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.
49,493 skills from 2,407 repositories · updated 33 minutes ago
18,234 skills
- 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↓ —
- ru-texthashgraph-online/awesome-codex-pluginsRussian text quality. Triggers: вычитай, проверь текст, поправь, отредактируй, причеши, ru-text. Typography silently on any Russian output; deeper editing on request. Info-style, editorial, UX writing, business correspondence, AI-text cleanup.DesignNo warnings★ 1.5K↓ —Also in 1 other repo
- local-seokostja94/marketing-skillsWhen the user wants to optimize for local search, set up Google Business Profile, or build local citations. Also use when the user mentions "local SEO," "Google Business Profile," "Google Maps," "NAP," "citations," "local search," "local business," or "service area." For location pages, use programmatic-seo.MarketingNo warnings★ 1.1K↓ —
- threat-modelmohitagw15856/pm-claude-skillsThreat-model a system or feature to find where it could be attacked, before you build it. Use when asked to threat-model, do a security design review, document security risks, identify attack surface, or apply STRIDE to a design. Produces a structured threat model: assets, trust boundaries and data flows, threats enumerated by category (STRIDE), risk scores, prioritized mitigations, and residual-risk sign-off. Defensive security for systems you own or are authorized to assess.SecurityNo warnings★ 1.5K↓ —
- claude-authenticityagentscope-ai/OpenJudgeDetect whether an API endpoint is backed by genuine Claude (not a wrapper, proxy, or impersonator) using 9 weighted rule-based checks that mirror the claude-verify project. Also extracts injected system prompts from providers that override Claude's identity. Fully self-contained — copy the code below and run, no extra packages beyond httpx. Use when the user wants to verify a Claude API key or endpoint, check if a third-party Claude service is authentic, audit API providers for Claude authenticity, test multiple models in parallel, or discover what system prompt a provider has injected.TestingNo warnings★ 1.1K↓ —
- goframe-v2hashgraph-online/awesome-codex-pluginsGoFrame development skill. TRIGGER when writing/modifying Go files, implementing services, creating APIs, or database operations. DO NOT TRIGGER for frontend/shell scripts.DataNo warnings★ 1.5K↓ —
- ship-gatealirezarezvani/claude-skillsUse before deploying or going live ('am I ready to ship', 'can I deploy', 'preflight check'). Scans the codebase with ship_gate_scanner.py across security, database, deploy, AI, dependencies and observability, and blocks on critical items.SecurityNo warnings★ 29.3K↓ —
- claude-apihashgraph-online/awesome-codex-pluginsAnthropic Claude API patterns for Python and TypeScript. Covers Messages API, streaming, tool use, vision, extended thinking, batches, prompt caching, and Claude Agent SDK. Use when building applications with the Claude API or Anthropic SDKs.EngineeringNo warnings★ 1.5K↓ —
- wechat-articlemohitagw15856/pm-claude-skillsWrite a WeChat Official Account (公众号) article: a headline that earns the open, a digest line, a structure built for reading on a phone, and an ending that drives a share or follow, without clickbait the article does not deliver. Use when asked 帮我写公众号文章, 公众号标题, 推文怎么写, 写一篇公众号推送, or write a WeChat article. Produces three headline options, the digest (摘要), the full article with sub-headings and short paragraphs, cover image guidance, a closing call to action, and a check of claims and sources.WritingNo warnings★ 1.5K↓ —
- brainstormingmohitagw15856/pm-claude-skillsRun a real brainstorm — divergent generation without judgment, then convergent selection with explicit criteria — instead of listing ten obvious ideas and calling it creativity. Use when asked to brainstorm, generate ideas or options, explore a solution space, or name something. Produces a genuinely wide option set (including the weird tail), then a shortlist selected against named criteria with the rejects preserved.PlanningNo warnings★ 1.5K↓ —
- company-briefmohitagw15856/pm-claude-skillsBuild a candidate's research brief on a company before an application or interview. Use when asked to research a company for a job, prep a company brief before an interview, or understand a prospective employer fast. Produces a one-page brief — what they do & how they make money, recent news & trajectory, product & competitors, likely challenges, culture signals, and smart questions to ask.ScienceNo warnings★ 1.5K↓ —
- oma-explanationfirst-fluke/oh-my-agentCreate an offline HTML explanation of a code change (diff, PR, branch) or of a topic, system, or question. Use when a visual walkthrough document is requested.EngineeringNo warnings★ 1.4K↓ —Also in 1 other repo
- 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↓ —
- demand-lettermohitagw15856/pm-claude-skillsDraft a firm, professional demand letter that states the facts, the legal/contractual basis, the specific demand, and a deadline. Use when asked to write a demand letter, send a formal demand for payment, draft a cease-and-desist, or formally request resolution before legal action. Produces a structured, factual letter with a clear ask and consequences — assertive but not threatening or defamatory. Not legal advice; have counsel review before sending.LegalNo warnings★ 1.5K↓ —
