Loading…
Showing 4861–4890 of 10175 skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| youtube-datasuperagnt/leverageYouTube channels, videos, transcripts, and comments for agents — no Google API key or daily quota to manage. | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| nobrainer-autoimprovenobrainer-tech/nobrainer-tech-flowUse when a skill or prompt needs to improve and a measurable, bounded baseline-variant-evaluation loop should replace one subjective rewrite. Aliases: nb-autoimprove, deep-autoresearch, code-autoresearch, nobrainer-capture-lesson, nobrainer-continuous-improvement. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| ask-mattJarvvski/jjfxAsk which skill or flow fits your situation. A router over the skills in this repo. | Stars: 43 | Updated | Claude CodeCodex | Verified | Install |
| code-reviewJarvvski/jjfxReview the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X". | Stars: 43 | Updated | Claude CodeCodex | Verified | Install |
| teachJarvvski/jjfxTeach the user a new skill or concept, within this workspace. | Stars: 43 | Updated | Claude CodeCodex | Verified | Install |
| writing-great-skillsJarvvski/jjfxReference for writing and editing skills well — the vocabulary and principles that make a skill predictable. | Stars: 43 | Updated | Claude CodeCodex | Verified | Install |
| tosca-agentsTricentis/mcp-skillsList, view, shut down, or delete execution agents in Tosca Cloud | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| tosca-cloud-basicsTricentis/mcp-skillsExplains how to work with Tricentis Tosca Cloud through toscactl: workspaces, assets, playlists, runs, and the core command loop. Use as foundation before other Tosca Cloud skills. Builder/DI/mobile gaps use tn — see runtime-routing.md. Does NOT cover detailed DI orchestration (use tosca-cloud). | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| tosca-cloud-connectTricentis/mcp-skillsConnects toscactl to Tosca Cloud — login, workspace selection, and connectivity check. Use when setting up toscactl, fixing auth errors, or before any other Tosca Cloud skill. For tn gap workflows only, also run configure_tn_connection.py. Does NOT cover direct IDE MCP. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| tosca-cloud-connectTricentis/mcp-skillsVerifies hosted Tosca Cloud MCP connectivity and routes to the right Cloud skills. Use when the user is setting up Cloud MCP, fixing 401 errors, or before other Tosca Cloud skills. Does NOT configure MCP servers — the user adds their tenant in the host (IDE settings or Copilot CLI `copilot mcp add`). | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| verify-oceans-adminahstn/oceans-llmVerify the Oceans LLM admin control plane and backend gateway against the real local stack, seeded demo data, and bounded live providers when required. Use for user-path checks of sign-in, models, API keys, observability, usage costs, spend controls, batches, agent sessions, request logs, Anthropic Messages thinking and effort compatibility, MCP registry and tool access, OpenRouter routing, guardrails, and Skills storage. | Stars: 1 | Updated | Claude CodeCodex | Verified | Install |
| interview-meJPeetz/agent-skillsUse this skill when an ask is underspecified — missing who it's for, why now, or what success looks like. One-question-at-a-time interview to extract what the user actually wants (not what they think they should want) before any plan, spec, or code exists. Requires a live, responsive user — do not invoke in non-interactive contexts (CI runs, scheduled tasks, autonomous loops). | Stars: 19 | Updated | Claude CodeCodex | Verified | Install |
| cve-remediationNVIDIA-AI-Blueprints/Retail-Agentic-CommerceDiscoverability shim for the Retail-Agentic-Commerce CVE remediation Codex skill. Use for CVE, BDSA, GHSA, OSV, Dependabot, Black Duck, Snyk, npm, PyPI, or package advisory remediation. | Stars: 88 | Updated | Claude CodeCodex | Verified | Install |
| pre-commit-analysisNVIDIA-AI-Blueprints/Retail-Agentic-CommerceDiscoverability shim for the Retail-Agentic-Commerce pre-commit analysis Codex skill. Use before commits, after significant changes, or for implementation-quality validation. | Stars: 88 | Updated | Claude CodeCodex | Verified | Install |
