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 7 hours ago
48,451 skills
- iros-experimentsbrycewang-stanford/Awesome-Journal-SkillsUse when designing or auditing IROS experiments — real-robot trial counts, success criteria set in advance, reset procedures, failure taxonomies, baseline fairness on matched hardware, sim-to-real gap reporting, small-n statistics, and the claim-to-evidence ladder that embodied-systems reviewers apply before they trust a demo.OtherNo warnings★ 1.4K↓ —
- podc-experimentsbrycewang-stanford/Awesome-Journal-SkillsUse when building the evidence for an ACM PODC paper — where "evidence" is a proof, not a benchmark. Covers matching upper and lower bounds, tightness arguments, model and assumption stress-tests, adversary-strength calibration, and the honest, clearly-optional role of any simulation in a distributed-computing-theory paper.TestingNo warnings★ 1.4K↓ —
- tiktok-shop-videoNewhashgraph-online/awesome-codex-pluginsTurn a product link into a TikTok Shop video that sells and stays compliant. Writes the script and shot list for a shoppable or affiliate video in TikTok Shop's own styles (personal review, before & after, unboxing, tutorial, problem and fix in one clip), with the product visible from the first frame, one specific number in the demo and a cart CTA, and enforces the 2025–2026 Shop rules that kill reach and accounts: a real person on screen, no AI voice as the presenter, no still-image slideshows (at least 3 s of moving footage), no price or deal that differs from the product page, no exaggerated claims or weight before/after, commercial sounds only, no near-duplicate reposts. Uses AI only for b-roll and product shots. Use when someone makes TikTok Shop videos as a seller or affiliate, asks why Shop videos stall at 200 views or got a violation, or wants Shop content plans. NOT for paid TikTok or Meta ads with AI actors (use ai-ugc-ad-video) or for editing existing footage (use ecommerce-video-edit).MediaNo warnings★ 1.5K↓ —
- context-auditundefined-ui/second-brain-osAudit an agent's context layout against the four places: system prompt, tools, history, tail. Use when the user asks to audit, review or fix their agent's context, prompt caching, token spend per turn, or CLAUDE.md / AGENTS.md layout. Read-only: reports findings and a fix list, changes nothing. Do NOT use for writing evals (evals-bootstrap) or for loop design (goal-test).ProductivityNo warnings★ 1.3K↓ —
- gate-checkundefined-ui/second-brain-osFind the decisions in a pipeline that do not need the expensive model and propose the gate for each: a rule, a classic classifier, or a small model, with fail-closed routing. Use when the user asks to cut model costs or latency, says the big model handles everything, or wants a triage / routing / filter layer in front of an agent. Analysis plus an optional baseline scaffold. Do NOT use for auditing context layout (context-audit) or for building eval suites (evals-bootstrap).ProductivityNo warnings★ 1.3K↓ —
- second-brain-changed-my-mindundefined-ui/second-brain-osTrace where the user's recorded position on something has shifted: superseded claims, contradictions between sources of different dates, and what evidence moved them. Use this skill when the user asks what they have changed their mind about, how their thinking on a topic developed, what they used to believe, or wants a quarterly look back at their own positions. Do NOT use for finding contradictions between sources with no time dimension, or for a current-state answer.OtherNo warnings★ 1.3K↓ —
- second-brain-transcriptundefined-ui/second-brain-osClean a raw transcript before ingestion: punctuate, paragraph, label speakers, fix mistranscribed technical terms, and split long recordings by topic. Use this skill when the user drops an auto-generated transcript, subtitle file, podcast or lecture transcript, meeting recording text, or asks to process a video or audio source. Do NOT use for text that is already prose, for summarising a transcript, or for the ingestion itself.MediaNo warnings★ 1.3K↓ —
- icml-experimentsbrycewang-stanford/Awesome-Journal-SkillsUse when stress-testing ICML experimental evidence before submission or rebuttal, including strong tuned baselines, mechanism-isolating ablations, seed variance and confidence intervals, compute disclosure, data leakage and split construction, reproducibility, negative results, and fit to ICML soundness, originality, and significance scoring.TestingNo warnings★ 1.4K↓ —
- work-with-creators-brief-writergooseworks-ai/goose-skillsWrites a one-page brief for one creator you have already picked: hook ideas in their format, at most three approved must-say lines, never-says, the disclosure for their platform, deliverables, timeline, the usage-rights ask and two examples. Adds a short first-message draft (gift and paid versions) for you to send. Use alone when you already have the creator, their best fitting post and the goal; otherwise run work-with-creators.WritingNo warnings★ 1.3K↓ —
