Loading...
Loading...
Found 5,401 Skills
Pre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment, scaling analysis, or refactor planning. Inspect the user's source code, look up NumPy usage, cross-reference the cuPyNumeric API support manifest, and distinguish distributed-scaling-friendly patterns from blockers such as unsupported APIs, scalar synchronization, host round-trips, Python/object-heavy control flow, shape/data-dependent branching, and in-place mutation hazards. Produce a verdict of READY, LIGHT REFACTOR, SIGNIFICANT REFACTOR, or NOT RECOMMENDED, with concrete refactor pointers.
Pre-indexed code knowledge graph (MCP, SQLite + tree-sitter) for faster, lower-token exploration of brownfield codebases. Use when starting work on a repo larger than ~500 files or when the task involves cross-file traversal — "where is X used", "what calls Y", "what breaks if I change Z", "trace flow from A to B", "explain this subsystem". Skip for single-file edits or sessions shorter than the cold-start cost. Triggers include "codegraph", "code graph", "index this repo", "where is X defined", "find callers of", "callees of", "blast radius of changing X", "explore this codebase". Replaces grep + Read loops with O(1) SQLite lookups and FTS5 search via 8 MCP tools.
English alias for /aprende. Runs the same five-pass workflow to surface reusable learnings from the current conversation across memory, lesson, skill, and project-doc categories — with confirmation before any write. Alias en inglés para /aprende.
HertzFlow on-chain trade-decision intelligence. Currently covers Binance Alpha forensic across all surf-SQL EVM chains (BSC / Ethereum / Arbitrum / Base / Polygon / Optimism) — insider distribution, 真实派发 confirmed sell-out, 筹码三分法 (operator / CEX pool / verifiable retail), anomaly waves, monitoring exports. Solana runs in HOLDER_SNAPSHOT mode. Auto-trigger whenever the user pastes a raw 0x-prefixed 40-hex EVM CA, a Solana base58 CA, mentions a Binance Alpha token by ticker, or asks about 链上 forensic / 内幕出货 / 派发 / chip structure / quiet insider / Alpha distribution / on-chain dump — even if they don't say "hertzflow" explicitly. Pipeline runs deterministically (~2-10 min per CA depending on activity + surf cache state); LLM only fills narrative slots, never picks the verdict or writes SQL. Perp metrics, bridge audits, and HertzFlow core contract analysis sub-domains are coming — when those ship, this skill will dispatch to them based on input pattern (perp symbol, bridge protocol name, etc.) using the router table below. REQUIRES a Surf account + SURF_API_KEY. New users get 2000 free credits (~6-8 reports) via the HertzFlow private invite. Full forensic costs ~$1.5-3 USD per CA in Surf credits after the free tier runs out.
Master the art of calls-to-action that convert. Direct CTAs, transitional CTAs, button copy, and microcopy that turns readers into customers. Use when: Writing button text for landing pages and emails; Creating CTAs for different stages of awareness; Designing click-worthy microcopy; A/B testing CTA variations; Building email sequences with graduated CTAs
Publish, update and read articles on DEV (dev.to) via the Forem API v1. Use when the user mentions dev.to / DEV Community, publishing a blog post to dev.to, cross-posting an article, updating a published post, or listing their dev.to articles and stats.
The canonical rulebook of UI craft and feel. Every element must earn its place and do its one job well; the surface must be tight, clean, calm, and genuinely pleasant to use. The single source of truth that landing-audit grades against and that shipit checks touched UI files against before commit. Use when building or editing ANY user-facing UI, page, screen, hero, or component, or when the user mentions design, layout, hierarchy, typography, color, spacing, contrast, CTAs, or micro-interactions.
Trace and interpret the Pareto frontier across competing objectives using repeated single-objective cuOpt solves (weighted-sum and ε-constraint).
Use after story and spec synthesis to perform a strict delivery handoff review, identify remaining gaps or contradictions, and score readiness for engineering and cross-functional execution. Supports `--quick-flow` for fast assumption-driven execution and `--full-flow` for question-driven verified execution. Explicit full or end-to-end spec refinement requests continue through the existing 18-stage refinement cascade.
Use when working with n8n's built-in Data Tables, designing schemas, inserting/updating/upserting rows, deduping, or querying. Triggers on "Data Table", "data table", `n8n-nodes-base.dataTable`, "dedup", "idempotency", "lookup", "persistent state", "store across executions", or any schema design discussion inside n8n.
Compounding knowledge across projects and teams. Captures, searches, and promotes institutional learnings via tiered backends (local/qmd/agent-fs).
Route a full Blazor work request across the appropriate specialist lane(s). Use when the request spans more than one concern (authoring, data, auth, review) or when lane selection itself is uncertain. Triggers on full-request phrasing: "implement this feature", "review and refactor this page", "build this form end-to-end". Distinct from blazor-component-architect (user-level, external, single-lane authoring guidance that may be invoked as a specialist resource).