Engineering
98,648 rows, by stacks then stars
psake/psake-llm-tools/plugins/powershellbuild/skills/powershellbuild Skill
1★ repoThis skill should be used when the user asks to "set up PowerShellBuild", "create a psakeFile with -FromModule", "configure PSBPreference", "publish a PowerShell module to PSGallery", "set up Pester tests for a module", or mentions PowerShellBuild, PSBPreference, -FromModule PowerShellBuild, PowerShellBuild.IB.Tasks, PSScriptAnalyzer integration, PlatyPS help generation, code coverage thresholds, or PowerShell module build/test/publish pipelines.
The same file is in 1 other repository
ChewbaccaRoars/pathfinder-skills/skills/agent-architect Skill
1★ repoGuides users from simple automations to building their own agents. Introduces concepts gradually — from scripts that check-and-act, to multi-step workflows, to decision logic, to full agents. Use when someone is ready to level up beyond simple automations.
namtroi/agentic-base/template/.claude/skills/plan Skill
1★ repoCreate implementation plans. Use for feature planning, system design, architecture, roadmaps.
winstonice-prog/excel-wps-table-diagnosis Skill
1★Diagnose spreadsheet structure and recommend practical Excel/WPS-compatible formulas and workflows for cleaning, lookup and matching, summarization, text and date cleanup, and common formula troubleshooting. Use when the user asks what formula to use, how to process a table, how to clean messy columns, how to match sheets, how to make a solution work in both Excel and WPS, or when headers and sample rows should be inspected before deciding what to do next.
humongus69/langsmith-fetch-skill Skill
1★Debug LangChain and LangGraph agents by fetching execution traces from LangSmith Studio. Use when debugging agent behavior, investigating errors, analyzing tool calls, checking memory operations, or examining agent performance. Automatically fetches recent traces and analyzes execution patterns. Requires langsmith-fetch CLI installed.
The same file is in 10 other repositories
OthmanAdi/vibe-skills/skills/vibe Skill
1★ repoGenerate and deploy production-grade websites from a natural language description. Use when asked to "vibe a site", "vibe code this", "build me a website and publish it", "create a landing page and deploy it", "make a portfolio site and put it online", "generate a site and ship it", or any request combining website creation with deployment. Produces a live URL via here.now.
The same file is in 2 other repositories
0xc000022070/agentic-flake/examples/3-home-manager/skills/api-design Skill
no license1★ repoREST API design patterns and conventions
codepros100-dev/claude-windows-health-check/windows-health-check Skill
1★ repoComprehensive Windows system health check, diagnostics, and remediation
HaoliangCheng/skills/skills/frontend-llm-output-handler Skill
1★ repoGuide for enhancing frontend code with the capability to render AI/LLM outputs (Markdown, LaTeX, code blocks) securely and accurately in the UI.
newyounghe-design/context-handoff-skill Skill
1★对话上下文交接与资产化管理。当用户需要压缩当前对话上下文、切换到新对话继续、或加载之前的交接文档时触发。触发关键词:"/handoff"、"交接"、"上下文压缩"、"压缩上下文"、"切换对话"、"恢复上下文"。
lopadova/playwright-enterprise-tester/skills/playwright-enterprise-tester Skill
1★ repoEnterprise-grade browser automation, E2E verification, AJAX-heavy UI testing, auth-protected flow testing, visual regression, and performance budget enforcement using Playwright Test. Autodetects Laravel, Vite, Mix, Node, Bun, Next.js and Cloudflare Worker contexts. Writes persistent Playwright specs, runs tests with rich diagnostics, classifies failures with deterministic playbooks, enforces silent-failure detection, reports frontend contract gaps, and emits a stable JSONL flakiness history for analytics dashboards. Two runner modes (local dev vs CI) with different defaults. 17 optional phase 2 features (cross-browser, axe a11y, Lighthouse, swarm mode, AI root cause analyzer, etc.), all toggleable independently via .playwright-tester.json. Defensive-minimal defaults, progressive opt-in. Never auto-triggers: invoked via /playwright-tester slash command or the playwright-enterprise-tester agent.
anotherben/claude-enterprise-skills/skills/enterprise-brainstorm Skill
1★ repoDeep enterprise brainstorming that turns vibe-coded ideas into Technical Design Documents. Three phases: EXTRACT (pull intent from user's head), DISCOVER (research codebase and surface implications), ENGINEER (produce full TDD autonomously). Use when starting any feature, system, or significant change. The user describes what they want — you deliver the engineering.
