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.
49,109 skills from 2,358 repositories · updated 16 minutes ago
48,059 skills
- content-repurposingScrapeCreators/social-media-research-skillsUse when the user wants to turn public social videos, transcripts, posts, or creator research into reusable content assets such as LinkedIn posts, X threads, short-form scripts, newsletters, blog outlines, carousels, or content calendars.ScienceNo warnings★ 5.3K↓ —
- bank-fee-refundmohitagw15856/pm-claude-skillsGet a bank fee waived or refunded — overdraft, late, maintenance, ATM, or foreign-transaction — with the ask written and the leverage that works. Use when asked to get a bank fee refunded, waive my overdraft fee, the bank charged me a fee, or how to get charges reversed. Produces a read on which fees are commonly reversible, the script to request a refund (in person, chat, or call), the loyalty/first-time/error leverage to use, and how to prevent the fee recurring — plus when to escalate or switch banks.WritingNo warnings★ 1.5K↓ —
- itcs-workflowbrycewang-stanford/Awesome-Journal-SkillsUse to plan an ITCS campaign end to end on its single annual cycle — backward from the early-September deadline through the no-rebuttal review, the November notification, the LIPIcs camera-ready, and the January conference with its Graduating Bits session.ProductivityNo warnings★ 1.4K↓ —
- acl-review-processbrycewang-stanford/Awesome-Journal-SkillsUse when reasoning about how an ACL paper travels through ACL Rolling Review and conference commitment, covering reviewer and area-chair roles, meta-reviews, the commitment decision by senior area chairs and program chairs, Findings versus main-conference outcomes, ethics review escalation, and resubmission strategy across cycles.EngineeringNo warnings★ 1.4K↓ —
- vis-workflowbrycewang-stanford/Awesome-Journal-SkillsUse when planning an IEEE VIS project timeline from area fit through the abstract and full-paper deadlines, the two-phase review, the conditional-accept second round, the IEEE TVCG camera-ready, the Graphics Replicability Stamp, and presentation, with backward-planning offsets for a visualization paper and honest handling of the annual cycle and the second-round revision window.ProductivityNo warnings★ 1.4K↓ —
- ad-library-teardownScrapeCreators/social-media-research-skillsUse when the user wants to analyze active ads from Meta/Facebook, Google, or LinkedIn ad libraries; tear down a competitor's messaging; extract hooks, offers, CTAs, video transcripts, landing page claims, and test ideas from public ads.MarketingNo warnings★ 5.3K↓ —
- unity-agent-workflowshashgraph-online/awesome-codex-pluginsUse for AI-assisted Unity work that needs live repo discovery, project-derived routing, runtime-owner proof, runtime-visible output hard stops, runtime numeric proof for repeated visible-output failures, state-step guards, multi-agent scope ownership, modular C#/asmdef safety, UI/scene/visual asset gates, data-first content changes, validation, cleanup proof, or durable workflow rules. Best when agents must prove the actual folder/module/scene/prefab/runtime owner before editing, especially runtime UI, generated assets, code graphs, tutorial/state flows, guided selection/action flows, overlay/dim source-bound mistakes, coordinate conversions, focus/highlight/marker/HUD alignment, predictive lead aiming, ballistic trajectories, spatial IoU verification, or repeated "fix still not visible" failures.DesignNo warnings★ 1.5K↓ —
- pnas-figuresbrycewang-stanford/Awesome-Journal-SkillsUse to finalize PNAS display items — column-width sizing (~9 / 11.4 / 18 cm), minimum font sizes, show-the-data with n and defined error bars, scale bars, colorblind-safe palettes, legend structure, image integrity, and color-mode notes. Enforces figure rigor before submission.MediaNo warnings★ 1.4K↓ —
- lancet-fitbrycewang-stanford/Awesome-Journal-SkillsUse when scoping a project and before any writing, to stress-test whether a study clears The Lancet's bar — clinically or public-health important, globally relevant, and likely to change practice or policy, often with an equity lens. Decides The Lancet vs a Lancet family title vs another general medical journal.TestingNo warnings★ 1.4K↓ —
- test-mac-appdaveebbelaar/bamaTest a macOS app at three levels, from Swift Testing unit tests and an in-app self-test to a debug bridge that lets an agent drive the running app and read its state, plus computer use for real clicks. Use when adding logic, fixing a bug, before a release, or when the user asks for tests, end-to-end checks, or "make sure it works".TestingNo warnings★ 1.4K↓ —
- improve-loopdaveebbelaar/bamaAutonomous loop that works through docs/STORIES.md one story at a time for a macOS app, building, snapshotting, comparing against reference screenshots, fixing, and committing, until a milestone is done. Use when the user says "keep going", "work through the backlog", "make it match the reference", or wants an unattended improvement loop.OtherNo warnings★ 1.4K↓ —
- scenario-storyboardsscenario-labs/skillsUse when a story must unfold across a sequence of Scenario images: a comic page or strip, manga or webtoon panels, a children's storybook, a film, game, or ad storyboard, animatic pre-viz frames, or any shot list where the same characters and world must persist from panel to panel and dialogue must stay legible. Keywords: storyboard, comic, panel, sequential art, storybook, shot list, pre-viz, animatic, scene to scene, character consistency.MarketingNo warnings★ 1.5K↓ —
