchmark multiple LLMs/agents arena-style but it's unclear which specific workflow fits — a general-purpose win-rate comparison on a custom task, or a benchmark specifically about reference/citation hallucination rate. Also use when the user mentions model arena, agent arena, pairwise model comparison, win-rate ranking, or comparing models on a task and hasn't specified whether that task is generic or about citation accuracy. This skill is the entry router for the arena-eval suite: it asks one diagnostic question when needed, then recommends the workflow or workflows needed to cover the request.PlanningNo warnings★ 1K↓ —
- email-lifecycle-send-checkgooseworks-ai/goose-skillsChecks a drafted email flow or broadcast before it is loaded: flow logic and exits, overlaps, offer depth and codes, stock, claims, consent and legal footer, SMS rules, rendering, voice and AI-copy tells, and the goal metric. Returns a pass / fixed / open-question table. Use alone when you already have the finished draft and the brand's product and policy facts; otherwise run email-lifecycle.ProductivityNo warnings★ 1.3K↓ —
- linkedin-postskostja94/marketing-skillsWhen the user wants to create LinkedIn post copy or optimize for LinkedIn. Also use when the user mentions "LinkedIn post," "LinkedIn article," "professional post," "post to LinkedIn," "LinkedIn content," "LinkedIn copy," "B2B LinkedIn," "LinkedIn engagement," "LinkedIn feed," "share box," "document post," "poll," "Newsletter," "reshare," or "LinkedIn marketing." For LinkedIn ads, use linkedin-ads.MarketingNo warnings★ 1.1K↓ —
- write-outreach-reply-readergooseworks-ai/goose-skillsStep of the write-outreach playbook: sorts outreach replies by type, matches each to its prospect row, sets that person's status and keeps useful exact words. Run write-outreach instead; not for direct use.WritingNo warnings★ 1.3K↓ —
- minutes-searchsilverstein/minutesSearch past meeting transcripts and voice memos for specific topics, people, decisions, or ideas. Use this whenever the user asks "what did we discuss about X", "find that meeting where we talked about Y", "what did Alex say", "did we decide on", "what was that idea about", or any question that could be answered by searching their meeting history. Also use for "do I have any notes about" or "check my meetings for".PlanningNo warnings★ 1.6K↓ —Also in 1 other repo
- adhd-output-stylefcakyon/claude-codex-settingsThis skill should be used when the user asks for "ADHD output", "fewer output tokens", "short numbered steps", "limited working memory formatting", or explicitly invokes "adhd-output-style".ProductivityNo warnings★ 1.2K↓ —
- ad-angle-minergooseworks-ai/goose-skillsResearch supported advertising promises from a specific buyer's context, current product facts, customer language and observed ads. Turn them into static, video or copy ideas; match video ideas to actual recipes and save a product-scoped angle bank for write-video-ad-script. Product-led discovery can use verified facts without reviews. Reference persistence and reach are observations, not proof of performance.MarketingNo warnings★ 1.3K↓ —
- cloudbase-agentTencentCloudBase/CloudBase-AI-ToolkitBuild and deploy AI agents with CloudBase Agent SDK (TypeScript & Python). Implements the AG-UI protocol for streaming agent-UI communication. Use when deploying agent servers, using LangGraph/LangChain/CrewAI adapters, building custom adapters, understanding AG-UI protocol events, or building web/mini-program UI clients. Supports both TypeScript (@cloudbase/agent-server) and Python (cloudbase-agent-server via FastAPI).DevOpsNo warnings★ 1.2K↓ —Also in 5 other repos
- analyze-performance-intakegooseworks-ai/goose-skillsStep of the analyze-performance playbook: gathers the week's numbers from tools, exports and pastes, cleans them, and writes the coverage line or switches to claims-only mode. Run analyze-performance instead; not for direct use.WritingNo warnings★ 1.3K↓ —
- paper-search-usagefcakyon/claude-codex-settingsThis skill should be used when the user asks to "search for papers", "find research papers", "search arXiv", "search PubMed", "look up a DOI", "download a paper", "search IEEE", or "search Scopus".ScienceNo warnings★ 1.2K↓ —
- 01-auto-arenaagentscope-ai/OpenJudgeAutomatically evaluate and compare multiple AI models or agents without pre-existing test data. Generates test queries from a task description, collects responses from all target endpoints, auto-generates evaluation rubrics, runs pairwise comparisons via a judge model, and produces win-rate rankings with reports and charts. Supports checkpoint resume, incremental endpoint addition, and judge model hot-swap. Use when the user asks to compare, benchmark, or rank multiple models or agents on a custom task, or run an arena-style evaluation.TestingNo warnings★ 1K↓ —
- analyze-performance-diagnosegooseworks-ai/goose-skillsStep of the analyze-performance playbook: flags tracking breaks with fixes and explains each big metric move with evidence, confidence and ruled-out causes. Run analyze-performance instead; not for direct use.OtherNo warnings★ 1.3K↓ —
- trip-plannermohitagw15856/pm-claude-skillsTurn a destination, some dates, and your vibe into a realistic day-by-day trip itinerary — paced for real humans, with a packing list and a rough budget. Use when asked to plan a trip, build a travel itinerary, what should I do in [place], or help me plan my holiday. Produces a day-by-day plan grouped by area (so you're not criss-crossing the city), must-book-ahead flags, a packing list tuned to the trip, a rough budget range, and honest notes on pace and gaps to fill with local info.PlanningNo warnings★ 1.5K↓ —
list-connections
microsoft/power-platform-skills
EngineeringUpdated yesterday
From the author
Lists Power Platform connections in the current environment. Use when you need a connection ID before adding a connector to a code app.
Install
npx skills add microsoft/power-platform-skills --skill list-connections -a claude-code
Installs to .claude/skills/list-connections/ · 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: MIT
Safety checks on SKILL.md
No warnings.
Why 88
Security100
Provenance77
Maintenance100
Licence100
Adoption49
Files (1)
- SKILL.md