agentsclimarketplace

The catalog

609,344 rows, by stacks then stars

  • Design skill

    testing-skill/design-skill/skills/design-skill Skill

    no license1★ repo

    Use this skill for beginner designers with a guided, hands-on starter that scaffolds simple design projects (landing page, logo, mobile UI) and actionable checklists to learn the design process.

    The same file is in 1 other repository

  • Otterai cli

    erickhchan/otterai-cli/skills/otterai-cli Skill

    1★ repo

    Use when the user mentions Otter, Otter.ai, or wants to find, search, download, export, or manage meeting notes, transcripts, recordings, or audio from calls, standups, syncs, or interviews.

  • Diagram to vector

    William-Yeh/diagram-to-vector Skill

    1★

    Convert hand-drawn diagrams and whiteboard sketches into structured vector formats. Use when the user wants to convert a tldraw, Excalidraw, Miro, or other whiteboard URL to Mermaid, draw.io, GraphViz, or SVG. Also use when transforming an uploaded screenshot or image of a diagram into editable vector format. Supports batch processing of multiple files.

  • Skill packager

    yaniv-golan/skill-packager-skill/.agents/skills/skill-packager Skill

    1★ repo

    Package AI agent skills into deployment formats — .zip, .skill, Claude plugin, Claude marketplace, Cursor plugin, Cursor marketplace, native Codex/ChatGPT plugin, ChatGPT/Manus zip, Codex CLI, NanoClaw marketplace, OpenClaw/ClawHub, Agent Skills standard (.agents/), or a universal repo with all formats + CI/CD. Use when the user says "package this skill", "deploy my skill", "create a plugin from this skill", "make this work on Cursor/ChatGPT/Codex/NanoClaw/OpenClaw", "set up a repo for my skill", or wants to distribute a SKILL.md to any platform.

  • Minecraft modding workbench

    adhi-jp/agent-skills/skills/minecraft-modding-workbench Skill

    1★ repo

    Workflow-focused agent skills and evaluation suites for software development, skill maintenance, and Minecraft modding.

  • Software engineering docs

    ahernandezmiro/software-engineering-docs/software-engineering-docs Skill

    1★ repo

    Generate and maintain structured software engineering documentation for new or existing applications. Use when asked to create, update, or normalize requirements.md, use_cases.md, specification.md, architecture.md, uml.md, or tests.md from source code and existing docs, and when enforcing consistency and domain boundaries (for example, preventing endpoint-level details in high-level requirements).

  • Conventional commit

    nanocodana/nanocodana/apps/node/skills-project/.claude/skills/conventional-commit Skill

    1★ repo

    Write a git commit message in Conventional Commits + gitmoji style

  • New mcp builder

    shane9coy/katana-agent/agent/skills/agent-tools/new-mcp-builder Skill

    no license1★ repo

    Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

    The same file is in 1 other repository

  • Feishu projects

    chuxubank/skills/feishu-projects Skill

    no license1★ repo

    This skill should be used when the user asks to "查看飞书项目", "查看需求", "查看缺陷", "查看任务", "我的待办", "搜索工作项", "查看视图", "查看空间信息", "查看排期", "查看评论", "查看操作记录", "查看团队", "创建工作项", "修改工作项", "资源库", "交付物", "上传附件", "下载附件", or any request related to Feishu/Lark project management (飞书项目/Meego). Provides workflows for querying, creating, and updating work items using the feishu MCP tools.

  • Skill quality

    skill-tools/skill-tools-plugin/skills/skill-quality Skill

    1★ repo

    Guide for writing high-quality SKILL.md files. Use when creating, improving, or debugging Agent Skills — covers descriptions, instructions, and common pitfalls.

