helium-mcp
ComposioHQ/awesome-codex-skills/helium-mcp/SKILL.md
Search real-time news with bias scoring, get live stock/ETF/crypto data with AI analysis, ML options pricing, balanced news synthesis, and meme search via the Helium MCP server.
One search for your own team's files and the public ecosystem. See how real projects write their agent instructions, and bring the good ideas home.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
ComposioHQ/awesome-codex-skills/helium-mcp/SKILL.md
Search real-time news with bias scoring, get live stock/ETF/crypto data with AI analysis, ML options pricing, balanced news synthesis, and meme search via the Helium MCP server.
tangency-labs/solidcraft/skills/solidcraft-modeling/SKILL.md
Use when building a new part, enclosure, bracket, plate, flange or any other 3D solid in SolidCraft through its MCP server (tools such as batch, execute, measure, screenshot), or when a SolidCraft session is using many tool calls or tokens.
bherbruck/solidcraft/skills/solidcraft-modeling/SKILL.md
Use when building a new part, enclosure, bracket, plate, flange or any other 3D solid in SolidCraft through its MCP server (tools such as batch, execute, measure, screenshot), or when a SolidCraft session is using many tool calls or tokens.
2 projects use a version of this
novuhq/novu/.agents/skills/nv-onboard-dcr-mcp/SKILL.md
Onboard a new DCR OAuth MCP catalog entry with provider-doc vetting and curl probes. Use when adding or changing `mode: dcr` entries in MCP_SERVERS. Abort if the provider requires whitelist or manual approval.
No other project uses it yet
google/adk-recipes/core/python/long-horizon-harness/horizon/builtin_skills/bootstrap-google-tools/SKILL.md
Install/auth CLIs the sandbox lacks - `gws` (Drive, Gmail, Sheets, Calendar), `gcloud`, `agents-cli`, `mcp-cli` (MCP servers). Use on "command not found" or before GCP/Workspace/MCP work.
Steady5 mentions in 2 weeks
1 project uses a version of this
AgriciDaniel/claude-seo/skills/seo-posthog/SKILL.md
PostHog MCP extension. PostHog analytics as a GA4 alternative or complement. Organic traffic, landing pages, device / country breakdowns, referrers, via the PostHog MCP server. Triggers on "PostHog", "posthog analytics", "GA4 alternative", "product analytics SEO".
topoteretes/cognee/.agents/skills/cognee-integrations/SKILL.md
Use when the user wants to connect cognee to external services — switching LLM or embedding providers (OpenAI, Azure, Gemini, Anthropic, Ollama, OpenRouter), changing databases (Postgres, PGVector, Neo4j, Neptune, Turso), S3 storage, or the MCP server for IDE integration.
Steady7 mentions in 2 weeks
No other project uses it yet
pinchtab/pinchtab/skills/pinchtab-mcp/SKILL.md
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
wanshuiyin/Auto-claude-code-research-in-sleep/skills/auto-review-loop-llm/SKILL.md
Autonomous research review loop using any OpenAI-compatible LLM API. Configure via llm-chat MCP server or environment variables. Trigger with "auto review loop llm" or "llm review".
Steady5 mentions in 2 weeks
2 projects use a version of this
wanshuiyin/Auto-claude-code-research-in-sleep/skills/skills-codex/auto-review-loop-llm/SKILL.md
Autonomous research review loop using any OpenAI-compatible LLM API. Configure via llm-chat MCP server or environment variables. Trigger with \"auto review loop llm\" or \"llm review\".
Steady5 mentions in 2 weeks
2 projects use a version of this
open-ani/animeko/.agents/skills/datasource-test/SKILL.md
Test and debug an Animeko media source from its JSON config using the datasource-test-mcp HTTP MCP server. Validates selector config syntax offline, runs the real SelectorMediaSourceEngine pipeline (searchSubjects → selectSubjects → searchEpisodes → selectEpisodes → selectMedia) with per-step traces, iterates CSS selectors offline against saved HTML, tests matchVideo regexes, extracts real video URLs via CEF WebView, and probes actual playback with VLC. Use when asked to 测试数据源 / 调试 selector 配置 / verify a datasource JSON works / diagnose why a source finds no candidates for an episode or fails to play. Covers web-selector (CSS selector) sources in depth; other factories (rss/dmhy/mikan/jellyfin/...) via end-to-end testing. Also defines the capability-evolution (进化) loop: when a site is provably beyond current engine/WebVideoExtractor capabilities, write a capability-gap document and hand it to an isolated subagent that implements the new capability and outputs a git patch, then re-verify. Works exclusively through the `ani-datasource-test` HTTP MCP; it never starts the server itself — if that MCP is not configured the skill stops and tells the user how to add it. When a `chrome-devtools` MCP is also available, it is used as the real-browser ground truth (rendered DOM, real network requests, click interactions) to distinguish config mistakes from genuine engine/extractor capability gaps.
No other project uses it yet
github/awesome-copilot/skills/aspire/SKILL.md
Aspire skill covering the Aspire CLI, AppHost orchestration, service discovery, integrations, MCP server, VS Code extension, Dev Containers, GitHub Codespaces, templates, dashboard, and deployment. Use when the user asks to create, run, debug, configure, deploy, or troubleshoot an Aspire distributed application.
17 projects use a version of this
addyosmani/agent-skills/skills/browser-testing-with-devtools/SKILL.md
Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data. Requires the chrome-devtools MCP server to be configured.
62 projects use a version of this
Often used withdeprecation-and-migrationconstraint-driven-developmentdoubt-driven-development
mcp-use/mcp-use/skills/manufact-analytics/SKILL.md
Query deployed MCP server usage, errors, latency, clients, and actors through the Manufact Cloud CLI using a live catalog and read-only SQL. Use for server analytics questions, not PostHog CLI adoption tracking or analytics configuration.
Steady8 mentions in 2 weeks
No other project uses it yet
google/adk-recipes/core/python/adk-voice-agent/sandbox/skills/connected-apps-mcp/SKILL.md
The `voice_agent` MCP server: the user's connected apps (Calendar, Gmail, Drive, Docs, Sheets, Slides, GitHub), the thread journal, memory, grounded search, talking to the user, and saving deliverables to Drive. Use before calling its tools.
Steady5 mentions in 2 weeks
1 project uses a version of this
apify/apify-mcp-server/.claude/skills/dig/SKILL.md
Explore, analyze, plan, or spec features for the Apify MCP server. Adapts to what the user asks — from quick code exploration to full GitHub issue specs. Use when the user asks to explore code, understand behavior, plan a change, design a feature, or create an issue spec.
Steady5 mentions in 2 weeks
6 projects use a version of this
microsoft/ai-agents-for-beginners/translations/fi/.agents/skills/local-ai-agents/SKILL.md
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and privacy, cost, and offline trade-offs.
Steady33 mentions in 2 weeks
No other project uses it yet
microsoft/ai-agents-for-beginners/translations/hi/.agents/skills/local-ai-agents/SKILL.md
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and privacy, cost, and offline trade-offs.
Steady33 mentions in 2 weeks
No other project uses it yet
microsoft/ai-agents-for-beginners/translations/hr/.agents/skills/local-ai-agents/SKILL.md
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and privacy, cost, and offline trade-offs.
Steady33 mentions in 2 weeks
No other project uses it yet
microsoft/ai-agents-for-beginners/translations/ne/.agents/skills/local-ai-agents/SKILL.md
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and privacy, cost, and offline trade-offs.
Steady33 mentions in 2 weeks
No other project uses it yet
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.