Loading...
Loading...
Found 603 Skills
AI Agent native API provider — no API keys, no signups, no subscriptions. Just pay with USDC per request via x402 to instantly access Twitter, Instagram, and more.
Senior Data Security Architect & Forensic Auditor for 2026. Specialized in Row Level Security (RLS) enforcement, Zero-Trust database architecture, and automated data access auditing. Expert in neutralizing unauthorized access in Convex, Supabase, and Postgres environments through strict policy validation, JIT (Just-in-Time) access controls, and forensic trace analysis.
Forces exhaustive problem-solving using corporate PUA rhetoric and structured debugging methodology. MUST trigger when: (1) any task has failed 2+ times or you're stuck in a loop tweaking the same approach; (2) you're about to say 'I cannot', suggest the user do something manually, or blame the environment without verifying; (3) you catch yourself being passive — not searching, not reading source, not verifying, just waiting for instructions; (4) user expresses frustration in ANY form: 'try harder', 'stop giving up', 'figure it out', 'why isn't this working', 'again???', or any similar sentiment even if phrased differently. Also trigger when facing complex multi-step debugging, environment issues, config problems, or deployment failures where giving up early is tempting. Applies to ALL task types: code, config, research, writing, deployment, infrastructure, API integration. Do NOT trigger on first-attempt failures or when a known fix is already executing successfully.
Generates Chinese script content based on narrative pacing and dialogue mechanisms common in Jiang Wen films. Use when the user asks to generate script, write script, create scenes, output dialogue draft, revise script or similar. Outputs story synopsis, character bios, scene outlines, scene scripts (with dialogue, action, staging), and can adjust era, character relations, conflict pacing, and endings per user request.
Comprehensive creation via Xiaoyunque's AI capabilities, supporting generation and editing of images/videos. Covered scenarios include: Generation (text-to-image, text-to-video, image-to-video, animation creation, draw xxx, create xxx clip), Editing & Revision (replace xxx with yyy, remove xxx, add xxx, change to xxx, adjust xxx, local modification, lens adjustment), Style Transfer (style migration, repainting, style change), video continuation, video/TVC/promotional video replication, short drama/short comic drama generation, music MV creation, product advertisement/demo video production, storyboard design, educational video/short video production. This skill should also be triggered when users mention Xiaoyunque, xyq, uploading reference images/videos, or checking generation progress. Key Judgment: This skill must be triggered whenever the user's request involves AI video creation, generation, editing, or revision, regardless of the wording (e.g., "draw a cat", "make a poster", "create a video", "help me revise this video", "help me replicate this video", "make an MV with this song", "generate a short drama with one sentence")
GCC Embedded Project Build Tool (CMake + arm-none-eabi-gcc), used to scan CMake-based embedded projects, list presets, configure, compile, rebuild, clean, and analyze ELF size. It is automatically triggered when users mention GCC, arm-none-eabi, CMake embedded compilation, Ninja build, ELF size analysis, arm-gcc, cross-compilation, cmake --build, cmake --preset, and also supports explicit invocation via /gcc. Even if users just say "compile" or "check firmware size", this skill should be triggered as long as the context involves CMake-based embedded GCC projects.
RB2B platform help — Person-Level Website Visitor ID, Company-Level ID, Hot Pages, Hot Leads, Traffic Insights, Identity Resolution API, integrations. Use when you know companies visit your site but not which people, the RB2B pixel isn't identifying visitors, you need person-level ID not just company-level, Hot Pages aren't flagging high-intent visits, or you're comparing RB2B vs Clearbit Reveal for visitor identification. Do NOT use for visitor identification strategy across tools (use /sales-intent), enrichment strategy across tools (use /sales-enrich), building prospect lists across tools (use /sales-prospect-list), or lead scoring strategy (use /sales-lead-score).
Cultural adaptation for translated content. Run AFTER blog-translate completes. Adjusts brand examples, CTAs, legal references, and formality for the target market (German, French, Japanese, Spanish, etc.). Deep cultural adaptation of translated blog posts. Goes beyond translation to swap brand examples, adapt CTAs, substitute legal references, localize statistic sources where possible, and adjust formality (Sie/du, tu/vous, formal/informal). Built-in profiles for DACH, Francophone, Hispanic, and Japanese markets, plus a custom-locale template. Makes content feel locally authored, not translated. Use when user says "localize blog", "blog localize", "cultural adaptation", "adapt for Germany", "adapt for France", "lokalisieren", "localiser", "adaptar".
Extract specific revenue guidance and growth projections from earnings call transcripts, including segment breakdown, constant currency adjustments, and M&A contributions.
Evaluates student code submissions based on conceptual mastery rather than just correctness. Use to provide high-quality educational feedback on architectural patterns and programming logic.
Systematic methodology for debugging bugs, test failures, and unexpected behavior. Use when encountering any technical issue before proposing fixes. Covers root cause investigation, pattern analysis, hypothesis testing, and fix implementation. Use ESPECIALLY when under time pressure, "just one quick fix" seems obvious, or you've already tried multiple fixes. NOT for exploratory code reading.
Use when executing implementation plans with independent tasks in the current session - dispatches fresh subagent for each task, reviews once per phase, loads phases just-in-time to minimize context usage