The same file is in 2 other repositories
liam-jons/claude-got-skills/plugins/assistant-capabilities/skills/assistant-capabilities Skill
1★ repoUse when users ask about current Claude capabilities, API features, model specifications, or need guidance building with Claude. Provides accurate answers about what Claude can do across all platforms (Claude.ai, Desktop, Claude Code, CoWork) including model selection and context limits, streaming and tool use, structured outputs, extension patterns like skills and hooks and MCP and plugins, Code Review, Remote Control, web and cloud sessions, and Slack integration. Essential when training data may be outdated, when comparing Claude to competitors like Copilot or Cursor or ChatGPT or Windsurf, when migrating from other AI tools, or when advising on architectural decisions and agent workflows.
lj22503/investment-framework-skill Skill
1★基于 DAIR-AI 提示词工程框架优化的投资决策支持系统。 基于 5 本经典投资书籍 + 凯文·凯利未来预测方法论的实战工具箱。 支持 Zero-shot、Few-shot、Chain-of-Thought (CoT) 等模式。 输出严格 JSON 格式,包含分析结果、建议、风险、行动项。
SkillMedev/full-stack-web-dev/skills/api-design Skill
1★ repoDesigns REST API surfaces - resource naming, HTTP method and status-code semantics, error shapes, pagination, and filtering - and delivers an endpoint spec a consumer can build against without asking questions. Use when someone asks "how should I name this endpoint", "what status code should this return", "should this be PUT or PATCH", "how do I paginate this list", or is reviewing an API before it ships to external consumers. Do NOT use for planning breaking-change rollouts and deprecation windows - use api-versioning-strategist instead; for GraphQL type and resolver design - use graphql-schema instead; for generating client SDKs from an existing spec - use api-client-generator instead; for designing inbound webhook endpoints - use webhook-receiver-hardener instead.
The same file is in 3 other repositories
Consultora-AMDT/claude-github-security-audit/en/github-security-audit Skill
1★ repoSecurity audit for GitHub repositories before integrating them into your stack. Seven dimensions: project health, code security, supply chain, code quality, license, MCP/plugin attack surface and external trust signals. Weighted scoring with ADOPT/EVALUATE/CAUTION/AVOID verdict and an HTML report. Inspired by Trail of Bits' supply-chain auditor and insecure-defaults frameworks. Activate with: audit repo, repo security, evaluate repo, evaluate library, evaluate dependency, review repo, supply chain, is this repo safe, security audit github, repo risk, evaluate MCP server, evaluate plugin, evaluate skill, evaluate integration. Also when the user shares a GitHub link and asks whether to integrate or trust it. Do NOT activate for own-codebase reviews or SEO audits.
Yebxi/skill-test-duke/claude-folder-skill Skill
no license1★ repoPrompt-injection evaluation harness for Claude/Codex-style skills. Use when testing whether an agent can read a realistic skill, follow benign workflow instructions, identify embedded adversarial instructions, and avoid executing injected setup steps or resource-abuse payloads.
thattimc/skills/skills/claude-code-review Skill
1★ repoCross-model review through Claude Code with local verification. Use when the user requests an independent Claude review or repository policy requires a Claude review pass.
hparamore/essential-claude-skills-hparamore/fable-toolkit/skills/best-practices-check Skill
no license1★ repoReview a codebase or change for code QUALITY — structure, naming, error handling, testing gaps, types, dependencies, and the project's OWN documented conventions — and report graded, prioritized findings. Use whenever the user asks to "review code quality", "check best practices", "is this well written", "clean this up", "tech debt audit", "does this follow our conventions", or wants a maintainability pass before merge/handoff. Judge against the project's actual standards, not a generic checklist. Not for functional bugs (use bug hunting), performance (use optimize), security vulnerabilities (use the security review), or visual/UX design (use the design audit) — this is about how well-written and consistent the code is.
kreek/consult/.agents/skills/ship Skill
1★ repoRun Consult's guarded maintainer flow for commit, merge, version bump, validation, and push.
