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.
49,418 skills from 2,407 repositories · updated 12 minutes ago
49,416 skills
- 02-rl-rewardagentscope-ai/OpenJudgeBuild RL reward signals using the OpenJudge framework. Covers choosing between pointwise and pairwise reward strategies based on RL algorithm, task type, and cost; aggregating multi-dimensional pointwise scores into a scalar reward; pairwise tournament reward for GRPO on subjective tasks (net win rate across group rollouts); generating preference pairs for DPO/RLAIF; and normalizing scores for training stability. Use when building reward models, scoring rollouts for GRPO/REINFORCE, generating preference data for DPO, or doing Best-of-N selection.ProductivityNo warnings★ 1.1K↓ —
- add-sharepointmicrosoft/power-platform-skillsUse when the user wants to read or write SharePoint lists, manage documents in a SharePoint document library, or create a new SharePoint list from a Power Apps mobile app.WritingNo warnings★ 1.1K↓ —
- k2fcakyon/claude-codex-settingsBuild and troubleshoot Cloudflare K2 or K2 Streams durable logs. Use for stream setup, producing from Workers or HTTP, configuring retention and inputs, and consuming through subscriptions.DevOpsNo warnings★ 1.2K↓ —
- setupfcakyon/claude-codex-settingsThis skill should be used when user encounters "ADC not found", "gcloud auth error", "GCloud MCP error", "Application Default Credentials", "project not set", or needs help configuring GCloud integration.OtherNo warnings★ 1.2K↓ —
- red-green-proofalirezarezvani/claude-skillsTurns a suspected bug into a proven one. Verify the cause against reality before claiming it, write a test that FAILS on the current code, apply the fix, watch it pass — then revert the fix and confirm the test goes red again, because a test that passes both ways proves nothing. Invoked bare after a debugging conversation, it takes the target from context rather than asking. Use when fixing a bug, investigating an incident, hardening a flaky area, or when asked to "add tests that reveal the bug". Triggers on "/red-green-proof", "prove the bug", "red-green", "make the test fail first", "is that test load-bearing", "reveal the bug with a test".TestingNo warnings★ 29.3K↓ —
- ai-content-collaborationrampstackco/claude-skillsHow humans and AI compose in content workflows. Where AI legitimately participates, where humans must own, hybrid workflow patterns, voice ownership preservation, the AI slop problem, disclosure and transparency, team calibration, and the ethics of intellectually honest AI-assisted content production. Triggers on AI content workflow, AI-assisted writing, hybrid content production, AI in editorial, AI slop, AI disclosure, AI usage policy, AI content ethics, voice preservation with AI, team AI calibration. Also triggers when content feels generic despite quality tools, when team AI usage has drifted into inconsistency, or when a regulated or trust-sensitive context requires explicit AI policy.LegalNo warnings★ 1K↓ —
- oma-debugUpdatedfirst-fluke/oh-my-agentDiagnose a reproducible failure, fix its cause, and verify the regression. Use for crashes, incorrect behavior, and failing tests.EngineeringNo warnings★ 1.4K↓ —Also in 4 other repos
- setup-offline-profilemicrosoft/power-platform-skillsUse when the user wants to enable offline mode for a Power Apps mobile app and create a Mobile Offline Profile in Dataverse — designs per-table row scope, relationships, columns, and sync frequency through a 3-gate approval flow.OtherNo warnings★ 1.1K↓ —
- write-outreachgooseworks-ai/goose-skillsCold outreach a person sends to business buyers: email and LinkedIn sequences, a first line per prospect, reply and objection answers, and a read of replies. Use when the marketer says "write a cold email sequence", "what do I send to this list", "write LinkedIn messages for these leads", "how do I reply to this prospect" or "handle this objection", "reply to this demo request", "win back or reconnect with accounts that churned or went quiet", or "why is nobody replying to my outreach". Drafts only; the marketer sends from their own tool. Not for finding the people — use research-audience; not for emails to subscribers or users, or consumer win-back — use email-lifecycle.WritingNo warnings★ 1.3K↓ —
- rpihashgraph-online/awesome-codex-pluginsDrive one accepted change through implementation and checks to done, with one fresh review only where a mistake is costly. Use when: asked to run or orchestrate work through RPI.EngineeringNo warnings★ 1.5K↓ —Also in 2 other repos
- writing-livekit-scenariosfcakyon/claude-codex-settingsCreates and maintains the scenarios a LiveKit agent simulation runs, and wires the agent to consume them. Use when the user asks "what should I test", "generate simulation scenarios", "write scenarios for my agent", "add a scenario for X", "organize my scenario files", "my simulations are flaky", "the scenario hits my real database", "seed state per scenario", "it passed but booked the wrong thing", "grade the final state", or wants to stress-test a flow before shipping. Covers generating a baseline with the LiveKit scenario generator and refining it, writing the cases generation misses, phrasing simulated-user instructions so they steer reliably, splitting scenarios into sets across files, and the agent-side code that seeds deterministic state from a scenario and fails a run on its final state. To run them use running-livekit-simulations.WritingNo warnings★ 1.2K↓ —Also in 1 other repo
- spec-workflowTencentCloudBase/CloudBase-AI-ToolkitUse when medium-to-large changes need explicit requirements, technical design, and task planning before implementation, especially for multi-module work, unclear acceptance criteria, or architecture-heavy requests.PlanningNo warnings★ 1.2K↓ —Also in 5 other repos