- scenario-refine-loopscenario-labs/skillsUse when a Scenario output must be checked and improved rather than accepted first roll: iterating a generation until it matches the brief, fixing a batch that came back off-brief, retrying failed shots methodically, wiring an automated generate, review, revise loop, or deciding whether to re-prompt, swap references, inpaint, post-process, or change model. Keywords: refine, iterate, critique, review loop, QA, self-correction, verify, acceptance criteria, retry, drift.TestingNo warnings★ 1.5K↓ —
- error-propagationhoangsonww/Claude-Code-Agent-MonitorTrace error propagation through a multi-agent session by agent depth — where failures originated, the depth at which they appeared, and how they cascaded up to parent agents — using the Agent Monitor workflow intelligence API and the session event stream. Use when a multi-agent run failed and you need to find the origin and blast radius of the failure.EngineeringNo warnings★ 1.1K↓ —
- setupfcakyon/claude-codex-settingsThis skill should be used when the user asks to "set up paper search", reports "paper-search command not found", wants to "replace paper search MCP", or needs help with paper search credentials.ScienceNo warnings★ 1.2K↓ —
- gohashgraph-online/awesome-codex-pluginsCarry out the intent approved in `ready`, as meant, and prove it with checks that actually ran. Comes back to you if the work would change what you approved, keeps the project docs in step, and never merges on its own. Use when the user invokes the `go` skill after `ready`. Requires git.EngineeringNo warnings★ 1.5K↓ —Also in 3 other repos
- chi-review-processbrycewang-stanford/Awesome-Journal-SkillsUse when interpreting the ACM CHI Papers review pipeline — 1AC and 2AC roles, the A/ARR/RR/RRX/X recommendation scale, desk-reject and rubric-based assisted desk-reject screening, the revise-and-resubmit threshold, round-2 PC decisions — and what each stage means for authors.EngineeringNo warnings★ 1.4K↓ —
- app-icondaveebbelaar/bamaLiquid Glass macOS app icon made as an Icon Composer file (Icon/AppIcon.icon, JSON plus SVG layers), compiled with actool, and reviewed in every look with ictool. Use when the user wants an app icon, a better icon, or a Dock icon.OtherNo warnings★ 1.4K↓ —
- oma-frontendNewfirst-fluke/oh-my-agentImplement or modify web UI in React, Next.js, or Angular. Use for components, pages, styles, forms, and frontend state or data flows.DesignNo warnings★ 1.4K↓ —
- tone-fixermohitagw15856/pm-claude-skillsRewrite a message to the tone you actually want — less harsh, more confident, warmer, firmer, or shorter — without losing your point. Use when asked to make this sound less rude, soften this email, make me sound more confident, make this nicer/firmer, or fix the tone of a message. Produces two or three rewrites at the target tone, a note on exactly what was changed and why, and a flag if the original's tone was fine as-is.WritingNo warnings★ 1.5K↓ —
- cis-controlsSushegaad/Claude-Skills-Governance-Risk-and-ComplianceExpert CIS Controls v8 (CIS Top 18) advisor — implementation group scoping (IG1/IG2/IG3), control gap assessments, safeguard-level guidance, asset inventory, software inventory, data protection, secure configuration, account management, access control, continuous vulnerability management, audit log management, email and web browser protections, malware defenses, network infrastructure management, network monitoring and defense, application software security, incident response, penetration testing, and CIS Controls mapping to NIST CSF, ISO 27001, SOC 2, and CMMC. Use for any question about CIS Controls, CIS Benchmarks, Implementation Groups, or prioritized cyber hygiene for any organization size.SecurityNo warnings★ 1K↓ —
- skill-inventoryhoangsonww/Claude-Code-Agent-MonitorInventory the installed skills and which plugins contribute them, then flag overlap with the user's own skills — read through the Agent Monitor Config Explorer API. Reads /api/cc-config/skills and /api/cc-config/plugins. Use when managing skills: deduping, deciding what to keep, or tracing a skill back to the plugin that ships it.EngineeringNo warnings★ 1.1K↓ —
- launch-postmohitagw15856/pm-claude-skillsWrite a developer-audience launch post — Show HN, a Product Hunt blurb, a 'we shipped X' dev blog intro, or a launch tweet thread. Use when launching a tool, library, API, or open-source project to a technical audience. Produces a credible, hype-free post that leads with what it does and why it's different, plus title options and a comment-ready first reply.WritingNo warnings★ 1.5K↓ —
- cost-breakdownhoangsonww/Claude-Code-Agent-MonitorBreak down Claude Code costs using the Agent Monitor pricing engine. Shows per-model costs (input, output, cache_read, cache_write at $/Mtok rates), per-session costs, daily trends, and compaction baseline token recovery. Use when analyzing spending, comparing model costs, or planning budgets.PlanningNo warnings★ 1.1K↓ —
02-rl-reward
agentscope-ai/OpenJudge
ProductivityUpdated 6 hours ago
From the author
Build 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.
Install
npx skills add agentscope-ai/OpenJudge --skill 02-rl-reward -a claude-code
Installs to .claude/skills/02-rl-reward/ · 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
Provenance76
Maintenance100
Licence100
Adoption49
Files (3)
- SKILL.md
- pairwise.md
- pointwise.md