Methasit-Pun/data_engineer_claude_skills/00-start-here/data-lifecycle Skill
no license1★ repoUmbrella skill for running a data project end-to-end through its lifecycle stages — discover sources → profile the data → architect the platform → build the medallion pipeline → refactor the code. Use this whenever the user is kicking off a new data project, asks "where do I start" or "what are the steps", or is somewhere mid-lifecycle and unsure which stage skill applies. This skill ROUTES to the stage sub-skills (data-sourcing, data-profiling, data-architecture, medallion-design, notebook-refactor) and sequences them, pulling in the right one for the user's current stage.
asiridalugoda/autonomous-loop Skill
1★Run an autonomous, self-directed build loop that keeps working across many goals without per-step prompting — design the system that does the work, then let it run (Addy Osmani's "loop engineering"). Use whenever the user wants to "keep going on your own", "run until done", grind through a backlog or goal-list unattended, set up a maker/checker agent workflow, run a self-improving or nightly loop, or build a durable externalized spine (goals + board + handover) so work survives context resets. Trigger on phrases like "autonomous loop", "keep working without me", "no human intervention", "loop engineering", "self-improving loop", "run the loop", "ralph loop", "multi-agent coordinator", or "agent roster" — even if they don't say "skill".
U0001F3A2/liquid-org/skills/compose-org Skill
no license1★ repoRun a task as an evolved multi-agent ORG using the installed liquid-org framework — where YOU (the running Claude) embody the org: you ask liquid-org which proven team topology + specialist personas to use (retrieved from its evolved pool, or assembled fresh), then dispatch ONE SUBAGENT PER TALENT to play each role independently, then grade and record the result so the pool learns. Use this whenever a task here would genuinely benefit from a team of INDEPENDENT specialist perspectives rather than a single pass — a non-trivial refactor, a bug fix that needs proposing + adversarial review, a multi-step analysis — and you want cross-task learning (good orgs get reused next time). Trigger on "compose an org / a team for this", "run a liquid-org team on X", "use the framework to do X", "dogfood this", or when the user wants the self-evolving system to actually perform a task. Do NOT use for trivial single-step edits (a team is overkill), or for developing liquid-org's own code (that's ordinary work, not org composition).
Avalon-27reg/smyslokod-starter/.claude/skills/diagnose Skill
1★ repoUse this when the user reports a bug, regression, or "что-то не работает" / "это сломалось" / "почему упало". Drives a systematic debugging cycle instead of guessing fixes. Skip for syntax errors and obvious typos.
DennisWei9898/loop-engineering-reviewer Skill
1★Loop Engineering 合規審查員 — 拿 Addy Osmani《Loop Engineering》當量尺,審查一個 agent / skill / 自動化迴圈專案「產出/驗證分離」的設計對不對,逐條給 PASS/FAIL/WARN + 證據,然後在**保留使用者原始風格**的前提下只修合規問題。提問走八二法則(規則不清時先挑 3-5 個影響最大的問,不一次拋 50 題),循序漸進把合規度拉到 100%。觸發詞:loop engineering 審查、審一下這個 agent、這個 skill 合不合規、loop 合規檢查、review 這個迴圈、loop-engineering-reviewer、幫我體檢這個 agent。
T4LEL/Claude-Arsenal/skills/add-ai Skill
1★ repoUse when adding an AI/LLM feature to a product - chat, generation, summarization, extraction, semantic search - or when the user says add AI, use Claude, chatbot, embeddings.
wemwi/skill-library/global-agent-framework Skill
no license1★ repoBuild-Time-Framework zum Bauen, Konfigurieren, Deployen und Debuggen von Claude Managed Agents (Claude Platform / Anthropic Console) in diesem Stack — Anleitung für die Arbeit AM Agenten, kein Skill der einem laufenden Agent angehängt wird. IMMER laden, sobald ein Managed Agent erstellt, konfiguriert, verdrahtet, deployed, versioniert oder gedebuggt wird — auch wenn das Wort Skill nicht fällt. Trigger u.a.: Managed Agent anlegen, Agent-Config (system/tools/mcp_servers/skills), Session starten, Scheduled Deployment / Cron-Trigger, Webhook-Brücke zum Starten von Sessions, Vault für Agent-Secrets, Permission-Policy, Least-Privilege, Allowlist/ Denylist, Tool-Oberfläche minimieren, enabled:false vs permission_policy, Agent- Version bumpen, Agent debuggen, neuen Agent ins Portfolio aufnehmen. Gilt für jeden Managed Agent in diesem Stack.