  • Skill creator

    wentallout/write-like-a-human/.agents/skills/skill-creator Skill

    no license1★ repo

    Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

    The same file is in 66 other repositories

  • Agents md improver

    yyykf/spellbook-skills/skills/agents-md-improver Skill

    1★ repo

    Maintain AGENTS.md-based project instructions for tools that support AGENTS.md. Use for instruction audits, session learnings, AGENTS.md updates, or migrating useful CLAUDE.md rules into a shared instruction source. Not for general docs, code review, runtime debugging, or global memory unless asked.

    The same file is in 1 other repository

  • Ai evaluation

    SWEStash/swe-workflow-skills/plugins/ai/skills/ai-evaluation Skill

    1★ repo

    Define how to evaluate ML models and GenAI/LLM apps — golden datasets, offline metrics, RAG evaluation (faithfulness, relevance, context precision/recall) with ragas/deepeval/promptfoo, LLM-as-judge design and calibration, eval regression gates in CI, online A/B and human feedback. Logging/comparing runs → ml-experiment-tracking; building the app → llm-app-engineering; general experiment statistics → statistical-analysis.

  • Generate component

    feel-flow/agent-skills-examples/generation/generate-component Skill

    1★ repo

    プロジェクトの規約に従ったReactコンポーネントを生成する。新規コンポーネントやページの作成時に使用。

  • Master assistant skill

    kjhk3082/master-assistant-skill Skill

    1★

    [EN] You MUST use this skill as the core orchestrator for all tasks. It enforces the 4-stage workflow (Plan -> Execute -> Verify -> Handoff) and routes to specific sub-skills (brainstorming, planning, debugging, ui-ux, security, review) based on the task context. [KO] 모든 작업의 핵심 오케스트레이터로 이 스킬을 반드시 사용해야 합니다. 4단계 워크플로우(계획 -> 실행 -> 검증 -> 핸드오프)를 강제하고 작업 컨텍스트에 따라 특정 하위 스킬로 라우팅합니다.

  • Bower

    indigokarasu/bower Skill

    1★

    Automatic Google Drive organizer. Scans Drive structure and file contents, builds a personalized preference profile, applies domain-specific logic (taxes by year, projects by name, home by system, finance by institution), and executes non-destructive moves, renames, and description writes. Learns organizational style over time and auto-approves consistently accepted patterns. Never deletes files. NOT for web research, document analysis, or Chronicle ingestion.

  • Skill dispatcher

    jovd83/skill-dispatcher Skill

    1★

    High-performance routing engine for AI AgentSkills. Classifies user intent, scans for specialized skills, and generates optimal dispatch decisions (HANDOFF, SEQUENCE, or NO_MATCH). Use this to manage complexity in large skill environments and ensure the best-equipped skill handles every task.

  • Jp design

    mrslbt/jp-web-design-guardrails/skills/jp-design Skill

    1★ repo

    Build Japanese-ready web interfaces with correct CJK typography, cultural UI patterns, and localization best practices. Use this skill whenever building a website, app, or component for the Japanese market, when the UI includes Japanese text (kanji, hiragana, katakana), when adding Japanese language support or i18n/l10n for Japan, when designing forms for Japanese users, when implementing vertical text (tategaki), when working with CJK font loading, or when the user mentions Japanese, Japan, 日本語, nihongo, CJK, kanji, hiragana, katakana, furigana, or any Japanese-specific design requirement. Also trigger when localizing an existing product for Japan, adding a lang="ja" attribute, or handling yen currency formatting.

  • Skill review

    whtsky/skills/.claude/skills/skill-review Skill

    no license1★ repo

    Audit and format SKILL.md files in this repository. You MUST invoke this skill proactively when: (1) adding a new skill, (2) editing an existing SKILL.md, (3) migrating a skill from another source. Also use when explicitly asked to review skill quality or run a batch audit.

  • Goose gui e2e

    Miyamura80/MCP-Template/.agents/skills/goose-gui-e2e Skill

    1★ repo

    Drive the real Goose desktop GUI (Electron) as an MCP client via Playwright to end-to-end test this template's MCP Apps - asserting the ui:// iframe actually renders and round-trips in a real host. Use to run, add, or debug MCP-App e2e scenarios.