- run-organic-social-post-checkgooseworks-ai/goose-skillsChecks a draft social post before it goes out: voice match against the account, would a person actually post it, AI-sounding phrases, claims against what the brand has signed off, banned words, disclosure and rights, trend timing, and whether a named person must approve it; rewrites weak drafts. Use alone when you already have the draft, the brand's voice and approved claims; otherwise run run-organic-social.OtherNo warnings★ 1.3K↓ —
- dac-supplementarybrycewang-stanford/Awesome-Journal-SkillsUse when deciding what belongs inside the six reviewed pages of an ACM/IEEE Design Automation Conference (DAC) Research Manuscript versus in an external repository, given DAC's tight 6+1 budget, its references-only seventh page, the double-blind constraint on any linked material, and the absence of a formal reviewed-appendix or artifact-badging track.DesignNo warnings★ 1.4K↓ —
- second-brain-publishundefined-ui/second-brain-osPrepare a subset of the vault for publishing: check opt-in flags, find private material, and report what would leak through links before anything is exported. Use this skill when the user wants to publish notes as a site or digital garden, asks what is safe to make public, or is setting up an export. Do NOT use for exporting a single document, or for running the publishing tool itself.ProductivityNo warnings★ 1.3K↓ —
- 00-academic-routeragentscope-ai/OpenJudgeUse when the user wants help with academic papers or citations but it's unclear which specific workflow fits — reviewing a paper, checking a BibTeX file for fake references, or benchmarking multiple LLMs on reference-recommendation accuracy. Also use when the user mentions paper review, peer review, BibTeX verification, citation checking, reference hallucination, or academic literature accuracy and hasn't specified which of those three tasks they mean. This skill is the entry router for the academic-eval suite: it asks one diagnostic question then routes to the right sub-skill.ScienceNo warnings★ 1K↓ —
- analyze-performancegooseworks-ai/goose-skillsWeekly performance read across every channel we run: what worked, why, and what to make next, judged on the business's real number (store revenue, qualified pipeline, retained users), not platform claims. Use when: write my Monday report; how are my ads doing — which ad won?; are my ads actually making money (Meta says 4x ROAS but revenue is flat); why did sales drop this week; did the test win; is my tracking working; monthly numbers for the replan; anything on fire today. Not for acting on the recommendations (pausing, scaling, launching) — use run-paid-campaigns; not for replanning the budget — use plan-campaign.TestingNo warnings★ 1.3K↓ —
- ui-designUpdatedTencentCloudBase/CloudBase-AI-ToolkitUse when users need visual direction, interface hierarchy, layout decisions, design specifications, or prototypes before implementing a Web or mini program UI.DesignNo warnings★ 1.2K↓ —Also in 5 other repos
- section-508Sushegaad/Claude-Skills-Governance-Risk-and-ComplianceExpert Section 508 compliance advisor for US federal ICT accessibility. Use this skill whenever a user asks about Section 508, WCAG 2.0/2.1 AA for federal systems, VPAT or Accessibility Conformance Reports (ACR), accessibility audits, remediation planning, PDF accessibility, web or software accessibility, mobile accessibility, federal procurement accessibility requirements, contractor obligations, undue burden exceptions, assistive technology compatibility, or Section 508 testing. Covers the Revised Section 508 Standards (2018), all WCAG 2.0 Level AA success criteria, the four POUR principles, testing methodologies, and agency compliance workflows. Trigger even if the user doesn't say "skill" — any Section 508 or ICT accessibility question for federal systems should use this skill.TestingNo warnings★ 1K↓ —
- iso27001Sushegaad/Claude-Skills-Governance-Risk-and-ComplianceExpert ISO 27001 compliance assistant for security and compliance teams. Use this skill whenever a user asks about ISO 27001 or ISO/IEC 27001, including any of the following: gap analysis, auditing, compliance assessments, control checklists, policy writing, document generation, Statement of Applicability (SoA), risk assessment, risk registers, risk treatment plans, Annex A controls, ISMS implementation, clause requirements, certification readiness, transitioning from 2013 to 2022, control implementation guidance, incident response policies, access control policies, supplier security, or any information security management system (ISMS) topic. Trigger even if the user doesn't say "skill" — any ISO 27001 or ISMS question should use this skill.SecurityNo warnings★ 1K↓ —
- metric-designagentscope-ai/OpenJudgeUse when the user has evaluation principles or a dataset but needs help choosing the right graders, designing evaluation metrics, creating LLM-as-judge prompts, combining multiple metrics into a composite score, or building an automated evaluation pipeline. Also use when the user mentions grader selection, metric design, judge prompt engineering, rubric design, evaluation pipeline code, or "how to evaluate [X] automatically." Outputs executable OpenJudge pipeline code.DesignNo warnings★ 1K↓ —
