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 17 hours ago
47,548 skills
- kaltstart-interviewKlotzkette/claude-fuer-deutsches-rechtFür Kaltstart-Interview: routet Rolle, Frist, Unterlagen und Fachschritt; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: Prozessrecht.PlanningNo warnings★ 1.8K↓ —
- gutachten-uebungKlotzkette/claude-fuer-deutsches-rechtFür Gutachtenstil-Übung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.OtherNo warnings★ 1.8K↓ —
- knowledge-baseinkeep/open-knowledgeHow to work in a Knowledge Base project (the `knowledge-base` starter pack). Read when the project has the three-layer source-grounded layout — `external-sources/` → `research/` → `articles/` — or when asked how this project is organized. Carries the layer model, per-folder rules, status flows, and log discipline so this guidance does NOT live inside template bodies or log.md. The three procedures live elsewhere: ingest in the platform `open-knowledge` skill, research and consolidate as their own sibling skills in this pack. Complements the platform `open-knowledge` skill; does not replace it.ScienceNo warnings★ 4.8K↓ —
- reverse-engineer-marketingNewcoreyhaines31/marketingskillsWhen the user wants to reverse engineer how another company grew and copy what worked. Also use when the user mentions 'reverse engineer,' 'how did X grow,' 'how does X get customers,' 'growth teardown,' 'marketing teardown,' 'GTM teardown,' 'growth blueprint,' 'what is X doing for marketing,' 'what made X take off,' 'copy X's playbook,' 'X's distribution strategy,' 'what content works for X,' 'funnel hack,' 'map their funnel,' or 'watch what X is doing.' Builds a dated log of a company's moves against its traffic curve from public data, sign-ups and demos, team interviews, and hidden signals (DNS, certificate logs, archives, sponsorships), compares it with the user's own data, and turns what lined up with growth into plays routed to the skill that runs each one. For a snapshot profile of a competitor's positioning, pricing, and features, see competitor-profiling. For comparison pages, see competitors. For why a single post went viral, see social.MarketingNo warnings★ 57.8K↓ —
- planning-with-filesOthmanAdi/planning-with-filesPersistent file-based planning for multi-step AI-agent work. Keeps task_plan.md, findings.md, and progress.md on disk; agent instructions read selected project planning context when invoked. Automatic recovery reads project planning files only. Explicit session-catchup.py --metadata reads same-project local agent session records and emits aggregate counts only; --replay may emit bounded nonce-framed excerpts. This adapter registers no lifecycle or Stop hook, never requests continuation, and never runs commands declared in Markdown. The skill has no network upload path. Use for research or work needing 5+ tool calls.PlanningNo warnings★ 27.8K↓ —
- cloudwatchitsmostafa/aws-agent-skillsAWS CloudWatch monitoring for logs, metrics, alarms, and dashboards. Use when setting up monitoring, creating alarms, querying logs with Insights, configuring metric filters, building dashboards, or troubleshooting application issues.DevOpsNo warnings★ 1.2K↓ —
- research-marketgooseworks-ai/goose-skillsMarket research and brand watch: which market the brand is in, how big the reachable part is, what's changing, how buyers buy and what they pay, what people are saying now, and what it means for positioning. Use when the marketer asks for market research, "how big is my market", "what's changing in my category", "what do others charge", "what are people saying about us", "is there demand for <idea>", or "watch my brand / tell me if something blows up" (alerts only, risk first). Also writes positioning choices and finished messages ("position my product", "write our positioning"). Researches first, asks only decisions at the end, and saves the output to the brand. Not for who the buyers are and their own words — use research-audience; not for a deep look at rivals — use research-competitors.ScienceNo warnings★ 1.3K↓ —
- api-docs-writermohitagw15856/pm-claude-skillsWrite clear, developer-facing API documentation. Use when asked to document an API endpoint, write API reference docs, create a developer guide, or turn a raw spec/Postman collection into documentation. Produces endpoint documentation with descriptions, parameters, request/response examples, and error codes.WritingNo warnings★ 1.5K↓ —