  • Avoid ai writing zh

    leoluyi/skills/skills/avoid-ai-writing-zh Skill

    1★ repo

    Audit and rewrite content to remove AI writing patterns ("AI-isms"). Extends the English-only avoid-ai-writing with an added Traditional-Chinese (Taiwan business usage) layer, so it handles English, Traditional Chinese, and mixed zh/en text. Use when asked to "remove AI-isms," "clean up AI writing," 「去除 AI 味」or「把中文改成人話」, or as a de-AI finishing pass before shipping English/mixed software-development docs — README, CONTRIBUTING, ADR, API docs, code comments. Also runs a detect-only structure-signals audit for a draft that carries no obvious AI-isms yet still reads as AI-written — uniform rhythm, no stance, no concrete examples, 「正確但沒有靈魂」— naming what is absent rather than rewriting for voice. It removes and flags AI patterns but does not create a voice — composing a blog or rewriting a draft into a human voice is blog-writing-zh's job, not this skill's.

  • Lammps analysis

    chatmaterials/lammps-analysis Skill

    1★

    Use when the task is to analyze completed or failed LAMMPS simulations, including thermo extraction, run-status interpretation, comparing multiple log.lammps outputs, and summarizing restart or force-field issues from finished runs.

  • Chestertons fence

    calvyntwh/karu-custom-skills/skills/chestertons-fence Skill

    1★ repo

    A safety protocol for refactoring. Do not remove a fence until you know why it was put up. Use when deleting, simplifying, or "fixing" code you do not fully understand.

  • Open api

    lucaducapuca/alibabacloud-bigdata-skills/skills/dataworks/open-api Skill

    1★ repo

    Operate Alibaba Cloud DataWorks through dynamic API discovery and official SDKs (Node.js, Python, Java). Covers data development, workflow operations, data integration, data quality, metadata lineage, workspace management, and more. APIs are discovered at runtime from official docs and OpenAPI metadata — no hardcoded list.

    The same file is in 1 other repository

  • Skill creator

    morzecrew/agent-skills/.agents/skills/skill-creator Skill

    1★ repo

    Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

    The same file is in 66 other repositories

  • Typst touying skill

    statzhero/typst-touying-skill Skill

    no license1★

    Touying slide framework for Typst. Use when creating presentations in Typst, adding slide animations, configuring Touying themes, using pause/meanwhile markers, building multi-file presentations, or integrating CeTZ/Fletcher diagrams with animations. Covers all built-in themes (simple, university, metropolis, aqua, dewdrop, stargazer) and custom theme creation.

  • Claude code environment backup

    gaoguobin/codex-environment-backup/skills/claude-code-environment-backup Skill

    1★ repo

    Claude Code environment backup, restore, doctor, and list workflows for local ~/.claude state. Use for requests like back up Claude Code, restore Claude Code backup, list/check Claude Code backups, or install/update/uninstall the backup skill.

  • Agentic engineering

    Lukk17/agent-standards/.agents/skills/agentic-engineering Skill

    1★ repo

    Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing.

  • Image comprehension ollama

    aosama/image-comprehension-ollama/skills/image-comprehension-ollama Skill

    1★ repo

    If you are a vision enabled model then you do not need this skill. Use this skill to analyze image files on disk via a local vision model (default: moondream:1.8b via Ollama). Invoke it whenever you encounter an image provided as a file path — such as a screenshot, photo, diagram, chart, or scan — and need a text description of its contents. The local model processes the image and returns a description to stdout, supplementing your workflow when images are not directly viewable in chat or when a local analysis is preferred. Supports PNG, JPEG, GIF, WebP, BMP.

