411 skills · sorted by relevance
Write engaging PR titles and descriptions for any forge (GitHub today; Bitbucket planned). Use when creating or updating PRs. Leads with narrative paragraphs and reaches for lists, tables, and diagrams when content is genuinely structured.
The English summary is being prepared. Showing the original description.
Process multimedia files with FFmpeg (video/audio encoding, conversion, streaming, filtering, hardware acceleration) and ImageMagick (image manipulation, format conversion, batch processing, effects, composition). Use when converting media formats, encoding videos with specific codecs (H.264, H.265, VP9), resizing/cropping images, extracting audio from video, applying filters and effects, optimizing file sizes, creating streaming manifests (HLS/DASH), generating thumbnails, batch processing images, creating composite images, or implementing media processing pipelines. Supports 100+ formats, hardware acceleration (NVENC, QSV), and complex filtergraphs.
The English summary is being prepared. Showing the original description.
Use when the user wants a complete SPSS or SPSS-MCP empirical research workflow: organize source data, prepare datasets, design variables and models, run SPSS analyses, export Chinese result paragraphs and tables, write a Chinese LaTeX paper, and compile the final PDF.
The English summary is being prepared. Showing the original description.
Review owned or authorized code for security using structure-first evidence: AST/structure maps, call graphs, complexity, Source/Sink flow, and defensive findings. Use when asked for security review, vulnerability review, AST structure map review, SAST triage, Source/Sink, taint flow, parser/scanner hardening, CI/CD security, LLM/agent tool boundary review, 脆弱性レビュー, 構造マップ, セキュリティレビュー.
The English summary is being prepared. Showing the original description.
"Calculate network centrality metrics to identify important nodes in graphs. Use this skill when the user needs to find key influencers, critical infrastructure nodes, or central actors in a network — even if they say 'who is most important in this network', 'key nodes', or 'network influence measurement'.".
The English summary is being prepared. Showing the original description.
Analyze story dependencies, detect issues, and generate visual dependency graphs
The English summary is being prepared. Showing the original description.
Replace sentence-by-sentence revised or paraphrased text back into an original paper or document while preserving the original formatting, typography, paragraph settings, citation layout, and document conventions as the source of truth. Use when the user provides revised text that maps back to original sentences, paragraphs, sections, or the whole document, but may also contain clear local sentence merges or splits, and asks to replace it back into the source, keep the original formatting, do sentence-by-sentence replacement, preserve original formatting, or only swap wording without rewriting the document. Only allow minimal edits to the rewritten text when fixing citation formatting, restoring protected original content, restoring the original person reference, or minimally splitting/merging text back into original sentence slots; otherwise do not improve grammar, style, logic, or wording.
The English summary is being prepared. Showing the original description.
Summarizes Google Cloud Data Lineage graphs to help users debug data quality issues and understand data provenance for BQ/GCS. Use when summarizing upstream and downstream data flows, and presenting complex lineage data as an intuitive Markdown report. Don't use for generic BigQuery queries, editing lineage relationships, or downstream deprecation. Don't use for downstream blast-radius impact analysis (use datalineage-bigquery-asset-impact-analysis skill instead).
The English summary is being prepared. Showing the original description.
Performs static analysis of binary code using radare2 and Ghidra — function enumeration, cross-reference tracing, decompilation, and control flow graphs without executing the binary. Use when disassembling or decompiling code, mapping functions, tracing data flow, or building hypotheses before dynamic verification.
The English summary is being prepared. Showing the original description.
Transform reference photographs and visually dense images into sparse, recognizable, high-saturation flat-vector-style illustrations through semantic compression rather than literal tracing. Use when the user asks for photo-to-flat illustration, photo-to-vector-style redraw, 照片转扁平插画, 无渐变高饱和插画, iconification, visual simplification, composition-preserving abstraction, a consistent minimal illustration set, or revisions that remove gradients, glow, texture, blur, clutter, text, logos, numbers, or UI. Default to human-perceived semantic complexity 6 out of 10 or lower, fixed-HSB solid fills, crisp boundaries, and no gradients or light-halo effects.
The English summary is being prepared. Showing the original description.
Write engaging PR titles and descriptions for any forge (GitHub today; Bitbucket planned). Use when creating or updating PRs. Leads with narrative paragraphs and reaches for lists, tables, and diagrams when content is genuinely structured.
The English summary is being prepared. Showing the original description.
Stress-tests a fuzzy or vague feature idea before any PRD, spec, or ticket is written. TRIGGER when: the user has a fuzzy feature idea — one or two paragraphs, vague on users / scope / success — and wants to harden it, or says "grill / stress-test / pressure-test this idea." DO NOT TRIGGER when: the idea is already turned into a spec or PRD; bug fixes or refactors; the idea is hardened and you are ready to write the PRD → creating-prd.
The English summary is being prepared. Showing the original description.