Skill observability monitoring
zavora-ai/skill-observability-monitoring Skill
no license1★Orchestrate full-stack observability — query logs, search traces, monitor metrics, manage alerts, handle incidents, track SLOs, and execute runbooks. Use when debugging errors, investigating latency, checking service health, managing alerts, responding to incidents, reviewing SLO burn rate, or finding runbooks.
t0ddharris/compound-marketing/.claude/skills/ab-test-setup Skill
no license1★ repoWhen the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "should I test this," "which version is better," "test two versions," "statistical significance," or "how long should I run this test." Use this whenever someone is comparing two approaches and wants to measure which performs better. For tracking implementation, see tracking-setup. For page-level conversion optimization, see page-cro.
josuebustosn/claude-students/skills/claude-students Skill
1★ repoTransforma una carpeta cruda de material de un parcial universitario (PDFs, DOC/DOCX, PPT, audios .ogg de WhatsApp, capturas) en un material de estudio polished y completo — HTML SOTA autocontenido + paquete de artefactos de NotebookLM (podcast en español, infografía, guía de estudio, briefing doc, mind map, quiz, flashcards). Usar este skill SIEMPRE que el usuario diga "tengo parcial de X", "ayúdame con este parcial", "armame el material de estudio", "convierte estos archivos en un HTML estudiable", "transforma esta carpeta en material de parcial", "pásame esta carpeta a HTML interactivo", o simplemente comparta una carpeta con archivos de materia universitaria. También activar cuando aparezcan archivos tipo "GUIA PARCIAL", "TEMA X", "CamScanner", "WhatsApp Ptt", "Parcial.pdf", "Acumulativo" en el contexto. El skill replica un patrón validado en múltiples entregas reales — no preguntar metodología antes de empezar, arrancar directo.
yorilavi/prompt-optimizer Skill
no license1★Optimizes prompts through an iterative Claude-GPT review process. Use when the user wants to optimize, improve, or refine a prompt. Supports automated review via Codex plugin or manual GPT handoff.
SkillMedev/vercel-platform/skills/next-on-vercel-perf Skill
1★ repoDiagnose and fix Core Web Vitals and page performance of a Next.js app on Vercel - measurement-first. Use when an LCP/INP/CLS score is bad, a page "feels slow", Lighthouse/PageSpeed/Speed Insights is red, the JS bundle is too big, images or fonts are janky, or you want Vercel-specific caching/edge wins. Triggers: "improve Core Web Vitals", "fix LCP", "reduce INP", "stop layout shift", "my Next.js page is slow on Vercel", "shrink my bundle", "next/image optimization", "font is causing CLS", "cache this page". Do NOT use to set up the deploy pipeline or rollbacks - use vercel-deploy-pipeline; for ISR/cache-component semantics and edge runtime choice - use vercel-edge-and-isr; for env/secrets - use vercel-env-management; for model/provider routing - use vercel-ai-gateway; for WAF/bot defense - use vercel-firewall-and-botid.
The same file is in 1 other repository
kbelasheuski/ios-architecture-skills/plugin/skills/ios-architect Skill
1★ repoSenior iOS architecture skill for choosing, auditing, refactoring, and migrating app architectures across UIKit and SwiftUI. Use when the user mentions architecture choice, refactor planning, codebase audit, migration between patterns, or asks which architecture to use.
bluem-dev/Etta/skill Skill
1★ repoEtta Cognitive OS is a model-agnostic cognitive architecture layer that enhances LLM reasoning quality, continuity, planning, and knowledge management. Use this skill whenever the user asks to run structured reasoning sessions, implement goal-state-decision cognitive loops, manage persistent memory across LLM interactions, apply critic-gated validation before any action, build autonomous agents with structured state, or when the user explicitly mentions "Etta", "cognitive OS", "cognitive layer", "critic loop", "state engine", or "structured reasoning". Also trigger when designing multi-step agent workflows that require auditability, rollback, and deterministic cognitive control on top of any LLM.
xcl2005/github-skill-curator Skill
1★Skill procurement and routing gate for Agent Skills. Use when the user asks to find, compare, install, update, audit, disable, remove, or curate Codex / Claude Code skills; asks for better, latest, high-star, GitHub-recommended, awesome-list, or reusable skills; or when a high-value repeated artifact workflow such as PPTX, DOCX, PDF, spreadsheets, LaTeX, academic writing, resumes, or reports may benefit from a specialized skill beyond built-in capabilities. It checks built-in and installed skills first, searches pinned core skills and curated indexes when useful, scores candidates by relevance, evidence, stars, recency, license, structure, curation quality, and safety, and asks before installing unknown third-party skills.
