Loading...
Loading...
Found 5,444 Skills
Reverse-engineer defense implementations → Targeted bypass for red teams. First reverse-engineer the hook tables, ETW providers, and AMSI implementations of EDR / Defender / AV, then develop targeted unhook / indirect syscall / ETW patch / call stack spoof solutions. Align with MITRE ATT&CK T1562 Defense Evasion. Trigger keywords: EDR bypass, AV bypass, evasion, unhook, direct syscall, indirect syscall, Hell's Gate, Halo's Gate, Tartarus Gate, ETW patch, AMSI patch, call stack spoofing, hardware breakpoint Blindside, MITRE T1562, ntdll unhook, kernel callback, CrowdStrike bypass, Defender bypass, Sentinel One bypass, Elastic Defend, Sysmon evasion, PPID spoof, Sleep mask, Process Hollowing, Reflective DLL.
Olares Files via olares-cli files — browse known paths; upload or download file bytes; edit, share, mount SMB/NFS, compress/extract archives, and manage Seafile sync across Drive/cache/external/cloud. Use for Olares Files and LarePass Files operations, not URL/yt-dlp/torrent download tasks (olares-knowledge).
Add and configure in-game voice chat and text chat for Unity multiplayer games using Unity Vivox. Covers microphone setup and mic permissions on Android/iOS, voice activity detection (VAD) tuning, voice volume and mute controls in a settings UI (VoiceVadMinimumVolume, mic slider, mute button, speaking indicator), proximity/3D spatial voice for FPS/co-op games, team/party/lobby/guild voice channels, push-to-talk, muting self and other players, whisper/direct messages, in-game text chat, and Vivox SDK init + Unity Authentication sign-in. Use when the user asks to add voice chat, voice comms, microphone/mic support, a voice-chat settings UI, mute button, VAD threshold, push-to-talk, proximity or spatial voice, team voice, party chat, lobby chat, direct messages, or mentions Vivox, VivoxService, com.unity.services.vivox, JoinGroupChannelAsync, JoinPositionalChannelAsync, LoginAsync, or migrating from legacy Vivox (Client.Instance / LoginSession / AccountId).
This skill is used when users want to find plugins for DeepSeek Harness: such as asking 'Are there any plugins that can...', 'Help me install XX', or 'What interesting things are there in the ecosystem'. It discovers public repositories across individuals and organizations from the `dsh-plugin` topic on GitHub, filters candidates, waits for user confirmation, then determines the installation method from the repository declaration and verifies the mounting. It only handles finding and installing plugins; for developing new plugins, redirect to `make-dsh-plugin`.
Use this skill when the user wants a .pptx with smooth cross-slide animation — PowerPoint Morph transitions, Keynote-style continuous motion, shapes that grow / move / rotate as the slide advances. Trigger on: 'morph', 'morph transition', 'smooth transition', 'continuous animation across slides', 'Keynote-style transition', 'animated slide sequence', 'shape continuity across slides'. Output is a single .pptx. This skill is a scene layer on top of officecli-pptx — inherits every pptx v2 rule (visual floor, grid, palettes, connector canon, Delivery Gate 1–5a). DO NOT invoke for a generic deck, pitch deck, or board review without cross-slide motion — route those to officecli-pptx base or officecli-pitch-deck.
Audit and optimize headings across AEM Edge Delivery Services pages for search intent, hierarchy, and consistency. Extracts all headings (H1-H6), evaluates uniqueness, keyword alignment, specificity, and structural correctness, then generates optimized heading suggestions per page. Use when improving on-page SEO, fixing heading hierarchy issues, or standardizing heading patterns across a site.
Use when writing, reviewing, debugging, or documenting LanceDB pipelines in Python or TypeScript, especially code that should work across local LanceDB OSS tables and remote LanceDB Enterprise/Cloud tables. Helps avoid non-portable full-table materialization, choose idiomatic query/search patterns, apply LanceDB performance defaults for ingestion, indexing, filtering, and diagnostics, and resolve connections to the remote server for Enterprise-only operations such as jobs.
Identify opportunities and risks from changes in prosperity, prices, orders, inventory, and profits across the upstream and downstream of the industrial chain, helping to determine which links are benefiting, under pressure, or about to transmit impacts. Suitable for industrial chain research, prosperity tracking, and chain-based stock selection.
Interact with GitHub, GitLab, Gitea, Forgejo, Codeberg, and Bitbucket repositories through one CLI. Use instead of `gh` or `glab` when the git remote is not github.com, when working against a self-hosted forge, or when the same workflow needs to run unchanged across forges. Covers pull/merge requests, issues, releases, CI pipelines, labels, and repo management.
视频处理，涵盖视频画质增强、视频理解、字幕擦除等能力。包含能力：analyze-video-highlights, analyze-video-storyline, asr-subtitles, enhance-video, enhance-video-generative, erase-video-subtitle, erase-video-subtitle-pro, generate-highlights-microdrama, generate-highlights-minigame, matte-greenscreen-video, matte-portrait-video, probe-video-metadata, segment-scenes, video-ocr。当用户需要使用 video 域的 MediaKit CLI 能力时触发。
Focused Signals scout for PostHog setup health. Reads the project's active health issues — the deterministic findings of PostHog's own health checks (no live events, outdated SDKs, missing reverse proxy, absent web vitals, ingestion warnings, failing data-warehouse models, and more) — and decides which are genuinely worth surfacing. Unlike a one-signal-per-issue push, it bundles kind-clusters into a single finding, weights by real blast radius (cross-referencing actual event volume and reach), and prioritizes issues an agent can resolve via the MCP. Emits only above the confidence bar; otherwise writes durable memory and closes out empty. Self-contained peer in the signals-scout-* fleet — no dependencies on other skills.
Orchestrate a complete competitive analysis across six steps, from landscape to strategic direction. Use when you need the full picture, not a single scan or card.