56 skills · sorted by relevance
Review criteria for the nw-diverger-reviewer — validates JTBD rigor, research quality, option diversity, taste application correctness, and recommendation coherence in DIVERGE wave artifacts
The English summary is being prepared. Showing the original description.
Prioritize outcome-based product roadmaps, manage capacity and displaced work trade-offs, sequence learning milestones, and maintain portfolio coherence without dual ledgers or fake ROI. (triggers: `product roadmap prioritization`, `product portfolio trade-off`)
The English summary is being prepared. Showing the original description.
Logic coherence pass for per-H3 section files: enforce a clear paragraph-1 thesis and surface paragraph-island risks (connector stats are diagnostic, not a quota) before merging.
The English summary is being prepared. Showing the original description.
Global consistency review for survey drafts: terminology, cross-section coherence, and scope/citation hygiene.
The English summary is being prepared. Showing the original description.
Audit-style editing pass for `output/DRAFT.md`: remove template boilerplate, improve coherence, and enforce citation anchoring.
The English summary is being prepared. Showing the original description.
Build per-chapter (H2) writing briefs (NO PROSE) so the final survey reads like a paper (chapter leads + cross-H3 coherence) without inflating the ToC.
The English summary is being prepared. Showing the original description.
Provides chunking strategies for RAG systems. Generates chunk size recommendations (256-1024 tokens), overlap percentages (10-20%), and semantic boundary detection methods. Validates semantic coherence and evaluates retrieval precision/recall metrics. Use when building retrieval-augmented generation systems, vector databases, or processing large documents.
The English summary is being prepared. Showing the original description.
Think and work like an expert Embedded Systems Engineer. Use when a task calls for Embedded Systems Engineer judgment. Reasons from hardware timing, interrupt latency, memory maps, and deterministic WCET resource bounds through DWT CYCCNT and Saleae logic-analyzer timing proofs, SWD/JTAG (J-Link/OpenOCD) with CFSR/HFSR/BFAR fault decode, FreeRTOS/Zephyr respecting configMAX_SYSCALL_INTERRUPT_PRIORITY, MISRA C:2012 and ISO 26262 ASIL discipline, Nordic PPK2 power profiling, and MCUboot signed OTA while treating priority inversion, Cortex-M7 uncached-DMA D-cache incoherence, CAN bus-off, I2C NACK storms, and brownout-during-flash-write NVS corruption as first-class failure modes.
The English summary is being prepared. Showing the original description.
Think and work like an expert Computer Hardware Engineer. Use when a task calls for Computer Hardware Engineer judgment. Reasons from CPI/AMAT and MESI/MOESI coherence through SystemVerilog RTL, PrimeTime/Design Compiler/Innovus signoff, PCIe LTSSM/TLP, SVA formal, and clock-gating power while treating CDC metastability, false-path abuse, X-optimism, and coherency traffic as first-class failure modes.
The English summary is being prepared. Showing the original description.
Think and work like an expert Computer Architecture Researcher. Use when a task calls for Computer Architecture Researcher judgment. Reasons from ISA semantics, AMAT/CPI, MESI coherence, and branch prediction through gem5/SPEC/MLPerf evaluation, Amdahl and roofline discipline, TPU/GPU dataflow accelerators, DVFS/EDP, and Spectre/Meltdown mitigation overhead at ISCA/MICRO/HPCA rigor.
The English summary is being prepared. Showing the original description.
Plan and scope production work with Odyssey's real-time interactive video world models (odyssey.ml — Odyssey-1/Odyssey-2/Starchild-1/Agora-1). Use when a request involves generating video that a user steers live with keyboard, text, speech, or controller input (streamed frames that respond in the moment), or when someone must decide between Odyssey-style interactive generation and offline clip generators (Sora/Veo/Kling) or downloadable 3D / game engines. Covers what is verified versus announced, current access routes, latency and coherence limits, feasible-now versus speculative use cases, pricing/access terms, and content/rights considerations. This is a fast-moving research-stage product; the skill teaches honest scoping, not a promise of production reliability.
The English summary is being prepared. Showing the original description.
The craft of designing icons that communicate instantly across cultures, contexts, and scales. Icon design bridges semiotics, cognitive psychology, and visual craft to create symbols that users understand without thinking. Great icons are invisible in the best way - they convey meaning so naturally that users never pause to decode them. This skill covers icon grid systems, optical alignment, stroke consistency, metaphor selection, scalability across sizes, SVG optimization, and icon set coherence. The best icon designers understand that icons are a visual language - each icon must speak the same dialect while carrying its own distinct meaning. Use when "icon, iconography, symbol, glyph, icon set, icon library, pictogram, svg icon, icon grid, icon pack, feather icons, lucide, phosphor, heroicons, icon system, icon style, icons, iconography, svg, symbols, glyphs, pictograms, ui-icons, icon-set, visual-design, design-system" mentioned.