Run work as an explicit event-driven state machine executed by subagents. The orchestrator is the runtime from the canonical loop — `state, effects = init(machine); execute(effects); while state is active: event = nextEvent(); state, effects = transition(machine, state, event); execute(effects); return state.output`. All routing judgment is authored ONCE, at plan time, into a machine file (states, event alphabet, transition table, budgets, final states); at runtime the orchestrator does pure table lookups and dispatches effects — it never decides, never authors, never ingests artifacts. Subagent/sync protocol is the timeboxed-iterating one: role prompts scaffolded once to disk and dispatched BY PATH, an initialiser preamble every subagent reads first, a self-populating cheatsheet, per-unit files, tiny structured returns, independent measurement gate. Use when the user says "workmachine", "run this as a state machine", "state-machine this", or when a goal has a small number of clearly named phases with explicit outcomes (built / passed / failed / blocked) and you want the routing to be auditable rather than judged on the fly. For clock-driven loops use timeboxed-iterating; for wide graphs with judged edge criteria use workgraph.
The English summary is being prepared. Showing the original description.
Generate Mermaid architecture diagrams from your codebase. Produces C4 context and container diagrams, sequence diagrams for key flows, ER diagrams from database schemas, and module dependency graphs. Use when you need architecture diagrams, system diagrams, database ERD, sequence diagrams, dependency visualization, or C4 model diagrams.
The English summary is being prepared. Showing the original description.
Convert unstructured documents into LLM-ready structured data. Supports PDF, Word, PPT, and images; extracts paragraphs, formulas, tables, charts, and other elements in one step; generates up to 8 levels of headings; and outputs Markdown organized in reading order. Useful for field extraction, comparison and validation, knowledge retrieval, and intelligent Q&A.
The English summary is being prepared. Showing the original description.
Comprehensive guide for creating software diagrams using Mermaid syntax. Use when users need to create, visualize, or document software through diagrams including class diagrams (domain modeling, object-oriented design), sequence diagrams (application flows, API interactions, code execution), flowcharts (processes, algorithms, user journeys), entity relationship diagrams (database schemas), C4 architecture diagrams (system context, containers, components), state diagrams, git graphs, pie charts, gantt charts, or any other diagram type. Triggers include requests to "diagram", "visualize", "model", "map out", "show the flow", or when explaining system architecture, database design, code structure, or user/application flows.
The English summary is being prepared. Showing the original description.
Elite AI context engineering specialist mastering dynamic context management, vector databases, knowledge graphs, and intelligent memory systems.
The English summary is being prepared. Showing the original description.
Data structures and algorithms for AI agent episodic memory. Covers vector stores (HNSW, IVF, PQ), temporal indexing, knowledge graphs with triple stores, hierarchical summarization, forgetting curves, working/long-term/ procedural memory, and memory consolidation. Deep analysis of MemGPT/Letta, Zep/Graphiti, Mem0, and the Stanford generative agents memory architecture. Teaches the CS fundamentals behind how agents remember, retrieve, and forget. Activate on: "agent memory", "episodic memory", "vector search algorithm", "HNSW", "memory retrieval", "forgetting curve", "knowledge graph memory", "MemGPT", "Letta", "Zep", "Mem0", "memory consolidation", "temporal retrieval", "agent long-term memory", "memory layer". NOT for: conversation protocol design (use agent-conversation-protocols), agent infrastructure selection (use agentic-infrastructure-2026), building RAG pipelines (use ai-engineer).
The English summary is being prepared. Showing the original description.
Builds, validates, schedules, and dynamically modifies DAG execution graphs. Decomposes problems into nodes with dependencies, performs topological sorting, detects cycles, resolves conflicts, and schedules wave-based parallel execution. Use when designing a DAG structure, validating dependencies, planning execution order, or modifying a DAG at runtime. Activate on "build DAG", "plan workflow", "DAG dependencies", "topological sort", "schedule execution", "modify DAG", "replan". NOT for executing DAGs (use dag-runtime), validating outputs (use dag-quality), or matching skills to nodes (use dag-skills-matcher).
The English summary is being prepared. Showing the original description.
Analyze hierarchical DAG-like systems by separating undirected substrate from ordering metadata, then classifying diamonds, mixers, shortcuts, and hidden cycle structure. Use for workflow architecture, citation or genealogy DAG comparison, and information-flow diagnosis. NOT for ordinary cycle detection in arbitrary graphs, one-node runtime debugging, or systems with no real ordering constraint.
The English summary is being prepared. Showing the original description.
Graph algorithms for detecting and resolving cycles in directed graphs and workflow definitions
The English summary is being prepared. Showing the original description.
Track complex, multi-session work with dependency graphs using bd (beads) issue tracker. Use when work spans multiple sessions, has complex dependencies, or requires persistent context across compaction cycles. For simple single-session linear tasks, TodoWrite remains appropriate.
The English summary is being prepared. Showing the original description.
Process multimedia files with FFmpeg (video/audio encoding, conversion, streaming, filtering, hardware acceleration) and ImageMagick (image manipulation, format conversion, batch processing, effects, composition). Use when converting media formats, encoding videos with specific codecs (H.264, H.265, VP9), resizing/cropping images, extracting audio from video, applying filters and effects, optimizing file sizes, creating streaming manifests (HLS/DASH), generating thumbnails, batch processing images, creating composite images, or implementing media processing pipelines. Supports 100+ formats, hardware acceleration (NVENC, QSV), and complex filtergraphs.
The English summary is being prepared. Showing the original description.
Semantic search, grep, and Q&A across codebases and documentation indexed in CodeAlive. Use when the user mentions "CodeAlive", asks to list or get data sources, list indexed repositories, search code or docs across remote repos, fetch artifact content, or trace call graphs across repositories.
The English summary is being prepared. Showing the original description.