  • Data systems trade offs

    chrisVillanueva/ai-skills-registry/data-engineering/data-systems-trade-offs Skill

    no license1★ repo

    [WHAT] Guides the agent through architectural trade-off analysis for data-intensive systems, covering operational vs analytical workloads, cloud vs self-hosted deployment, distributed vs single-node topology, and regulatory compliance constraints. [WHEN] Activate when the user is evaluating data system architecture, choosing between OLTP and OLAP, deciding on cloud vs on-prem, considering whether to distribute a system, or assessing data privacy and compliance requirements. [KEYWORDS] trade-offs, architecture, OLTP, OLAP, data warehouse, cloud-native, self-hosted, distributed systems, single-node, scalability, reliability, maintainability, GDPR, data compliance.

  • Kavach

    SarthiAI/kavach-skill/kavach Skill

    1★ repo

    Add a default-deny execution gate around AI-agent actions in Python or Node / TypeScript using the kavach-sdk library. Use when the user is integrating Kavach, wants to add policy enforcement, drift detection, signed permit tokens, signed audit chains, secure channels, or default-deny request validation, mentions Gate, Guarded, PermitToken, ActionContext, EvaluateOptions, McpKavachMiddleware, guardTool, check_tool_call, evaluate_tool_call, or wants to wrap LangChain, LangGraph, MCP tool calls, Express, Fastify, or any agent tool-call code behind a deny-by-default check. Skip if Kavach is already wired up and the user is debugging unrelated code, or if the user is asking about a different policy engine (OPA, Cerbos, Casbin).

  • Peep

    otiai10/overpeeped/Sources/Overpeeped/Resources/skills/peep Skill

    1★ repo

    overpeeped (デスクトップマスコットアプリ) に Claude Code セッションを登録する。`/peep` でセッションをヒナ化 (`/peep <名前>` で命名しつつ登録)、`/peep status` で状態確認、`/peep stop` で監視終了、`/peep nickname <名前>` で命名/改名。並列に走る複数の Claude Code セッションを忘れずに見守りたいときに使う。

  • 01 data intake

    Lambenthan/empirical-research-pipeline/modules/01-data-intake Skill

    no license1★ repo

    Empirical data intake for raw data triage in econometrics and public-health / epidemiology research. Use when the user has just received a raw dataset (.csv, .dta, .xlsx, .sav, .sas7bdat, .parquet) and does not yet know what cleaning is needed or which downstream pipeline — 00 StatsPAI / 00.1 Python / 00.2 Stata / 00.3 R — to route to. Runs a data-driven 5-slot conditional Q&A (discipline, research design, unit of observation, focal variables, software target), where slots that the data already answers are skipped or pre-filled, and slots that the data cannot answer are surfaced as multiple-choice questions. Executes the deterministic 80% of Step 1 cleaning that the four flagships' references treat as user-decided — column rename to snake_case, automatic dtype coercion for unambiguous cases, duplicate detection, primary-key validation, panel structure inference, missing-rate inventory, outlier flagging (flag only, not winsorize). Concludes with a built-in deterministic data evaluation phase that grades the cleaned dataset against 23 pure-rule checks (10 strengths + 13 optimization rules) and produces a strengths / optimizations / overall-grade markdown report — entirely from internal metrics, no networking, no external models. Produces five output files — cleaned dataset in the Slot-5 native format (.dta / .parquet / .rds), an always-on `cleaned_dataset.xlsx` 7-sheet inspection workbook for visual spot-check, `data_contract.yaml` describing verified dataset properties, `routing_recommendation.md` pointing to the correct flagship and mode, and `data_evaluation.md` with the strengths / risks / verdict report. Holds the public-health / epidemiology cleaning patterns the four flagships' Step 1 references omit — index date / time-zero alignment, censoring vs missing distinction, person-time construction, washout periods, immortal-time-bias detection, ICD/CPT/ATC code normalization. Does NOT replicate flagship Step 1 — multiple imputation, advanced outlier methods, detailed merge mechanics, event-study time alignment all hand off to the matched flagship by reference. Triggers on phrases like "原始数据", "数据清洗", "不知道用哪个 pipeline", "怎么开始", "raw data", "data intake", "data triage", "data wrangling", "empirical data cleaning", "panel attrition", "cohort 数据", "index date", "public health data", "流行病学数据", ".dta 怎么处理", "this data is a mess", "数据质量评价", "data evaluation".