alebgl77/grafana-llmops-forge Skill
1★Pilote l'observabilité IA/LLM de bout en bout sur Grafana (OSS, Cloud, Enterprise) avec un seul prérequis — une instance Grafana accessible. Auto-découverte (version, APIs, datasources), détection des signaux LLM présents (OTel GenAI gen_ai.*, LiteLLM, vLLM, TGI, GPU/DCGM), génération et déploiement automatiques de dashboards — FinOps & coûts multi-providers (US/EU/Asie), gateway, tracing agents & RAG, adoption interne, gouvernance EU AI Act, inference self-hosted — alerting SLO, registre de modèles avec pricing, puis contrôle visuel du rendu réel (captures renderer/navigateur inspectées par vision). Utilise ce skill dès que l'utilisateur mentionne Grafana, un dashboard, du monitoring/observabilité IA ou LLM, des coûts de tokens, du FinOps IA, du LLMOps, des agents ou du RAG, l'adoption de modèles, la conformité AI Act, ou Prometheus/Loki/Tempo appliqués à l'IA — même sans le mot « dashboard ». Vaut aussi pour auditer un Grafana existant ou une stack IA qui n'émet encore rien.
Aidress skill find verified language translation agent
Aidress-ai/aidress-skill-find-verified-language-translation-agent Skill
1★Find a Verified Language Translation Agent. Agent discovery, trust verification, and capability routing powered by Aidress — the coordination registry for autonomous AI agents. Use for content agent discovery, trust verification, and capability routing — via Aidress (https://api.aidress.ai).
zwbao/skill-creator-pro Skill
1★Use when creating new skills, iterating on existing skills, auditing skill quality, bumping skill versions, or optimizing skill trigger descriptions. Pro-grade lifecycle covering scaffold, baseline testing, evals, lint, semver, CHANGELOG, and description optimization. Triggers on "create a skill", "new skill", "迭代 skill", "优化 skill", "skill 版本", "skill lint", "review this skill", "write a skill for X", "turn this into a skill", or whenever the user starts or edits a SKILL.md.
ivogabriel19/git-github-workflow-skill/skills/git-github-workflow Skill
1★ repoProfessional Git and GitHub workflow conventions, including CI configuration. Use this skill for every version control or repository operation — staging changes, writing commit messages, creating or switching branches, opening pull requests, rewriting history, tagging releases, setting up branch protection, authoring or reviewing GitHub Actions workflows, or any `git` command. Apply these rules mechanically to keep `main` deployable, commits atomic and conventional, history navigable, PRs reviewable in under thirty minutes, and CI fast and reliable. Trigger this whenever you're about to commit, push, open or merge a PR, run `rebase`, `reset`, `cherry-pick`, write a `.github/workflows/*.yml` file, or configure repository settings — even for trivial one-line changes.
glichtenthal/test-drive Skill
1★Use when the user has a plausible but untested idea, belief, thesis, strategy, decision, prompt, skill, message, artifact, or AI output and asks how to validate it, test it, try it, de-risk it, gather evidence, run analysis, run a regression, dry-run it, evaluate it before shipping, identify needed connectors, or turn judgment into evidence-seeking action.
NafisRayan/100x-Agent-Toolkit/skills/21st-dev-builder-v2 Skill
no license1★ repoBuild websites and web apps using 21st.dev — the largest marketplace of shadcn/ui-based React Tailwind components with 1400+ components. Use when user mentions "21st.dev", "21st", "ใช้ 21st", "จาก 21st", "build with 21st", "21st component", "21st magic MCP", or references the 21st.dev component registry in any language. Covers building complete sites (landing pages, dashboards, portfolios, e-commerce storefronts, auth pages), browsing and installing individual 21st.dev components into existing projects, and setting up the 21st.dev MCP server. Also trigger when user wants premium UI components specifically from the 21st.dev registry. Do NOT trigger for general web development, standard shadcn/ui, plain Tailwind CSS, React Native, API development, testing, deployment, or any task that doesn't explicitly reference 21st or 21st.dev.
zavora-ai/skill-workflow-orchestration Skill
no license1★Orchestrate multi-step workflows with approval gates, state machines, and conditional branching. Use when building automated processes, managing approval chains, running multi-step tasks, or coordinating sequential operations with decision points.
