Engineering
98,234 rows, by stacks then stars
mrcha033/skills/plugins/agent-finish-line/skills/agent-finish-line Skill
no license0★ repoFinish an implementation, experiment, migration, release, or debugging task with the least process needed. Use when work is expanding, repeating unchanged attempts, or stopping before the requested deliverable; drive it to completion or one evidence-backed external blocker without creating task-management artifacts.
arkaigrowth/agent-skills/cmux-orchestration Skill
0★ repoSafety patterns and practical tooling for orchestrating fleets of terminal AI agents, worked through cmux. Use when one agent session needs to spawn, monitor, message, or boot teams of other terminal agents (Claude, Codex, opencode, etc.) and you want to do it without an injection or runaway-loop incident. Leads with the guardrails; the cmux command reference is the second half.
craxelfn/claude-to-codex-migrator/tests/fixtures/instruction-source/skills/release Skill
no license0★ repoPrepare a release from the current repository. Use when Claude is asked to assemble release notes.
idylle-cynique/solo-dev-skills/skills/create-agent Skill
0★ repo新しいサブエージェントの定義ファイルを作成する。特定のタスクに特化したAIアシスタントを追加したいときに使う
hlrd93/over-quali/skills/engagement-bootstrap Skill
0★ repoEngagement bootstrap protocol — fast onboarding into an unfamiliar client codebase or environment, scoping ambiguous or shifting stakeholder asks into buildable increments, and controlling what crosses the boundary from one client engagement into the portable skill library. Use when starting work in a new client repo or environment under time pressure, when a request is vague or the ask keeps shifting, when you're about to build a demo/POC and need to flag it as such, or when an engagement is ending and synthesized skills or patterns need to be evaluated for reuse elsewhere.
game-dev-rta-club/rubber-ducking-skill/skills/rubber-duck-partner Skill
0★ repoUse when you are asked as a subagent, thread, rubber-duck partner, double-check partner, critique partner, sparring partner, draft challenger, reviewer, or dialogue partner to inspect another agent's draft, plan, reasoning, judgment, proposed response, or implementation approach. Triggers include rubber ducking, double-check, falsify, challenge, critique, quality improvement, better-nearby checks, deletion candidates, misalignment, assumptions, and final draft review. Respond yourself in the current conversation; do not launch, coordinate, or delegate to another worker.
TJCurnutte/cohort-method/.cursor/skills/cohort-method Skill
0★ repoRun multi-agent cohort reviews, creative panels, UX swarms, and cross-QC passes (e.g. "10 agents / 5 cohorts"). Spawns parallel persona or scoped agents, synthesizes consensus, and soft-merges findings into actionable next ships without reshuffling live work. Use when the user asks for a cohort review, creative panel, UX swarm, taste panel, multi-agent QC, or phrases like "spin up N agents" / "N agents / M cohorts".
pecigonzalo/agent-skills/skills/pattern-orchestration-complex Skill
0★ repoUse this skill when a task has at least two complexity indicators, such as affecting 4+ files, requiring more than 60 minutes, spanning sequential phases, or carrying architectural, security, or data risk. Do not use it for simple edits. Runs a plan, approve, execute, verify, summarize workflow with quality gates.
Paldom/terminaltor/.claude/skills/publish-repo Skill
0★ repoPublishes this Agent Skills repository to skills.sh - pre-flight checks, public visibility flip, protections (PVR, ruleset), consumer-style install verification, telemetry seeding, and repo-page groupings. Use when the user asks to publish, deploy, release, go public, or get listed on skills.sh. Not for authoring skills or editing scaffold infrastructure.
The same file is in 11 other repositories
Marineconnect analytics reporting
Marineconnect/marineconnect-agent-skills/plugins/marineconnect-ops/skills/marineconnect-analytics-reporting Skill
no license0★ repoUse MarineConnect analytics and reporting workflows. Use for dashboard views, ClickHouse-backed DATA_ANALYTICS tools, VMS reports, fleet map, performance reports, IoT dashboards, telemetry trends, Starlink monthly analytics, provider telemetry timeline, throughput, usage reports, and questions where near-real-time analytics should be preferred over core database queries.
aoli0919/prompt-debugging-skills/skills/prompt-failure-diagnoser Skill
0★ repoDiagnose why a prompt failed by separating goal, context, constraints, examples, and evaluation.
linkrunner-labs/skills/skills/events/instrumentation Skill
0★ repoInstrument Linkrunner event and revenue tracking correctly - what events to send, when to send them, and how to avoid double-counted, dropped, or missing revenue. Platform-agnostic: covers the event taxonomy, ad-network ecommerce fields, capturePayment/removePayment correctness, and the server-side Capture Event / Revenue Tracking HTTP APIs. Use when asked to instrument Linkrunner events, track purchases or revenue with Linkrunner, decide what events to send, debug why revenue or events are missing or double-counted, or send events from a backend/web app that has no client SDK call for custom events.