- train-sentence-transformershuggingface/skillsTrain or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder, dense or static embedding model for retrieval, similarity, clustering, classification, paraphrase mining, dedup, multimodal), `CrossEncoder` (reranker, pair scoring for two-stage retrieval / pair classification), `SparseEncoder` (SPLADE, sparse embedding model for learned-sparse retrieval), and `MultiVectorEncoder` (ColBERT / late-interaction, per-token embeddings scored with MaxSim). Covers loss selection, hard-negative mining, evaluators, distillation, LoRA, Matryoshka, and Hugging Face Hub publishing. Use for any sentence-transformers training task.OfficialProductivityNo warnings★ 11.2K↓ —
- huggingface-paper-publisherhuggingface/skillsPublish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research articles.OfficialScienceNo warnings★ 11.2K↓ —
- huggingface-community-evalshuggingface/skillsRun evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware. Use for backend selection, local GPU evals, and choosing between vLLM / Transformers / accelerate. Not for HF Jobs orchestration, model-card PRs, .eval_results publication, or community-evals automation.OfficialOtherNo warnings★ 11.2K↓ —
- 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★ 11.2K↓ —
- openmeld-cliamplifthq/openmeldUse OpenMeld when a task needs Organization knowledge or Skills, Center Agent help, shared Spaces or Files, another Agent or computer, or scheduled cloud work. Also use for OpenMeld setup and Wake replies.EngineeringNo warnings★ 1.4K↓ —Also in 4 other repos
- plan-campaign-channel-decisiongooseworks-ai/goose-skillsStep of the plan-campaign playbook: marks each candidate channel Run, Test, Later or No with a brand-fact reason and founder hours. Run plan-campaign instead; not for direct use.MarketingNo warnings★ 1.3K↓ —
- debugging-ci-failuresamplifthq/openmeldDebugs failing GitHub Actions CI runs for PostHog PRs, commits, and branches, and answers broad CI-health questions ("is CI red?", "is master green today?", "what's broken right now?"). Use when the user asks why CI is red, asks for the current CI or master status, or mentions a failing check, GitHub Actions run, Depot runner, workflow, job, shard, merge queue kick, flaky test, lint failure, typecheck failure, snapshot diff, migration check, generated types drift, or skills build failure. Start with the `hogli ci:insights` digest (cross-run CI history from engineering analytics), then guides read-only inspection, failure classification, smallest local reproduction with hogli, and safe reporting without rerunning CI or posting to GitHub. Running unattended as the "Master-red diagnosis" workflow: see references/master-red-incident.md.EngineeringNo warnings★ 1.4K↓ —
- writing-testsamplifthq/openmeldGates whether a new test should exist and forces it to be efficient, protecting CI from low-value test bloat. Use before any change to what a pytest, Jest, or Playwright test asserts or sets up, down to one fixture or one assertion added to an existing block. Front-loads the value bar (every test must catch a realistic regression no existing test already catches; extend the nearest existing test before writing a new standalone one; test behavior through the public interface, not implementation details; collapse near-duplicates into parameterized cases) and the efficiency bar (deterministic, isolated, fast; pick the cheapest test level; Django TestCase over TransactionTestCase; no sleeps, no real network; no time bombs from absolute dates left to age against the real clock; no database a test never uses). Includes a "don't write it" decision tree. For fixing an existing flaky test use `/fixing-flaky-tests`; after this gate says a Playwright test is warranted, use `/playwright-test` for mechanics.TestingNo warnings★ 1.4K↓ —
- openmeld-cliamplifthq/openmeldOfficial public OpenMeld Skill for agents using the `openmeld` CLI to consult the Center Agent, set up OpenMeld, connect local agents, create or request Agent Profiles, work in Organizations and Spaces, observe or stop Wakes, trace delivery, and repair local state.EngineeringNo warnings★ 1.4K↓ —
- react-doctoramplifthq/openmeldUse when the user requests React Doctor or a React code-health audit, or when a concrete React diagnostic question would benefit from its scan. Not a default step after React changes or before committing.EngineeringNo warnings★ 1.4K↓ —