| setupNVIDIA-AI-Blueprints/Retail-Agentic-CommerceDiscoverability shim for the Retail-Agentic-Commerce setup Codex skill. Use when the user asks to setup, install, start, launch, or run the project stack. | Stars: 88 | Updated | Claude CodeCodex | Verified | Install |
| planningdayfinggg/openai-codex-agent-skillsBreaks work into ordered, verifiable tasks before implementation. Use it whenever the user asks for a plan, a roadmap, or an estimate, when requirements or a spec must become tasks, when the work spans several modules, sessions, or agents, or when a task feels too large or vague to start. Skip it for a change whose scope and order are already obvious. | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| otel-semantic-conventionssb-dev/openquantOpenTelemetry Semantic Conventions expert. Use when selecting, applying, or reviewing telemetry attributes. Triggers on tasks involving attribute selection, semantic convention compliance, attribute migration, or custom attribute decisions. Covers the attribute registry, naming patterns, attribute placement, and versioning. For span names, span kinds, and span status codes, see the otel-instrumentation skill. | Stars: 1 | Updated | Claude CodeCodex | Verified | Install |
| video-editing-skillsocial-media-skills/video-editing-skillVideo editing skill: edit a talking-head video (YouTube video, course lesson, product demo, podcast on camera, vlog) the way an editor would. Transcribes with word timestamps (free local faster-whisper, your own Groq or OpenAI key, or an existing SRT/VTT), removes silences, "um"s and "uh"s, stutters and retakes (keeps the last take), adds jump-cut punch-ins, cleans and levels the audio, writes an SRT caption file and YouTube chapters, optionally burns captions or makes a vertical version, shows a cut list to approve before rendering, then posts to YouTube and other platforms with WoopSocial after you say yes. Works on Mac, Windows and Linux with ffmpeg and Pillow; no paid API required. Use when someone says "edit my video," "remove silences," "cut the ums," "remove filler words," "jump cut my video," "clean up this recording," "edit this talking head video," or "video editing with Claude Code." Never cuts what the user marked to keep, confirms before anything posts. Standalone: needs no other skills. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| client-revisionsiart-ai/freelance-motion-skillsThis skill should be used when the user asks to "stop scope creep", "limit revision rounds", "write SOW revision language", "the client keeps asking for changes", "how do I say this is out of scope", "translate vague feedback", "client said make it pop", or "write a change-order email". It provides revision-cap contract language, a consolidated-feedback request, a vague-feedback translator, and a polite out-of-scope email. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| git-commitpivoshenko/pivoshenko.aiRun git commit using Angular conventional commit format (header + footer only, no body). Use when the user asks to commit, create a commit, /git-commit, or save changes to git. Also trigger on "snapshot this", "save my work", "check in changes", "wrap up", "ship this locally", or whenever the user finishes a logical unit of work and the tree is dirty. Boundary with `git-pr-create`: this skill owns only the explicitly local framing - bare "ship this" / "ship it" / "send for review" means the work should leave the machine, which is `git-pr-create`'s flow. Stages relevant files and commits immediately without asking for confirmation. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| git-issue-createpivoshenko/pivoshenko.aiOpen one standalone GitHub issue with `gh` - duplicate-checked first, conventional title, repo-template-aware body, auto-resolved labels. Use for every issue-filing request however casual: "open an issue", "file a bug", "make a ticket", "/git-issue-create", "track this", "note this down", "we should fix X later", or whenever the user describes a defect or wanted capability that is clearly not being built right now. A raw `gh issue create` skips the duplicate search, label resolution, and body caps this skill owns. Boundary: work starting now goes to `git-branch-create`; an issue that already exists goes to `git-issue-start`. Creates the issue immediately without asking for confirmation. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| git-issue-startpivoshenko/pivoshenko.aiTake a GitHub issue from open to a checked-out branch - assign it to you, mark it in progress if the repo has such a label, derive a conventional branch name from its `type: *` label, branch off the detected base. Use for "start issue 42", "work on #42", "/git-issue-start 42", "let's do 42", "pick up that issue", "take the oauth issue", "I'll take this one", or whenever the user points at a tracked issue and is about to write code for it. Resolves an issue named by title via `gh issue list --search`. Boundary: with no issue in play it is `git-branch-create`'s, and this skill delegates naming and base detection to it. Assigns and branches immediately without asking for confirmation. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| git-pr-createpivoshenko/pivoshenko.aiOpen a GitHub pull request for the current branch using `gh` - conventional title, repo-template-aware body, auto-derived labels, push if needed. Use for every PR-creation request however casual: "create/open/raise a PR", "PR this", "send PR", "/git-pr-create", "ship this", "ship it", "send for review", "ready for review", "publish this branch", or whenever the user signals work on a feature branch should leave their machine. A raw `gh pr create` skips the push, label derivation, title format, and safety rules this skill owns. Boundary with `git-commit`: an explicitly local framing ("commit this", "save my work", "ship this locally") stops at a commit. Pushes the branch and opens the PR immediately without asking for confirmation. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| herdr-dispatchpivoshenko/pivoshenko.aiRun a task list across parallel visible Herdr workers - one tab per worker in the Herdr app (`hc` plus `herdr-app`), or a budgeted pane grid in the Herdr TUI (`herdr`) - start one agent per task, brief it, collect results from files, handle blocked workers, clean up. Use when the user says "dispatch these", "run these in parallel", "fan this out", "spin up agents", "/herdr-dispatch", or whenever the `herdr-workflow` instruction sends delegated work to Herdr. That instruction holds the policy; this is the mechanics. Full CLI references -> `hc --skill` and `herdr-app --skill` in the app. Requires HC_TERMINAL_ID (app) or HERDR_ENV=1 (TUI). | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| monte-carlo-analyze-root-causemonte-carlo-data/mc-agent-toolkitInvestigate data incidents and find root causes using Monte Carlo's observability data. Guides the agent through systematic investigation: alert lookup, lineage tracing, ETL checks, query analysis, and data profiling. Activates when a user asks about data issues, incidents, alerts, or why data looks wrong. | Stars: 94 | Updated | Claude CodeCodex | Verified | Install |
| monte-carlo-manage-macmonte-carlo-data/mc-agent-toolkitCreate, edit, validate, and import Monitors-as-Code YAML files. CLI-first; falls back to MC MCP tools, then manual validation. | Stars: 94 | Updated | Claude CodeCodex | Verified | Install |
| monte-carlo-storage-cost-analysismonte-carlo-data/mc-agent-toolkitAnalyze a warehouse for stale, unused, or redundant tables via the analyze_storage_costs MCP tool. Classifies waste patterns and table categories, computes safety tiers, and handles category drill-downs and lineage follow-ups. | Stars: 94 | Updated | Claude CodeCodex | Verified | Install |
| monte-carlo-troubleshoot-agent-tracesmonte-carlo-data/mc-agent-toolkitTroubleshoots Monte Carlo AI agent alerts and traces — eval score drops, latency/token spikes, trajectory and validation breaches. Not for data incidents (monte-carlo-analyze-root-cause) or monitor creation (monte-carlo-monitoring-advisor). | Stars: 94 | Updated | Claude CodeCodex | Verified | Install |
| zoom-cobrowse-sdkzoom/skillsZoom Cobrowse SDK for web - JavaScript SDK for real-time collaborative browsing between agents and customers. Features include annotation tools, privacy masking, remote assist, and PIN-based session sharing. | Stars: 93 | Updated | Claude CodeCodex | Verified | Install |
| zoom-mcp/canvaszoom/skillsZoom Canvas MCP server guidance for Canvas file and block operations, collaborators, sharing settings, ownership, Markdown import, and content export. Use for the current Canvas MCP endpoint and OAuth scopes; use the parent Zoom MCP skill for server selection. | Stars: 93 | Updated | Claude CodeCodex | Verified | Install |