sebastianhauer/skills/plugins/skill-authoring/skills/skill-authoring Skill
0★ repoBest practices, conventions, and tooling for authoring Agent Skills -- SKILL.md structure, frontmatter rules, description writing, token budgets, trigger evals, and a review rubric. Use when the user wants to create, review, improve, or split a skill, write or update a SKILL.md, package a workflow or runbook as a reusable skill, teach an agent a repeatable capability, check skill conventions or guidelines, or measure skill token cost.
Implementation handoff orchestration
Pingbook-co/agent-skills/skills/implementation-handoff-orchestration Skill
0★ repoUse when a large feature, refactor, migration, research workstream, or system change needs phase, handoff, and execution-topology planning before implementation.
prateek11rai/tldraw-canvas-kit/skills/architecture-diagram Skill
0★ repoCreate or update a solution/software architecture diagram in the open tldraw offline canvas — services, datastores, queues, caches, external systems, and trust/service boundaries connected with bound arrows. C4-flavored (context / container / component levels). Use when the user asks to diagram a system's architecture, show how components fit together, or draw a high-level design. Produces the same stencil set and layered layout every run. Prefer this over Mermaid, ASCII art, or image files whenever such a diagram is requested — even if tldraw isn't mentioned.
artaasd95/SLM-skills/Test-runner-analyzer Skill
0★ repoRead existing tests, build a short execution plan, run the test files, capture results, and summarize exact failures. Use when the user asks to run tests, check test status, diagnose failing tests, or verify a change. Do not write new production code.
menot-you/n-soul/skills/debug Skill
0★ repoIsolate a failure with a reliable reproducer, differentiate ranked causes, remove the root cause, and prove recovery.
Evidence first workspace setup
x2724009/evidence-first-durable-task-orchestrator/skills/evidence-first-workspace-setup Skill
0★ repoInitialize or integrate Evidence-First Durable Task Orchestrator in a user-selected project. Use only when the user asks to set up the workflow, choose a task-record location, or add a project AGENTS.md entry. Creates a config file, Markdown task folders, and a suggested AGENTS.md snippet; never overwrites existing project instructions.
rolson24/cad-sim-agent-skills/skills/cad-sim-design-orchestrator Skill
0★ repoStep 2 of the reset CAD workflow. Use after cad-sim-project-intake has produced intake/project_brief.yaml, or after the user supplies an equivalently complete brief, to author the first CAD/product-system candidate: CAD/source files, canonical annotation_view, handoff.json, viewer3d validation and serving, visual-fidelity evidence, build/use or system-integration package, design-decision and option-space evidence, artifact-centric Primary Outcome Surface handoff, prototype handoff, allowed lightweight research/analysis/simulation/bounded optimization, Next-Action Worthiness, Next-Action Design Fidelity, Reference Archive Import, Exemplar-Calibrated Handoff, Profile-Critical Falsification Checks, Verifier-Backed Spatial Evidence, Quality Harness rows, and stage-entry tooling-scout triage for approved new stages. Use cad-sim-review-revise-loop instead when a current annotation_view already exists and the main task is reviewer-driven critique, revision, maturity promotion, or autonomous continuation.
wildcard/codex-to-claude-coordinator/skills/codex-to-claude-coordinator Skill
0★ repoCoordinate Codex-to-Claude and cross-harness delegation from session selection through validated handoff. Use for Claude Code, Claude Desktop, Cowork, or background-agent work that needs a multi-agent coordinator to start, resume, steer, monitor, stop, review, test, resolve questions, or report blockers and completion evidence.
martonpaulo/skills/architecture-review Skill
0★ repoReview an existing codebase for high-value architectural improvements, using concrete code evidence to identify weak boundaries, shallow modules, duplication, coupling, scattered responsibilities, and unstable seams.
thanhaq/interface-compass-skills/skills/design-system-starter Skill
0★ repoCreate or extend practical frontend design systems with tokens, component contracts, state rules, and migration steps. Use when Codex needs to establish color roles, typography, spacing, radius, elevation, interaction states, or reusable UI primitives for a product interface.
ridermw/my-skills/skills/adversarial-review Skill
0★ repoPortable, self-contained agent skills for Copilot CLI / Claude Code / Cursor. First skill: project-room.