- deck-from-docmohitagw15856/pm-claude-skillsTurn the user's REAL doc into a slide deck — open the source, structure the narrative, and build the actual .pptx — not slide-writing tips. Use when asked to make a deck from this doc, turn my brief into slides, build the presentation from my Drive doc, or deckify this in Cowork. Reads the document via the Google Drive/Docs connector, maps it to a one-idea-per-slide narrative, and produces a real presentation artifact (.pptx) with speaker notes plus a slide-by-slide outline.DocumentsNo warnings★ 1.5K↓ —
- openmeld-cliamplifthq/openmeldUse OpenMeld through its public CLI to work in Spaces, reply to a Wake, consult the Center Agent, connect this computer, manage Agent Profiles, or diagnose delivery.EngineeringNo warnings★ 1.4K↓ —
- ad-creative-testingNewhashgraph-online/awesome-codex-pluginsTurn one winning ad into a creative testing plan for TikTok and Meta. Decodes why an ad won (hook, argument, buyer, format), plans concepts that Meta's Andromeda and TikTok treat as genuinely different (buyer × angle × format × first frame, not caption swaps), sets how many creatives to launch, the budget per test and when to judge, writes file and ad names that make results readable, reads hook rate, hold rate, CTR and CPA to find which part failed, and says when to kill, iterate or scale. Use when someone asks how many ads to test, how to make ad variants, why their variants all perform the same, whether an ad is fatigued, when to kill an ad, or how to scale a winner. NOT for producing the videos (use ecommerce-video-ads, ecommerce-video-edit or product-video-hooks) or for media-buying account setup.TestingNo warnings★ 1.5K↓ —
- product-video-hooksNewhashgraph-online/awesome-codex-pluginsTurn a product into scroll-stopping video hooks. Writes the first 3 seconds of TikTok, Reels and Meta product videos as three agreeing layers (what is on screen, the spoken line, the text overlay), from the buyer's own words, across 20+ hook types taken from Meta's Hooks Menu, Motion's 2026 hook data, Hormozi's callouts and the TikTok openers that spread in 2026 (late discovery, compliment then reveal, problem and fix in one clip, reply to a comment). It matches each hook to the buyer's awareness, checks it against platform claim rules, and, when footage exists, makes one MP4 per hook for testing. Use when someone asks for hooks, openers, the first 3 seconds, a better intro, or new hook variants for a product video or ad. NOT for whole ad plans (use ecommerce-video-ads), generating a viral-style product-in-use hook clip from photos (use varg-product-hook), app or SaaS hooks, or YouTube titles and thumbnails.MediaNo warnings★ 1.5K↓ —
- varg-unboxing-videoNewhashgraph-online/awesome-codex-pluginsTurns product photos into an unboxing or ASMR video ad on varg: hands-only, top-down or POV, the box tapped, opened and the product lifted out and switched on, with native ASMR sound (taps, crinkle, lid pop) and no music, in timed VISUAL / ACTION / SOUND blocks on Seedance 2.5 with the box and the product as references. Unboxing has the highest winner rate of any Meta ad format (9.8%, Motion 2026) while only 2.1% of ads use it. Use when a seller (TikTok Shop, Shopify, dropshipping, Amazon) asks for an unboxing video, an ASMR or satisfying product video, "open the box" content, a packaging reveal, or a hands-only product demo made from photos. Not for talking-head UGC (use ai-ugc-ad-video), the full 60 s guide reel (varg-dropship-reel) or a studio spin of the product alone (product-photo-to-video).MediaNo warnings★ 1.5K↓ —
- slack-agent-flownanocoai/nanoclawLet an existing Slack agent create new agents that arrive as their own Slack bots — provisioned app, operator DM, and a shared three-way room, hot-started without a host restart.OtherNo warnings★ 31.1K↓ —
cost-optimization
rampstackco/claude-skills
DevOpsUpdated 6 days ago
From the author
Audit and reduce infrastructure and tooling costs without sacrificing reliability or velocity. Use this skill when reviewing monthly cloud or SaaS spend, finding unused resources, rightsizing infrastructure, negotiating vendor contracts, deciding what to consolidate, or planning for budget cuts. Triggers on cost optimization, cloud spend, SaaS spend, rightsizing, unused resources, FinOps, infrastructure audit, vendor consolidation, budget cut, cost review. Also triggers when finance flags rising costs or when a contract renewal is up.
Install
npx skills add rampstackco/claude-skills --skill cost-optimization -a claude-code
Installs to .claude/skills/cost-optimization/ · 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
Provenance76
Maintenance100
Licence100
Adoption49
Files (3)
- README.md
- SKILL.md
- references/cloud-audit-checklist.md