Skill cicd pipeline management
zavora-ai/skill-cicd-pipeline-management Skill
no license1★Orchestrate CI/CD pipelines — check build status, view logs, download artifacts, rerun workflows, trigger deployments, and manage release gates. Use when checking build status, debugging pipeline failures, triggering reruns, deploying to environments, or managing release workflows.
alialavia/pbt-skills/skills/pbt-hypothesis Skill
1★ repoHypothesis-specific patterns for property-based testing in Python — strategies, RuleBasedStateMachine, settings, and Hypothesis ecosystem gotchas. Use this skill whenever the task involves Hypothesis tests, the `hypothesis` package, `@given`, `st.` strategies, `RuleBasedStateMachine`, `@example`, or any Python property-based testing work. This skill pairs with the core `property-based-testing` skill, which handles property discovery and design — load both together for any Hypothesis task. This skill does not re-derive the workflow; it assumes the core skill is loaded and only covers Hypothesis syntax, idioms, and library-specific patterns.
sirius-zuo/architect-skills/architect-codebase-review Skill
1★ repoUse when an existing codebase needs an architecture review. Explores the codebase, generates current-state architecture diagrams using Mermaid.js, evaluates against architecture principles, proposes recommended improvements with revised diagrams, and saves an HTML report to docs/architecture/review/.
knack-run/knack-starter-pack/skills/first-skill-template Skill
1★ repoScaffold a new Claude Code skill at `.claude/skills/<name>/SKILL.md` with the canonical Knack body pattern (frontmatter, when-to-use, inputs, steps, output format, worked-example pointer, don'ts). Triggers on "scaffold a skill called X", "make me a new skill", "create a SKILL.md for X", "I want to write my first Claude Code skill". Refuses to overwrite an existing file; refuses to invent skill content the user hasn't supplied.
takeaseatventure/sql-sentinel/skills/sql-sentinel Skill
1★ repoAudit SQL for the cost & performance anti-patterns that burn warehouse credits. Catches SELECT *, full-table scans, non-sargable predicates, Cartesian joins, NULL-trap NOT IN, and 17 more rules. Scores warehouse health 0-100 and outputs a prioritized cost-reduction plan for BigQuery, Snowflake, Redshift, and Postgres.
SpoiledMilkLabs/skills/skills/handoff Skill
1★ repoCapture session state at end of a coding session so a future Claude Code session can resume cold, or resume from a prior handoff. Trigger PROACTIVELY when the user signals end of session — "wrapping up", "call it for tonight", "let's stop here", "I need to go", "continue tomorrow", "pick this up later", "save where we are", "done for now" — and also on explicit /handoff. For resume, trigger when user says "resume", "pick up where we left off", "continue from yesterday", "what was I working on", or /handoff resume.
jai2010/shorthand-mem Skill
no license1★A two-way semantic compiler that compresses PRDs, codebases, research papers, and meeting notes into dense symbolic notation, and reconstructs them back into professional prose. Use this skill whenever the user writes SQUEEZE, EXPAND, DIFF, MERGE, SUMMARISE, LIST SQUEEZES, RECALL, SEARCH, DELETE, or EXPORT ALL — or when they want to compress, store, retrieve, compare, or summarise any document. Works across four domains: PRD, CODE, PAPER, MEETING. No MCP server or API key required — runs entirely within Claude.
tokyubevoxelverse/semver-cop Skill
1★Determine whether the next release is legally a patch, minor, or major by diffing the public API surface against the last published version. Use before cutting a release, when reviewing "is this breaking?", or when writing honest release notes.
vindm/dotclaude/deferred/skills/ai-workflow Skill
1★ repoSet up LLM workflow discipline for projects that use AI / LLM calls in production or eval suites. Authors an eval-cost-watcher agent that projects token cost BEFORE regression evals run, plus an AI-workflow-discipline rule covering mock-mode placement, fixture freshness, and multi-stage cost accumulation. Optionally a small eval-regression skill stub. Invoke /dotclaude:ai-workflow only when the project actually has AI workflows.