  • Research viz

    wyc79/research-viz-skill/research-viz Skill

    1★ repo

    Reproducible Python research-visualization workflow for tabular data (csv/xlsx/tsv/txt). Produces a self-documenting `visualizations/` folder with a pandas+numpy parser (quality checks, missing-data handling), a matplotlib+seaborn plot generator, and a streamlit/altair interactive viewer — each behind a small shell wrapper. Use this skill whenever the user wants to "visualize / explore / plot / chart / dashboard" a dataset, asks for "research visualizations", to "make a streamlit app from this data", to "clean up this CSV and chart it", points at a `data/` folder of tabular files, says "summarize this dataset visually", or hands over an .xlsx/.csv/.tsv and wants to see what's in it. Also use whenever the user opens a folder that already contains `visualizations/info/context.md` — the skill is designed to be resumable across agent sessions via that context file.

  • Anthropic sdk

    andreab67/agent-skills/anthropic-sdk Skill

    1★ repo

    Anthropic Claude SDK — Messages API, tool use, streaming, cost estimation, model selection

  • Enhanced self

    LewenW/claude-distill-me/skills/enhanced-self Skill

    1★ repo

    Personal behavioral patterns generated by Distill-Me. Activates when acting on behalf of the user.

  • Jp law

    HighBridgeDragon/jp-law-skill/jp-law Skill

    1★ repo

    Search and retrieve Japanese laws and regulations via the official e-Gov Law API V2 (no auth required). Supports law name search, article retrieval, amendment history, and full-text keyword search. Useful for legal research, compliance checks, contract review, and any task involving Japanese statutes (民法/Civil Code, 会社法/Companies Act, 個人情報保護法/APPI, 労働基準法/Labor Standards Act, etc.). 日本の法令をe-Gov法令API V2経由で検索・取得するスキル。法令名検索、条文取得、改正履歴、キーワード検索に対応。Use this skill when researching Japanese laws, regulations, or legal texts.

  • Agi skill

    Ivorisnoob/agi-skill Skill

    1★

    Activate the Sovereign Systems Architect (SSA) persona — a synthesis of Robert C. Martin's clean code discipline, Garry Tan's GStack agentic velocity, and Terry Davis's first-principles purity. Use this skill whenever the user asks to architect, review, plan, or build software systems with AGI-level rigor. Trigger when the user mentions clean architecture, SOLID principles, agentic workflows, GStack, cognitive gearing, first-principles engineering, technical debt reduction, SSA persona, or asks for a "10-star product" review. Also trigger for code reviews, feature planning, debugging root cause analysis, or any task where the user wants maximum engineering quality and velocity. When in doubt, use this skill for any non-trivial software engineering task — it always produces superior, more intentional output than generic coding assistance.

  • Codex fewer permission prompts

    gaoguobin/codex-fewer-permission-prompts Skill

    no license1★

    Codex permission prompts helper for /fewer-permission-prompts default dry-run, safe prefix_rule proposals, execpolicy verification, apply, and rollback.

  • Product research

    199-biotechnologies/product-research Skill

    1★

    Researches, compares, and recommends products before a purchase — any physical product, SaaS, gadget, instrument, software, or service. Triggers on "should I buy X", "X vs Y", "recommend a [product]", "what's the best [category]", "before I buy", "is [product] worth it", "help me decide between X and Y", or any shopping-intent phrasing with a budget or use case. Does NOT trigger for post-purchase support, feature-only questions from existing owners, or abstract "best of all time" trivia with no user context.

