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.
45,604 skills from 2,205 repositories · updated 10 hours ago
5,657 skills
- assessment-sequence-governancezero-lab-ai/skillsValidates supplied immutable ordered manifests of opaque defensive assessment actions for authority, safeguards, evidence, and separate-operator review. Use when reviewing assessment sequencing without creating, changing, or executing actions.EngineeringNo warnings★ 282↓ —
- r-performancebrycewang-stanford/Auto-Empirical-Research-SkillsR performance best practices including profiling, benchmarking, vctrs, and optimization strategies. Use when optimizing R code.EngineeringNo warnings★ 4.8K↓ —
- action-list-reviewxiaomoBoy/pi-bluebook把会议记录整理为可核对的行动清单;当任务要求提取负责人、截止日期、交付物和限制时使用。EngineeringNo warnings★ 327↓ —
- reviewbrycewang-stanford/Auto-Empirical-Research-SkillsAll quality reviews — routes to appropriate critics based on target file type and flags. Replaces /paper-excellence, /proofread, /econometrics-check, /review-r, /review-paper.EngineeringNo warnings★ 4.8K↓ —
- nxMindrally/skillsBest practices for Nx monorepo development, project configuration, and code generationEngineeringNo warnings★ 286↓ —
- dataset-integrity-assessmentzero-lab-ai/skillsAudits dataset sources, labels, transformations, review, versioning, split integrity, retraining triggers, and rollback controls for poisoning and targeted degradation risk. Use when reviewing an ML training or evaluation data supply chain.EngineeringNo warnings★ 282↓ —
- skilldskilld-dev/skilldOperate skilld CLI for Skill discovery, use, installation, inspection, updates, authentication, configuration, restoration, and removal, including Repository, curator, and collection refs. Also read the skilld.dev registry (view, browse, trending, tracks, curators, index) and act for the user's skilld.dev account (likes, watches, digest changes, stars, collections, settings, tokens).EngineeringNo warnings★ 327↓ —
- daily-codingbrycewang-stanford/Auto-Empirical-Research-SkillsUse for everyday coding tasks that involve writing or modifying source code.EngineeringNo warnings★ 4.8K↓ —
- null-safetyrrezartprebreza/spring-boot-skillsUse when annotating nullability in Spring Boot 3 / Spring Framework 6 code, integrating Kotlin, or adding static nullability checks without assuming Spring Framework 7 JSpecify defaults.EngineeringNo warnings★ 325↓ —
- markdown-unwrapbrycewang-stanford/Auto-Empirical-Research-SkillsUnwraps hard-wrapped markdown files so that each sentence ends with a newline instead of mid-sentence line breaks. Joins continuation lines within a paragraph into single lines, then re-breaks at sentence boundaries (period, question mark, exclamation point). Preserves blank lines, headings, fenced code blocks, block quotes, and list items. Use when asked to unwrap text, fix line breaks, reflow sentences, or clean up hard-wrapped markdown or .qmd files.EngineeringNo warnings★ 4.8K↓ —
- master-thesis-reviewbrycewang-stanford/Auto-Empirical-Research-SkillsGenerate master's thesis review reports (硕士论文评阅意见) calibrated to a given score. Outputs academic evaluation and shortcomings/suggestions in Chinese. Trigger when user says "master thesis review" / "硕士论文评阅" / "论文评阅" / "评阅意见" / "thesis review".EngineeringNo warnings★ 4.8K↓ —
- review-skillskilld-dev/skilldReview an Agent Skill for valid structure, clear triggers, usable instructions, current evidence, and risky or unclear actions.EngineeringNo warnings★ 327↓ —
- API FuzzingPramodDutta/qaskillsAPI endpoint fuzzing for discovering unexpected behaviors, crashes, and security vulnerabilities through malformed requests, boundary values, and protocol violations.EngineeringNo warnings★ 240↓ —
- idea-discovery-robotbrycewang-stanford/Auto-Empirical-Research-SkillsWorkflow 1 adaptation for robotics and embodied AI. Orchestrates robotics-aware literature survey, idea generation, novelty check, and critical review to go from a broad robotics direction to benchmark-grounded, simulation-first ideas. Use when user says "robotics idea discovery", "机器人找idea", "embodied AI idea", "机器人方向探索", "sim2real 选题", or wants ideas for manipulation, locomotion, navigation, drones, humanoids, or general robot learning.EngineeringNo warnings★ 4.8K↓ —
- auto-review-loop-llmbrycewang-stanford/Auto-Empirical-Research-SkillsAutonomous research review loop using any OpenAI-compatible LLM API. Configure via llm-chat MCP server or environment variables. Trigger with "auto review loop llm" or "llm review".EngineeringNo warnings★ 4.8K↓ —
- unpaywall-apibrycewang-stanford/Auto-Empirical-Research-SkillsFind free legal full-text versions of scholarly articles via UnpaywallEngineeringNo warnings★ 4.8K↓ —
- coding-guidelinesbrycewang-stanford/Auto-Empirical-Research-SkillsStandardized Python & Stata coding practices for empirical research projectsEngineeringNo warnings★ 4.8K↓ —
- artifact-lookupjmagly/aiwgSearch and navigate SDLC artifacts by topic, type, phase, or tag using the aiwg index CLIEngineeringNo warnings★ 225↓ —
- anywritelingxling/awesome-skills-cnCompiled CLI covering all 52 endpoints of the Anytype local API — objects, properties, tags, search, chat, files — one binary, no MCP server needed.EngineeringNo warnings★ 321↓ —
- auto-review-loopbrycewang-stanford/Auto-Empirical-Research-SkillsAutonomous multi-round research review loop. Repeatedly reviews via Codex MCP, implements fixes, and re-reviews until positive assessment or max rounds reached. Use when user says "auto review loop", "review until it passes", or wants autonomous iterative improvement.EngineeringNo warnings★ 4.8K↓ —
- data-cleaningbrycewang-stanford/Auto-Empirical-Research-SkillsClean and transform messy data for analysis in Python, R, or StataEngineeringNo warnings★ 4.8K↓ —
- action-list-reviewxiaomoBoy/pi-bluebook把會議記錄整理為可核對的行動清單;當任務要求提取負責人、截止日期、交付物和限制時使用。EngineeringNo warnings★ 327↓ —
- speaker-idBlackBeltTechnology/pi-agent-dashboardName anonymous diarized SRT speakers from a persistent local voiceprint library and repair speaker drift; local, CPU-only, no API key. Triggers "who is speaker 2", "put names on the transcript", "label the meeting SRT", "the diarization split one person into three", "enroll my voice". Backed by the pi-voiceid CLI.EngineeringNo warnings★ 331↓ —
- stata-modernizebrycewang-stanford/Auto-Empirical-Research-SkillsImprove, modernize, and optimize existing Stata code for performance, portability, and maintainability. Use when legacy patterns such as preserve/restore, cd,EngineeringNo warnings★ 4.8K↓ —