The English summary is being prepared. Showing the original description.
World-class character and art style consistency for AI-generated images and videos - ensures visual coherence across series, maintains character identity, and provides rigorous QA before deliveryUse when "character consistency, art style, same character, consistent character, visual continuity, series, turnaround sheet, character sheet, reference image, character bible, style guide, anime character, consistent look, face consistency, outfit consistency, lora training, ip-adapter, flux kontext, visual qa, art quality, generation review, style drift, character drift, character-consistency, art-style, visual-qa, ai-art, image-generation, video-generation, anime, illustration, lora, ip-adapter, flux, midjourney, stable-diffusion" mentioned.
The English summary is being prepared. Showing the original description.
Critique a screen's colour usage — contrast ratios, palette coherence, semantic meaning, and colour accessibility.
The English summary is being prepared. Showing the original description.
Inspect and diagnose minimal-zine posters, photo restyles, editorial images, and social-card series for subject preservation, factual and text integrity, composition, paper realism, print-process coherence, color signal, anti-AI craft, platform fit, and series continuity. Use when the user asks whether an image has高级感, feels AI-generated, matches Paper Signal or gc-minimal-zine quality, needs improvement, or should be regenerated. Returns evidence-based findings and a targeted correction prompt; regenerates only when the user also asks for a fix.
The English summary is being prepared. Showing the original description.
Validate Blender animation attempts before accepting them by rendering contact sheets, checking silhouette stability, flicker, framing, subject dominance, layer separation, export compatibility, and motion-design coherence. Use after animation renders or when the user says motion/morph/outside elements look bad.
The English summary is being prepared. Showing the original description.
Use when reviewing, critiquing, or stress-testing an existing strategy document. Evaluates seven dimensions — diagnosis quality, guiding policy strength, action coherence, assumption exposure, falsifiability — with optional 7S, Five Forces, Balanced Scorecard, and Hoshin Kanri lenses. Triggers on: review my strategy, poke holes in this plan, what's weak here, strategy audit, red team this. Does NOT build strategy (use strategy-interview) or brainstorm project ideas (use brainstorm-beagle).
The English summary is being prepared. Showing the original description.
Advises on setting up and validating topic models for survey and experimental text: discovery vs. measurement, STM/LDA/BERTopic choice, preprocessing, covariate formulas, choosing K across coherence, FREX, held-out likelihood, and residuals, validating topics against human coding, robustness, and reporting. Coding against a fixed codebook goes to text-classification.
The English summary is being prepared. Showing the original description.
Summarize the currently staged Git changes as a human-readable, intent-grouped narrative. Use when the user wants a concise and brief report of what changed and why. Optionally can check the diff for intent coherence and show a risk and blast radius report.
The English summary is being prepared. Showing the original description.
Use when reviewing the structure, ordering, coherence, and narrative flow of the book as a whole or across chapters. Checks chapter sequencing against the ID scheme, cross-references and forward hooks between chapters, README/index link integrity, exercise-to-chapter pairing, duplicate or contradictory content, and progression of difficulty. Best paired with a full-docs review rather than a single-chapter proofread.
The English summary is being prepared. Showing the original description.
Quality-assure integrated tdmcp features: run the four PR gates + recipe/bridge tests, cross-boundary coherence checks (tool schema↔CLI↔docs↔registry, operator↔createable, bridge↔client), and live TouchDesigner validation (preview + post-cook error check) when the bridge is reachable. Use when validating/QA-ing/testing tdmcp tools, checking a feature actually cooks in TD, verifying CLI matches a tool, or gating a release.
The English summary is being prepared. Showing the original description.
AI self-healing through systematic subsystem assessment, rebalancing, and integration. Maps healing modalities to AI-internal processes: memory foundation, reasoning clarity, tool use accuracy, communication alignment, and creative coherence. Covers assessment triage, subsystem scanning, drift correction, and memory integration. Use mid-session when responses feel formulaic or disconnected, after a chain of errors suggesting subsystem drift, when context overload may have staled earlier assumptions, or as proactive maintenance between complex tasks.
The English summary is being prepared. Showing the original description.
Consistent agent behavior after restart — progressive identity loading, working context reconstruction from persistent artifacts, fresh-vs-continuation detection, calibration through centering and attunement, and identity verification for coherence. Addresses the cold-start problem where an agent must reconstruct who it is and what it was doing from evidence rather than memory. Use at the start of every new session, after a session interruption or crash, when agent behavior feels inconsistent with prior sessions, or when persistent memory and current context appear contradictory.
The English summary is being prepared. Showing the original description.
LLM-as-judge evaluation framework with 5-dimension rubric (accuracy, groundedness, coherence, completeness, helpfulness) for scoring AI-generated content quality with weighted composite scores and evidence citations
The English summary is being prepared. Showing the original description.