- entity-seokostja94/marketing-skillsWhen the user wants to optimize for entity recognition, Knowledge Graph, or entity-based SEO. Also use when the user mentions "entity SEO," "entity optimization," "Knowledge Graph," "Knowledge Panel," "entity signals," "brand entity," "entity linking," "entity relationships," or "entity-first content." For structured data, use schema-markup.MarketingNo warnings★ 1.1K↓ —
- red-teamalirezarezvani/claude-skillsUse when planning or running an authorized red team engagement or attack path analysis. Plans the kill chain with engagement_planner.py: MITRE ATT&CK techniques, choke points, OPSEC risk and crown jewels.PlanningNo warnings★ 29.3K↓ —
- oma-scmfirst-fluke/oh-my-agentManage Git branches, merges, conflicts, commits, and release baselines. Use for repository history and change-management operations.EngineeringNo warnings★ 1.4K↓ —
- impact-reportmohitagw15856/pm-claude-skillsWrite a compelling nonprofit impact or annual report that shows donors what their money achieved. Use when asked to write an impact report, an annual report, a grant outcomes report, or to report results to funders/donors. Produces a structured report — mission and year in brief, outcomes with real numbers and a beneficiary story, financials at a glance, and a forward ask — that builds trust and renews giving.FinanceNo warnings★ 1.5K↓ —
- bootstrapagentscope-ai/OpenJudgeUse when the user has nothing — no traces, no labels, no eval set — and needs to build a v0 evaluation from scratch. Also use when the user says "I need to start evaluating my app but don't know where to begin," "I want to set up eval for a new product," or has just identified failure modes and needs to turn them into principles. Outputs a v0 grader in 30 minutes using OpenJudge SimpleRubricsGenerator, plus a roadmap to reach calibrated evaluation.PlanningNo warnings★ 1.1K↓ —
- design-fixhashgraph-online/awesome-codex-pluginsCompare one already-implemented screen or component against its Figma source and fix the deviations you pick -- reads the node live through the figma-bridge MCP, or from the Node Specs of an existing /design plan, then diffs box, layout, typography, fill, stroke, radius, effects, and content against the code that renders it. Reports first, fixes only what you select, and never touches Figma.DesignNo warnings★ 1.5K↓ —
- runhashgraph-online/awesome-codex-pluginsRun a full pipeline for a task. Orchestrates roles through stages (standalone or HOTL-integrated).ProductivityNo warnings★ 1.5K↓ —
- pip-respondermohitagw15856/pm-claude-skillsRespond to a performance improvement plan strategically — decode what the PIP really is, decide fight-vs-land-softly with clear eyes, build the evidence file, and run the parallel job search the situation demands. Use when asked I was just put on a PIP what do I do, help me respond to a performance improvement plan, is my PIP survivable, or write my PIP check-in updates. Produces the honest read of the PIP, the two-track plan (perform + search), the documentation system, and templates for check-ins and the written response.WritingNo warnings★ 1.5K↓ —
- 02-bib-verifyagentscope-ai/OpenJudgeVerify a BibTeX file for hallucinated or fabricated references by cross-checking every entry against CrossRef, arXiv, and DBLP. Reports each reference as verified, suspect, or not found, with field-level mismatch details (title, authors, year, DOI). Use when the user wants to check a .bib file for fake citations, validate references in a paper, or audit bibliography entries for accuracy.ScienceNo warnings★ 1.1K↓ —
- meeting-prepnano-muse/nanoMusePrepare for a meeting (who is in it, what was last said with them, what the user owes them and wants from them) as a one-page brief. Use when the user asks to prepare for or get ready for a meeting, a call or a visit; a trigger can run it before every meeting with a client.OtherNo warnings★ 3.2K↓ —
yolo-training
fcakyon/claude-codex-settings
DataUpdated 6 hours ago
From the author
This skill should be used when user asks to "improve my mAP", "why is my model overfitting", "my training is diverging", "read my results.csv", "interpret my training curves", "my AP50 is good but AP50-95 is bad", "my recall is low", "how do I pick learning rate", "which augmentations should I use", "should I use a bigger model", "tune hyperparameters", or asks how to train YOLO26 for detection, instance or semantic segmentation, pose, OBB, classification, or depth.
Install
npx skills add fcakyon/claude-codex-settings --skill yolo-training -a claude-code
Installs to .claude/skills/yolo-training/ · 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: APACHE-2.0
Safety checks on SKILL.md
No warnings.
Why 88
Security100
Provenance77
Maintenance100
Licence100
Adoption50
Files (3)
- SKILL.md
- references/diagnostics.md
- references/task-notes.md