cs-shadowbq/claude-context/skills/claude-context Skill
1★ repoSearch across all ~/.claude data (conversations, project memories, global memories, plans, agents) to find prior work, past solutions, and relevant context before reading raw files or grepping manually. Use this whenever the user asks things like "have we dealt with this before," "did I solve this somewhere," "find that memory/note about X," "what project was that in," or when you (Claude) need to recall a prior decision, convention, or fix across projects without knowing which project or conversation it's in. Always prefer this tool over `grep`/`find`/reading whole .claude files directly — it is dramatically cheaper in tokens and returns structured, rankable results.
zavora-ai/skill-test-execution Skill
no license1★Orchestrate test execution — run unit, integration, and E2E tests, collect coverage reports, and analyze failures. Use when running tests, checking coverage, debugging test failures, or validating code changes before merge.
HelloThisWorld/agent-skill-verification-template/skills/codebase-understanding Skill
1★ repoAnswers questions about a codebase using source-grounded evidence. Every factual claim must cite a specific file and line; ambiguous or unsupported questions return insufficient_evidence instead of a guess.
Stepkar2004/init-configurator/.claude/skills/bootstrap Skill
1★ repoPhase 0 of any project - fire whenever asked to start, scaffold, set up, or adopt a project ("new Python CLI", "set this repo up properly", "add a frontend stack"). Interview, scaffold via OFFICIAL creators, describe into project.yaml, prove with gates.
ykotik/cli-power-skills/skills/api-testing Skill
1★ repoUse when testing HTTP endpoints, probing URLs for status and headers, or running declarative API test suites from plain text files
The same file is in 2 other repositories
refaelach/gmba-class-19-skills/skills/decision-making/llm-council Skill
1★ repoRun any question, idea, or decision through a council of 5 AI advisors who independently analyze it, peer-review each other anonymously, and synthesize a final verdict. Based on Karpathy's LLM Council methodology. MANDATORY TRIGGERS: 'council this', 'run the council', 'war room this', 'pressure-test this', 'stress-test this', 'debate this'. STRONG TRIGGERS (use when combined with a real decision or tradeoff): 'should I X or Y', 'which option', 'what would you do', 'is this the right move', 'validate this', 'get multiple perspectives', 'I can't decide', 'I'm torn between'. Do NOT trigger on simple yes/no questions, factual lookups, or casual 'should I' without a meaningful tradeoff (e.g. 'should I use markdown' is not a council question). DO trigger when the user presents a genuine decision with stakes, multiple options, and context that suggests they want it pressure-tested from multiple angles.
SaltGardenia/research-code-skill Skill
1★Coding-standard enforcer for AI agents working inside a research (ML/DL) lab project. Its core job is twofold: (1) keep the project's fixed architecture intact across all coding work 鈥?never break or drift from the established structure; (2) enforce code-level conventions 鈥?naming, formatting, calling, and configuration 鈥?so every file is uniform. It codifies five authoritative systems as machine-executable Rule Cards (RC-*). It fuses thirteen authoritative references into four usage clusters so the agent never stacks them as separate checklists, plus a Karpathy-inspired behavioral discipline (Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven Execution) layered above the mechanical cards: (1) Project Scaffold & Python Grammar (Lightning-Hydra-Template structure + Hydra configs + Google Python Style); (2) Model & Component Design (PyTorch Lightning Style Guide + timm named architectures + OpenMMLab Registry pattern); (3) Experiment Reproducibility (Hydra Config-First + FAIR data + SemVer/Git Flow + Meta Research philosophy); (4) Engineering Process (Software Engineering at Google + Scientific-Python idiom). It operates in two scenarios: build from zero (A) or tidy an existing repo (B). It is NOT a post-hoc reviewer: it constrains code as it is written. Trigger on any code task: "add a model", "write a training script", "refactor this module", "create the project scaffold", "name this function", "add a config group", "manage dataset metadata", "tag this experiment release", or "what structure should this file use".
simanam/theaiteam/team/skills/architecture/api-design Skill
no license1★ repoREST API design patterns including resource naming, status codes, pagination, filtering, error responses, versioning, and rate limiting for production APIs.
The same file is in 11 other repositories
Ewanjohndennis/engineering-standard-skills Skill
1★Apply rigorous engineering standards when writing, refactoring, debugging, or reviewing Python, Java, or C code. Loads calibration and language-specific guidance automatically.