  • Agent retro loop

    OctavianTocan/agent-retro-loop Skill

    1★

    Retrospective loop for AI agents. Gathers recent session logs, extracts behavior-changing lessons, checks them against existing memory and skills, writes a review buffer, then applies safe non-conflicting memory or skill updates while asking before conflicts or risky changes.

  • External llm

    leon2k2k2k/agent-skills/external-llm Skill

    1★ repo

    Multi-turn conversation with an external reasoning model (DeepSeek Reasoner, o1, o3) via any OpenAI-compatible API. Session persistence, pushback workflow, and structured reports. Use for proof verification, reasoning tasks, or getting a second opinion.

  • Gmail persona

    sanoakr/ai-skills/gmail-persona Skill

    no license1★ repo

    Build a reusable knowledge base of personas from Gmail history — one file per sender or department — and use those personas to answer questions and draft emails in the right style. Use this skill whenever the user wants to: - "build personas from my Gmail" - "create a contact knowledge base from email" - "who usually contacts me about X?" - "draft a reply to [person/department] in their style" - "what writing style does [department] use?" - "summarize how [person] communicates" - "create a self-persona from my sent emails" - "analyze my email communication patterns" The skill guides the full workflow: search → index → persona files → Q&A / email drafting. Trigger even when only part of this workflow is mentioned.

  • Act

    petr-korobeinikov/skills/skills/act Skill

    1★ repo

    Second line of defence after actionlint: runs GitHub Actions workflows locally with act (nektos/act) to check they actually work, not just that they parse. Proposes the run on a workflow commit; never blocks it.

  • Aor req

    Agents-On-Rails/aor-skills/.claude/skills/aor-req Skill

    1★ repo

    Author User Needs (UN), Product Requirements (PR), and Software Requirements (SR) using EARS-12 patterns with full UN→PR→SR traceability.

  • Super product business finance

    arpitexplores/super-product-business-finance Skill

    1★

    Product, business, and finance: market sizing, pricing, monetisation, and PM frameworks.

    The same file is in 1 other repository

  • Ppki ipb

    dzakwanalifi/ppki-ipb/skills/ppki-ipb Skill

    1★ repo

    Pedoman Penulisan Karya Ilmiah (PPKI) IPB University 2024. Use for formatting rules, citation styles (APA 7th), academic writing standards, and evaluating/reviewing/improving Indonesian writing using EYD V.

  • Align

    Background-Craft/hydrant-skills/skills/align Skill

    1★ repo

    Scan the user's codebase, ask up to five clarifying questions, and write a fenced Alignment block into AGENTS.md that the Hydrant lifecycle skills (`/go`, `/prep`, `/preflight`, `/yeet`) read for stack-specific behavior. Use when the user asks for `/align`, says "align hydrant-skills", wants the lifecycle skills tuned to this codebase's conventions, or runs the install for the first time.

  • Typst cetz skill

    statzhero/typst-cetz-skill Skill

    no license1★

    CeTZ (TikZ-inspired drawing for Typst) patterns for creating diagrams. Use this skill when creating diagrams, flowcharts, graphs, plots, or technical illustrations in Typst documents. Covers coordinate systems, drawing primitives, styling, anchors, marks, trees, and plotting.

  • Architect mindset

    UniverLab/skills/architect-mindset Skill

    1★ repo

    Use this skill when designing systems rather than implementing them: choosing boundaries and contracts, comparing architecture options, planning multi-component work, decomposing a problem into independently verifiable parts, reviewing a design for failure modes, or writing specs and decision records that other agents (or cheaper models) will execute. It applies systemic thinking at the design level; for code-level structure use code-engineering instead.

  • Domain modeling pre prune cfea0f22

    stevennitesh/programming-agent-skills/docs/validation/evals/domain-modeling-pre-prune-cfea0f22 Skill

    1★ repo

    Model and persist a project's context-scoped ubiquitous language, invariants, bounded contexts, relationships, and approved durable decisions. Use when domain meaning needs focused clarification or capture, including delegated capture, or an already-settled decision needs ADR assessment; exclude ordinary vocabulary lookup and general design debate.