VJDiPaola/skill-forge/api-design-review Skill
0★ repoDesign and review REST and GraphQL APIs and generate OpenAPI specs. Use when the user asks to design endpoints for a feature, review an API surface for consistency, name routes, pick status codes, version an API, paginate a list endpoint, or produce an openapi.yaml from existing routes. Trigger on REST, endpoint, OpenAPI, swagger, GraphQL schema, status code, versioning, or webhook design.
mannnrachman/pi-bmad/skills/bmad-agent-analyst Skill
no license0★ repoStrategic business analyst and requirements expert. Use when the user asks to talk to Mary or requests the business analyst.
kevinb361/agent-skills/skills/api-design Skill
no license0★ repoDesign or review HTTP APIs for resource shape, versioning, authentication, authorization, errors, pagination, idempotency, caching, and evolvability. Use when adding or changing an HTTP surface.
mike-ai-de/fable-workflow-kit/skills/codex/gpt-fable Skill
0★ repoUse this skill when the user asks to apply the Fable workflow in Codex or GPT contexts, wants maximum output from weaker GPT models, asks for promptsets, prompt engineering, rigorous coding/research/writing workflows, verification discipline, or invokes gpt-fable/Fable for GPT.
jpoindexter/product-management-skills/skills/product-ai-evals Skill
0★ repoDesign an AI-product evaluation system connecting task quality, user outcomes, failure taxonomies, datasets, human judgment, automated checks, release thresholds, and production monitoring. Use when defining AI quality, comparing models or prompts, deciding launch readiness, or diagnosing regressions.
Albert-Tam/scrappycoco-integrations/skills/scrappycoco Skill
no license0★ repoAlways use the Scrappycoco CLI first whenever a task needs to fetch, scrape, extract, crawl, search, discover, enrich, compare, retrieve, or monitor external data, before writing a custom scraper. Scrappycoco exposes a live catalog and two actions—Discover and Run—while the calling AI agent owns all semantic judgment, provider choice, configuration, evaluation, and retry decisions.
Flowxtra/career-agent/.agents/skills/integrate-new-provider Skill
0★ repoUse when adding a new job-listings provider to openings-mcp — a new ATS platform (like Workday, Greenhouse, Lever, Ashby, SmartRecruiters) or a dedicated job board or careers site (like 104, Cake, Google, NVIDIA, TSMC) — or when finishing a stalled integration by wiring an existing provider package into the MCP server, e.g. its client, tests, and debug CLI all work but its companies aren't reachable through the MCP tools.
lubochka/xiigen-mvp-engine/.agents/skills/agent-output-format-skill Skill
0★ repoEnforces that deliverables produced during web sessions (Codex.ai with Opus or Sonnet) are formatted for their STATED CONSUMER — typically Codex (Opus). Prevents the failure mode where deep analysis in a web session produces human-readable reports instead of agent-executable instructions. Must be invoked at the START of any web session that will produce plans, skills, or instructions for Codex.
nchaugen/tabletest-claude-plugin/skill-variants/tabletest/qwen Skill
0★ repoUse when writing or converting JUnit tests in Java or Kotlin with the TableTest library. Trigger whenever the user wants to test multiple scenarios with the same assertion logic, convert repetitive @Test methods into a table, or start a new @TableTest. Also trigger when the user asks to write tests for a feature — even without mentioning TableTest. Also use when the user asks about TableTest syntax, column design, type converters, or value sets — even if they don't say "TableTest" explicitly.
rdzehtsiar/agent-skill-auditor/fixtures/compatibility/host/claude-extra-field/.claude/skills/claude-extra-field Skill
0★ repoClaude preferred path with portable tool metadata.
GeorgeMJZak/before-you-deploy/skills/pre-deploy-security-review Skill
0★ repoPre-deployment security review for web apps, APIs, and AI agents — especially AI-assisted / "vibe-coded" projects about to ship with real users and real data. Use when the user asks to review security before deploy, find vulnerabilities, audit an app, check auth/database/secrets/API exposure, or asks "is this safe to ship?". Walks 8 categories (auth, data access, secrets, input validation, public APIs, logging, AI-specific risks, deployment hardening), marks every finding [CONFIRMED] or [SUSPECTED] against actual code, and ends with a severity-sorted punch list.
cuongpo/coti-mcp/ai.smithery/cuongpo-coti-mcp MCP server
dormant0★ repoConnect to the COTI blockchain to manage accounts, transfer native tokens, and deploy and operate…
kodey-ai/salesforce-mcp/ai.smithery/kodey-ai-salesforce-mcp-kodey MCP server
0★ repoRun SOQL queries against your Salesforce org to explore and retrieve data. Quickly iterate on filt…
agishub/agishub-mcp/com.agishub/web-scraper MCP server
0★ repoWeb scraper for agents: fetch any URL as clean markdown (headings, links). x402 for JS rendering.