- eu-ai-actSushegaad/Claude-Skills-Governance-Risk-and-ComplianceEU AI Act (Regulation (EU) 2024/1689) compliance advisor — risk classification across all four tiers, all 9 prohibited practices (Art. 5, including the nudification/CSAM prohibition from Dec 2, 2026), all 8 Annex III high-risk use case areas, provider and deployer obligations (Arts. 9–17, 26), GPAI model obligations including the July 2025 Code of Practice (Arts. 51–55), conformity assessment and CE marking (Arts. 43–48), EU AI database registration, Art. 50 transparency (chatbots, synthetic media, AI-generated content), governance (AI Office, AI Board), penalties (Art. 99), confirmed phase-in timeline (Digital Omnibus, Reg. (EU) 2026/1744, in force July 27, 2026: Annex III deferred to Dec 2, 2027; Annex I to Aug 2, 2028), and cross-framework mapping to ISO 42001, NIST AI RMF, and GDPR. Use for any EU AI regulation, AI system classification, or AI compliance question. Current as of August 2026. GPAI enforcement powers active since August 2, 2026.DevOpsNo warnings★ 1K↓ —
- 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★ 1K↓ —
- comparetaishi-i/awesome-japanese-nlp-resourcesCompare several Japanese NLP libraries, models, or datasets for a keyword (a specific tool name, or a function/task like '形態素解析') across a handful of criteria chosen for that comparison, rendered as a ○/△/✕ table. Use when the user wants a side-by-side comparison of multiple Japanese NLP tools/libraries/datasets, not just the single best one. Trigger phrases include 'X と Y と Z を比較して', '形態素解析ライブラリを比較', 'MeCab と Sudachi どっちがいい', 'どのツールを使うべき', 'compare japanese tokenizers', 'mecab vs sudachi vs janome', 'which embedding model should I use', '日本語NERライブラリの比較表', 'pros and cons of japanese OCR tools'. For a single ranked list use search; for alternatives to one specific tool (or contribution candidates) without a multi-axis table, use discover.MediaNo warnings★ 1K↓ —
- discovertaishi-i/awesome-japanese-nlp-resourcesGiven a Japanese NLP GitHub repo/model/dataset (URL / owner/repo / tool name) OR a topic, find what's already in awesome-japanese-nlp-resources and discover related resources NOT yet listed (contribution candidates). Mines the bundled dataset, then expands via web research across GitHub and Hugging Face. Use when the user names a SPECIFIC repository, model, or tool and wants alternatives/equivalents, OR wants to discover Japanese NLP resources for a topic that are NOT yet in the list, OR wants to prepare a contribution. Trigger phrases include 'mecabに似たツール', 'fugashiの代替', 'alternatives to fugashi', 'repos like manga-ocr', 'what else is like sudachi', 'リストに無い新しい日本語NLP', 'awesome-japanese-nlpに追加できそうな', '最近公開された日本語NLPツール', 'find unlisted Japanese NLP repos', 'new Japanese models on Hugging Face', 'contribute a new resource'. For a simple lookup of what already exists, use the search skill instead.ScienceNo warnings★ 1K↓ —
- meta-evalagentscope-ai/OpenJudgeUse when the user wants to build an evaluation system for an LLM/agent application but doesn't know where to start — they have traces, prompts, RAG pipelines, or nothing at all. Also use when the user mentions evaluation, eval, benchmarking, testing LLM quality, measuring agent performance, assessing RAG accuracy, or wants to compare prompts/models. This skill is the entry router: it asks diagnostic questions then recommends which sub-skill (local workflow) to use next.TestingNo warnings★ 1K↓ —
- researchtaishi-i/awesome-japanese-nlp-resourcesAnalyze current trends and challenges in Japanese NLP for a topic. Surveys the existing awesome-japanese-nlp-resources dataset and augments it with up-to-the-minute web research to produce a combined trend + issue report. Use only when the user explicitly wants a trend/landscape report, a challenges/limitations report, or a general research overview of a Japanese NLP topic (this combines the bundled dataset with live web research). Trigger phrases include '日本語LLMの最新トレンド', '〜の動向をまとめて', '最近の日本語NLPの流れ', '日本語LLMの課題', '〜の問題点・限界', '未解決の論点', 'trend report on Japanese embeddings', 'latest Japanese speech models', 'challenges in Japanese NER', 'limitations of Japanese embeddings'. For a simple lookup use the search skill; this one runs web research.ScienceNo warnings★ 1K↓ —
pnas-writing
brycewang-stanford/Awesome-Journal-Skills
WritingUpdated Sep 27, 2026
From the author
Use to structure a PNAS main text and hold its length — Title, Significance Statement, Abstract, Introduction, Results, Discussion, in-text Materials and Methods, references — and to choose the required Classification (Biological/Physical/Social Sciences + minor subject) and keywords at submission.
Install
npx skills add brycewang-stanford/Awesome-Journal-Skills --skill pnas-writing -a claude-code
Installs to .claude/skills/pnas-writing/ · 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
Adoption50
Files (1)
- SKILL.md