  • Content creation skill

    ChuluuMGL/content-creation-skill Skill

    1★

    Media content creation package workflow. Use when the user wants to turn source material, notes, links, ideas, product details, or rough drafts into publish-ready media content for Xiaohongshu, WeChat official account, WordPress, website articles, Douyin scripts, newsletters, or social posts; score and polish content by writing purpose; adapt one draft across platforms; or make targeted section-level revisions. This skill focuses on drafting, scoring, revision, packaging, cover-image prompts, and manual publishing checklists, not automatic platform publishing.

  • Hucre best practices

    lazuee/agent-skills/skills/hucre-best-practices Skill

    1★ repo

    Use when working with hucre to read/write spreadsheets, choose format-specific imports, stream large data, validate schemas, and preserve round-trip content.

  • OnboardingV2

    launchdarkly/experimental-agent-skills/skills/onboardingV2 Skill

    no license1★ repo

    This repository is meant to serve as a publicly available agent-skill to be toggled between to iterate on experimental agent-skills

  • Persona model trainer

    acnlabs/persona-model-trainer Skill

    no license1★

    Fine-tune any HuggingFace instruction-tuned model (Gemma 4, Qwen 3, Llama, Phi, Mistral, and more) on persona data from anyone-skill. Produces a self-contained, locally runnable persona model — no cloud API required.

  • Analyze code

    lgtm-hq/ai-skills/skills/analyze-code Skill

    1★ repo

    Code-level quality analysis. Use when asked to review code for smells, security issues, implementation quality, or test coverage.

  • Wiki bootstrap

    jpab/maieutic-tools/tools/anamnesis-wiki/skills/wiki-bootstrap Skill

    1★ repo

    Builds a codebase wiki from scratch through deep reading and phased Socratic questioning. Thorough — run once on a new project.

  • Git repo doctor

    LaughingisLaughing/git-repo-doctor Skill

    1★

    Diagnose a bloated or corrupted Git repository and produce a safe, rollback-aware cleanup plan. Use when a .git directory is huge (many GB), full of objects/pack/tmp_pack_* or tmp_obj_* files, or holding hundreds of thousands of loose objects; when git gc/repack/fetch was interrupted (OOM, crash, timeout); when git count-objects reports "garbage"; when an editor or coding agent crashes while scanning a repo; or when the user asks how to safely shrink, clean, prune, or reclaim disk space from a Git repository. The tool is strictly read-only: it inspects and prints a plan but never runs destructive commands.

  • Event analytics

    simonkoehler/event-skills/event-analytics Skill

    1★ repo

    Measure, analyze, and report on actual B2B event performance using post-event data. Generates KPI frameworks, post-event survey questions, ROI calculations from actual results, attendance analysis, session performance reports, sponsor fulfillment reports, and lessons-learned documents. Use this skill whenever someone asks to measure event success, create event KPIs, build a post-event survey, calculate actual event ROI from post-event data, analyze attendance data, create a post-event report, compare event performance year-over-year, measure sponsor satisfaction, evaluate session ratings, write a lessons-learned document, or plan a post-event debrief. Also triggers for NPS surveys, lead quality analysis, content engagement metrics, and event benchmarking. Part of the event-management-skills collection — measures outcomes while other skills handle planning, execution, and content.

  • Codebase visualize

    Shaelz/codebase-visualize-skill/skills/codebase-visualize Skill

    1★ repo

    Use to build a visual + operational map of a repository for an AI coding agent. Scans a target repo into a structured graph JSON and renders a self-contained interactive HTML map, with claim labels (fact / inference / unknown), risk hints, and an agent routing panel that suggests what to read before editing a file or domain. Good triggers: visualize this codebase, map the repo, show me the structure, what should I read before editing X, where do things live, generate a codebase map/graph. Does NOT do AST/import analysis, MCP, or diagram-tool export.