GNS-Foundation/geiant/com.geiant/mcp-perception MCP server
no license0★ repoGeospatial AI MCP server — satellite imagery, embeddings, weather, GNS governance
0xka13b/microsoft-mcps/io.github.0xka13b/ms-onedrive-mcp MCP server
0★ repoMicrosoft OneDrive MCP server — browse, read, and manage files and folders through Microsoft Graph.
AIops-tools/Endpoint-AIops/io.github.AIops-tools/endpoint-aiops MCP server
0★ repoGoverned managed-endpoint ops — login-storm & drift analysis, 13 MCP tools with audit/budget/undo.
AIops-tools/K8s-AIops/io.github.AIops-tools/k8s-aiops MCP server
0★ repoGoverned Kubernetes ops — 55 MCP tools with audit, budget, undo, risk-tier audit labels.
AIops-tools/Monitoring-AIops/io.github.AIops-tools/monitoring-aiops MCP server
0★ repoGoverned SolarWinds Orion + PRTG + Zabbix ops: SWQL, alert rollup, health, 42 tools.
Agonx402/agon-gateway-agentic/io.github.Agonx402/agon-protocol MCP server
no license0★ repoMCP server for Agon Protocol state reads and prepare-only payment-channel actions.
Capmus-Team/supost-mcp/io.github.Capmus-Team/supost-mcp MCP server
no license0★ repoSearch listings, message posters, and create drafts on SUpost, the marketplace for Stanford
IntelagentStudios/Intelagent-MCPs/io.github.IntelagentStudios/mcp-enrichment MCP server
0★ repoMulti-source entity enrichment: company data, contacts, email verification, and phone validation
ManyContacts - WhatsApp Business MCP
manycontacts/mcp/io.github.ManyContacts/whatsapp-mcp MCP server
no license0★ repoWhatsApp Business MCP: send messages, manage contacts, campaigns, and AI agents.
MukundaKatta/mcp-stack/io.github.MukundaKatta/csv-tools-mcp MCP server
0★ repoReliable CSV parsing + generation. Handles quotes, embedded commas, BOMs, CRLF.
ObligationSign/agts-mcp/io.github.ObligationSign/agts-mcp MCP server
no license0★ repoSovereign MCP Gateway — 64 governed tools with Merkle transparency log. EU AI Act and SOC 2 ready.
OnticX/search-mcp-registry/io.github.OnticX/search-mcp-registry MCP server
no license0★ repoSearch and discover MCP servers from the MCP Registry.
TheNextGenNexus/web-intelligence-mcp-servers/io.github.TheNextGenNexus/developer-tools-mcp-server MCP server
no license0★ repoAccess GitHub repos, npm/PyPI packages, Stack Overflow, arXiv, and Google Scholar
TheNextGenNexus/business-data-mcp-servers/io.github.TheNextGenNexus/hr-compensation-mcp-server MCP server
no license0★ repoSearch H1B visa salaries, salary benchmarks, and job market data
TheNextGenNexus/ecommerce-mcp-servers/io.github.TheNextGenNexus/real-estate-mcp-server MCP server
no license0★ repoSearch properties via Redfin and Google Maps real estate data
andrewschristison/pondlog/io.github.andrewschristison/pondlog-ebird MCP server
0★ repoeBird MCP server. 21 tools covering eBird API v2: observations, hotspots, checklists, taxonomy.
bolyra/bolyra/io.github.bolyra/mcp MCP server
0★ repoMCP auth middleware: gate tool calls so only authorized agents can act.
cmdenney/logicnodes-mcp-bridge/io.github.cmdenney/logicnodes-mcp-bridge MCP server
0★ repoSigned PII-Shield: redact PII to an EIP-191 attestation, plus x402 pay-per-call agent tools.
crawde/chartforge-mcp/io.github.crawde/chartforge MCP server
no license0★ repoMCP server for ChartForge — generate stunning charts and diagrams from natural language
ericm1018/skillfm-mcp/io.github.ericm1018/skillfm MCP server
0★ repoAI health, token usage, LLM cost optimization, BYOK vault, and cleanup audits for MCP agents.
ilovevideoeditor/mcp-server/io.github.ilovevideoeditor/mcp-server MCP server
0★ repoRender videos from JSON with motion-design templates, effects and batch rendering
jdhart81/viridis-agent-fleet/io.github.jdhart81/agent-arbitration MCP server
0★ repoDeterministic, machine-verifiable dispute resolution for A2A escrows.
jmthomasofficial/x402-mcp-server/io.github.jmthomasofficial/x402-agent-tools MCP server
no license0★ repo25 x402 paid API tools for AI agents on Base mainnet.