- evidence-based-reviewsrampstackco/claude-skillsProduce honest product reviews and buying guides without fabricated first-hand experience, using disclosed evidence tiers: verified specs, owner-experience synthesis at scale, expert triangulation, and hands-on only when true. Use this skill whenever the user wants to write product reviews or buying guides without hands-on access, set up a review methodology, add evidence disclosure to review content, align reviews with Google's reviews system or FTC affiliate disclosure expectations, or decide when Review and Product schema are honest to use. Triggers on product review, buying guide, best-of list, review methodology, evidence basis, hands-on testing, we tested, affiliate review site, review disclosure, methodology block, original research, reviews system. Also triggers when review content claims testing that did not happen, or when an affiliate site needs a trust mechanism that survives scrutiny.TestingNo warnings★ 1K↓ —
- second-brain-quizundefined-ui/second-brain-osGenerate questions from the user's own concept pages so they can find out what they saved but never learned, and compare their answers against what the pages say. Use this skill when the user wants to test themselves, revise, make flashcards from their notes, or asks what they have forgotten. Do NOT use for generic quizzing on a topic the vault does not cover, or for answering a question from the vault.TestingNo warnings★ 1.4K↓ —
- cloudbase-mcpTencentCloudBase/CloudBase-AI-ToolkitCloudBase MCP reference. Use when connecting local or remote MCP, calling tools from the shell with mcporter, reading tool schemas, choosing the domestic or international endpoint, setting site, region, cloud mode, or plugin flags, or contributing a fix to the open-source MCP server, skills, or CLI.EngineeringNo warnings★ 1.2K↓ —Also in 5 other repos
- video-genUpdatedChatCut-Inc/agent-pluginAI video generation via Seedance, Kling, Gemini Omni, MiniMax H3, and MiniMax H3 Max. Use when the user wants to generate a video clip — text-to-video, image-to-video, first/last-frame transitions, reference-guided generation — or wants to modify / edit / extend an existing generated clip.MediaNo warnings★ 1K↓ —
- work-with-creators-creator-discoverygooseworks-ai/goose-skillsStep of the work-with-creators playbook: builds and screens a long list of creators from fans, category creators and search, and ranks finalists to vet next. Run work-with-creators instead; not for direct use.OtherNo warnings★ 1.3K↓ —
- learn-my-brandgooseworks-ai/goose-skillsLearn my brand once and stop asking me every time. Use when someone says learn my brand, set up my brand, here's our brand book, remember how we talk, what can we claim, can we say this, approve our claims, sign off our voice, our price or product changed, the client approved the claims, pick up where we left off, or check our claims are still current. Reads what GooseWorks already found about the brand, asks only the gaps as drafts to confirm, audits every claim (including ones research marked approved) and gets the ones that matter signed off with proof, scope and review date, turns the voice into rules the owner confirms, checks logo, colours and fonts, and saves it all as it goes so every other job loads it instead of asking. Ends with an unknowns list and a read-back. Not for who our customers are and what they say (use research-audience) or writing positioning from scratch (not covered yet).ScienceNo warnings★ 1.3K↓ —
- grantsalirezarezvani/claude-skillsUse for any NIH funding question ('find grants for my research', 'which NIH institute'). Maps the idea to institutes, study sections and NOSIs via RePORTER, matches mechanisms with mechanism_matcher.py and writes a .docx strategy. NIH only.DocumentsNo warnings★ 29.3K↓ —
- oma-qafirst-fluke/oh-my-agentReview changes for correctness, security, accessibility, and performance. Use for scoped quality reviews or verification plans; bug fixes use oma-debug.TestingNo warnings★ 1.4K↓ —
- oma-recapUpdatedfirst-fluke/oh-my-agentSummarize AI conversation histories for a specified date or period. Use for daily work recaps and cross-tool activity summaries.PlanningNo warnings★ 1.4K↓ —Also in 3 other repos
- 02-ref-hallucination-arenaagentscope-ai/OpenJudgeBenchmark LLM reference recommendation capabilities by verifying every cited paper against Crossref, PubMed, arXiv, and DBLP. Measures hallucination rate, per-field accuracy (title/author/year/DOI), discipline breakdown, and year constraint compliance. Supports tool-augmented (ReAct + web search) mode. Use when the user asks to evaluate, benchmark, or compare models on academic reference hallucination, literature recommendation quality, or citation accuracy.ScienceNo warnings★ 1.1K↓ —
- taste-skillhuytieu/COG-second-brainAnti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.DesignNo warnings★ 1.3K↓ —Also in 1 other repo
- wrap-upalirezarezvani/claude-skillsUse when closing out a launched managed agent ('wrap up', 'what do I own now'). Inventories primitives with primitives_inventory.py, regenerates the overview with overview_page.py and suggests next upgrades with upgrade_suggester.py.OtherNo warnings★ 29.3K↓ —
port
hashgraph-online/awesome-codex-plugins
TestingUpdated 15 hours ago
From the author
Make an existing single-player web game multiplayer in a Homie studio. Reads the game (loop, input, state, camera), grades the port easy, medium, hard or not a fit and says why, adds netplay public rooms (bots in empty seats, join in progress, server rules, predicted movement, rounds), phone touch controls, a stable camera and the big-screen view, proves it with the owner tests (held and alternating directions, real touch on iPhone WebKit and Android Chrome, a late joiner, a departing first player, two fresh browsers finishing a round), then publishes only when requested. Use when someone says "make this multiplayer", "make my game multiplayer on Homie", "port this game to my studio", or points at a single-player web game.
Install
npx skills add hashgraph-online/awesome-codex-plugins --skill port -a claude-code
Installs to .claude/skills/port/ · 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 onlyUses the networkLicence: APACHE-2.0
Safety checks on SKILL.md
No warnings.
Why 88
Security100
Provenance78
Maintenance100
Licence100
Adoption51
Files (5)
- SKILL.md
- references/CHECKS.md
- references/LESSONS.md
- references/PORT-TEMPLATE.md
- references/RECIPE.md